Dissertations / Theses on the topic '3D point cloud representation'
To see the other types of publications on this topic, follow the link: 3D point cloud representation.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic '3D point cloud representation.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Diskin, Yakov. "Dense 3D Point Cloud Representation of a Scene Using Uncalibrated Monocular Vision." University of Dayton / OhioLINK, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1366386933.
2
Diskin, Yakov. "Volumetric Change Detection Using Uncalibrated 3D Reconstruction Models." University of Dayton / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1429293660.
3
Morell, Vicente. "Contributions to 3D Data Registration and Representation." Doctoral thesis, Universidad de Alicante, 2014. http://hdl.handle.net/10045/42364.
Abstract:
Nowadays, new computers generation provides a high performance that enables to build computationally expensive computer vision applications applied to mobile robotics. Building a map of the environment is a common task of a robot and is an essential part to allow the robots to move through these environments. Traditionally, mobile robots used a combination of several sensors from different technologies. Lasers, sonars and contact sensors have been typically used in any mobile robotic architecture, however color cameras are an important sensor due to we want the robots to use the same information that humans to sense and move through the different environments. Color cameras are cheap and flexible but a lot of work need to be done to give robots enough visual understanding of the scenes. Computer vision algorithms are computational complex problems but nowadays robots have access to different and powerful architectures that can be used for mobile robotics purposes. The advent of low-cost RGB-D sensors like Microsoft Kinect which provide 3D colored point clouds at high frame rates made the computer vision even more relevant in the mobile robotics field. The combination of visual and 3D data allows the systems to use both computer vision and 3D processing and therefore to be aware of more details of the surrounding environment. The research described in this thesis was motivated by the need of scene mapping. Being aware of the surrounding environment is a key feature in many mobile robotics applications from simple robotic navigation to complex surveillance applications. In addition, the acquisition of a 3D model of the scenes is useful in many areas as video games scene modeling where well-known places are reconstructed and added to game systems or advertising where once you get the 3D model of one room the system can add furniture pieces using augmented reality techniques. In this thesis we perform an experimental study of the state-of-the-art registration methods to find which one fits better to our scene mapping purposes. Different methods are tested and analyzed on different scene distributions of visual and geometry appearance. In addition, this thesis proposes two methods for 3d data compression and representation of 3D maps. Our 3D representation proposal is based on the use of Growing Neural Gas (GNG) method. This Self-Organizing Maps (SOMs) has been successfully used for clustering, pattern recognition and topology representation of various kind of data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models without considering time constraints. Self-organising neural models have the ability to provide a good representation of the input space. In particular, the Growing Neural Gas (GNG) is a suitable model because of its flexibility, rapid adaptation and excellent quality of representation. However, this type of learning is time consuming, specially for high-dimensional input data. Since real applications often work under time constraints, it is necessary to adapt the learning process in order to complete it in a predefined time. This thesis proposes a hardware implementation leveraging the computing power of modern GPUs which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). Our proposed geometrical 3D compression method seeks to reduce the 3D information using plane detection as basic structure to compress the data. This is due to our target environments are man-made and therefore there are a lot of points that belong to a plane surface. Our proposed method is able to get good compression results in those man-made scenarios. The detected and compressed planes can be also used in other applications as surface reconstruction or plane-based registration algorithms. Finally, we have also demonstrated the goodness of the GPU technologies getting a high performance implementation of a CAD/CAM common technique called Virtual Digitizing.
4
Orts-Escolano, Sergio. "A three-dimensional representation method for noisy point clouds based on growing self-organizing maps accelerated on GPUs." Doctoral thesis, Universidad de Alicante, 2013. http://hdl.handle.net/10045/36484.
Abstract:
The research described in this thesis was motivated by the need of a robust model capable of representing 3D data obtained with 3D sensors, which are inherently noisy. In addition, time constraints have to be considered as these sensors are capable of providing a 3D data stream in real time. This thesis proposed the use of Self-Organizing Maps (SOMs) as a 3D representation model. In particular, we proposed the use of the Growing Neural Gas (GNG) network, which has been successfully used for clustering, pattern recognition and topology representation of multi-dimensional data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models, without considering time constraints. It is proposed a hardware implementation leveraging the computing power of modern GPUs, which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). The proposed methods were applied to different problem and applications in the area of computer vision such as the recognition and localization of objects, visual surveillance or 3D reconstruction.
5
Zhao, Yongheng. "3D feature representations for visual perception and geometric shape understanding." Doctoral thesis, Università degli studi di Padova, 2019. http://hdl.handle.net/11577/3424787.
Abstract:
In this thesis, we first present a unified look to several well known 3D feature representations, ranging from hand-crafted design to learning based ones. Then, we propose three kinds of feature representations from both RGB-D data and point cloud, addressing different problems and aiming for different functionality.
With RGB-D data, we address the existing problems of 2D feature representation in visual perception by integrating with the 3D information. We propose an RGB-D data based feature representation which fuses object's statistical color model and depth information in a probabilistic manner. The depth information is able to not only enhance the discriminative power of the model toward clutters with a different range but also can be used as a constraint to properly update the model and reduce model drifting. The proposed representation is then evaluated in our proposed object tracking algorithm (named MS3D) on a public RGB-D object tracking dataset. It runs in real-time and produces the best results compared against the other state-of-the-art RGB-D trackers. Furthermore, we integrate MS3D tracker in an RGB-D camera network in order to handle long-term and full occlusion. The accuracy and robustness of our algorithm are evaluated in our presented dataset and the results suggest our algorithm is able to track multiple objects accurately and continuously in the long term.
For 3D point cloud, the current deep learning based feature representations often discard spatial arrangements in data, hence falling short of respecting the parts-to-whole relationship, which is critical to explain and describe 3D shapes. Addressing this problem, we propose 3D point-capsule networks, an autoencoder designed for unsupervised learning of feature representations from sparse 3D point clouds while preserving spatial arrangements of the input data into different feature attentions. 3D capsule networks arise as a direct consequence of our unified formulation of the common 3D autoencoders. The dynamic routing scheme and the peculiar 2D latent feature representation deployed by our capsule networks bring in improvements for several common point cloud-related tasks, such as object classification, object reconstruction and part segmentation as substantiated by our extensive evaluations. Moreover, it enables new applications such as part interpolation and replacement.
Finally, towards rotation equivariance of the 3D feature representation, we present a 3D capsule architecture for processing of point clouds that is equivariant with respect to the SO(3) rotation group, translation, and permutation of the unordered input sets. The network operates on a sparse set of local reference frames, computed from an input point cloud and establishes end-to-end equivariance through a novel 3D quaternion group capsule layer, including an equivariant dynamic routing procedure. The capsule layer enables us to disentangle geometry from the pose, paving the way for more informative descriptions and structured latent space. In the process, we theoretically connect the process of dynamic routing between capsules to the well-known Weiszfeld algorithm, a scheme for solving iterative re-weighted least squares (IRLS) problems with provable convergence properties, enabling robust pose estimation between capsule layers. Due to the sparse equivariant quaternion capsules, our architecture allows joint object classification and orientation estimation, which we validate empirically on common benchmark datasets.
6
Konradsson, Albin, and Gustav Bohman. "3D Instance Segmentation of Cluttered Scenes : A Comparative Study of 3D Data Representations." Thesis, Linköpings universitet, Datorseende, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-177598.
Abstract:
This thesis provides a comparison between instance segmentation methods using point clouds and depth images. Specifically, their performance on cluttered scenes of irregular objects in an industrial environment is investigated. Recent work by Wang et al. [1] has suggested potential benefits of a point cloud representation when performing deep learning on data from 3D cameras. However, little work has been done to enable quantifiable comparisons between methods based on different representations, particularly on industrial data. Generating synthetic data provides accurate grayscale, depth map, and point cloud representations for a large number of scenes and can thus be used to compare methods regardless of datatype. The datasets in this work are created using a tool provided by SICK. They simulate postal packages on a conveyor belt scanned by a LiDAR, closely resembling a common industry application. Two datasets are generated. One dataset has low complexity, containing only boxes.The other has higher complexity, containing a combination of boxes and multiple types of irregularly shaped parcels. State-of-the-art instance segmentation methods are selected based on their performance on existing benchmarks. We chose PointGroup by Jiang et al. [2], which uses point clouds, and Mask R-CNN by He et al. [3], which uses images. The results support that there may be benefits of using a point cloud representation over depth images. PointGroup performs better in terms of the chosen metric on both datasets. On low complexity scenes, the inference times are similar between the two methods tested. However, on higher complexity scenes, MaskR-CNN is significantly faster.
7
Cao, Chao. "Compression d'objets 3D représentés par nuages de points." Electronic Thesis or Diss., Institut polytechnique de Paris, 2021. http://www.theses.fr/2021IPPAS015.
Abstract:
Avec la croissance rapide du contenu multimédia, les objets 3D deviennent de plus en plus populaires. Ils sont généralement modélisés sous forme de maillages polygonaux complexes ou de nuages de points 3D denses, offrant des expériences immersives dans différentes applications multimédias industrielles et grand public. La représentation par nuages de points, plus facile à acquérir que les maillages, a suscité ces dernières année un intérêt croissant tant dans le monde académique que commercial. Un nuage de points est par définition un ensemble de points définissant la géométrie de l’objet et les attributs associés (couleurs, textures, les propriétés des matériaux, etc.). Le nombre de points dans un nuage de points peut aller d'un millier, pour représenter des objets relativement simples, jusqu'à des milliards pour représenter de manière réaliste des scènes 3D complexes. Ces énormes quantités de données posent de grands défis liés à la transmission, au traitement et au stockage des nuages de points 3D. Ces dernières années, de nombreux travaux ont été dédiés principalement à la compression de maillages, tandis qu’un nombre plus réduit de techniques s’attaquent à la problématique de compression de nuages de points 3D. L’état de l’art fait ressortir deux grandes familles approches principales: une première purement géométrique, fondée sur une décomposition en octree et une seconde hybride, exploitant à la fois la projection multi-vues de la géométrie et le codage vidéo. La première approche permet de préserver une information de géométrie 3D précise mais contient une faible cohérence temporelle. La seconde permet de supprimer efficacement la redondance temporelle mais est pénalisé par une diminution de la précision géométrique, liée au processus de projection 3D/2D. Ainsi, le compromis entre efficacité de compression et précision des objets reconstruit doit être optimisé. Premièrement, une segmentation adaptative par octree a été proposée pour regrouper les points avec différentes amplitudes de mouvement dans des cubes 3D. Ensuite, une estimation de mouvement est appliquée à ces cubes en utilisant une transformation affine. Des gains en termes de performances de distorsion de débit (RD) ont été observés dans des séquences avec des amplitudes de mouvement plus faibles. Cependant, le coût de construction d'un octree pour le nuage de points dense reste élevé tandis que les structures d'octree résultantes contiennent une mauvaise cohérence temporelle pour les séquences avec des amplitudes de mouvement plus élevées. Une structure anatomique a ensuite été proposée pour modéliser le mouvement de manière intrinsèque. À l'aide d'outils d'estimation de pose 2D, le mouvement est estimé à partir de 14 segments anatomiques à l'aide d'une transformation affine. De plus, nous avons proposé une nouvelle solution pour la prédiction des couleurs et discuté du codage des résidus de la prédiction. Il est montré qu'au lieu de coder des informations de texture redondantes, il est plus intéressant de coder les résidus, ce qui a entraîné une meilleure performance RD. Les différentes approches proposées ont permis d’améliorer les performances des modèles de test V-PCC. Toutefois, la compression temporelle de nuages de points 3D dynamiques reste une tâche complexe et difficile. Ainsi, en raison des limites de la technologie d'acquisition actuelle, les nuages acquis peuvent être bruyants à la fois dans les domaines de la géométrie et des attributs, ce qui rend difficile l'obtention d'une estimation précise du mouvement. Dans les études futures, les technologies utilisées pour les maillages 3D pourraient être exploitées et adaptées au cas des nuages de points non-structurés pour fournir des informations de connectivité cohérentes dans le tempsWith the rapid growth of multimedia content, 3D objects are becoming more and more popular. Most of the time, they are modeled as complex polygonal meshes or dense point clouds, providing immersive experiences in different industrial and consumer multimedia applications. The point cloud, which is easier to acquire than mesh and is widely applicable, has raised many interests in both the academic and commercial worlds.A point cloud is a set of points with different properties such as their geometrical locations and the associated attributes (e.g., color, material properties, etc.). The number of the points within a point cloud can range from a thousand, to constitute simple 3D objects, up to billions, to realistically represent complex 3D scenes. Such huge amounts of data bring great technological challenges in terms of transmission, processing, and storage of point clouds.In recent years, numerous research works focused their efforts on the compression of meshes, while less was addressed for point clouds. We have identified two main approaches in the literature: a purely geometric one based on octree decomposition, and a hybrid one based on both geometry and video coding. The first approach can provide accurate 3D geometry information but contains weak temporal consistency. The second one can efficiently remove the temporal redundancy yet a decrease of geometrical precision can be observed after the projection. Thus, the tradeoff between compression efficiency and accurate prediction needs to be optimized.We focused on exploring the temporal correlations between dynamic dense point clouds. We proposed different approaches to improve the compression performance of the MPEG (Moving Picture Experts Group) V-PCC (Video-based Point Cloud Compression) test model, which provides state-of-the-art compression on dynamic dense point clouds.First, an octree-based adaptive segmentation is proposed to cluster the points with different motion amplitudes into 3D cubes. Then, motion estimation is applied to these cubes using affine transformation. Gains in terms of rate-distortion (RD) performance have been observed in sequences with relatively low motion amplitudes. However, the cost of building an octree for the dense point cloud remains expensive while the resulting octree structures contain poor temporal consistency for the sequences with higher motion amplitudes.An anatomical structure is then proposed to model the motion of the point clouds representing humanoids more inherently. With the help of 2D pose estimation tools, the motion is estimated from 14 anatomical segments using affine transformation.Moreover, we propose a novel solution for color prediction and discuss the residual coding from prediction. It is shown that instead of encoding redundant texture information, it is more valuable to code the residuals, which leads to a better RD performance.Although our contributions have improved the performances of the V-PCC test models, the temporal compression of dynamic point clouds remains a highly challenging task. Due to the limitations of the current acquisition technology, the acquired point clouds can be noisy in both geometry and attribute domains, which makes it challenging to achieve accurate motion estimation. In future studies, the technologies used for 3D meshes may be exploited and adapted to provide temporal-consistent connectivity information between dynamic 3D point clouds
8
Hejl, Zdeněk. "Rekonstrukce 3D scény z obrazových dat." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2012. http://www.nusl.cz/ntk/nusl-236495.
Abstract:
This thesis describes methods of reconstruction of 3D scenes from photographs and videos using the Structure from motion approach. A new software capable of automatic reconstruction of point clouds and polygonal models from common images and videos was implemented based on these methods. The software uses variety of existing and custom solutions and clearly links them into one easily executable application. The reconstruction consists of feature point detection, pairwise matching, Bundle adjustment, stereoscopic algorithms and polygon model creation from point cloud using PCL library. Program is based on Bundler and PMVS. Poisson surface reconstruction algorithm, as well as simple triangulation and own reconstruction method based on plane segmentation were used for polygonal model creation.
9
Smith, Michael. "Non-parametric workspace modelling for mobile robots using push broom lasers." Thesis, University of Oxford, 2011. http://ora.ox.ac.uk/objects/uuid:50224eb9-73e8-4c8a-b8c5-18360d11e21b.
Abstract:
This thesis is about the intelligent compression of large 3D point cloud datasets. The non-parametric method that we describe simultaneously generates a continuous representation of the workspace surfaces from discrete laser samples and decimates the dataset, retaining only locally salient samples. Our framework attains decimation factors in excess of two orders of magnitude without significant degradation in fidelity. The work presented here has a specific focus on gathering and processing laser measurements taken from a moving platform in outdoor workspaces. We introduce a somewhat unusual parameterisation of the problem and look to Gaussian Processes as the fundamental machinery in our processing pipeline. Our system compresses laser data in a fashion that is naturally sympathetic to the underlying structure and complexity of the workspace. In geometrically complex areas, compression is lower than that in geometrically bland areas. We focus on this property in detail and it leads us well beyond a simple application of non-parametric techniques. Indeed, towards the end of the thesis we develop a non-stationary GP framework whereby our regression model adapts to the local workspace complexity. Throughout we construct our algorithms so that they may be efficiently implemented. In addition, we present a detailed analysis of the proposed system and investigate model parameters, metric errors and data compression rates. Finally, we note that this work is predicated on a substantial amount of robotics engineering which has allowed us to produce a high quality, peer reviewed, dataset - the first of its kind.
10
Roure, Garcia Ferran. "Tools for 3D point cloud registration." Doctoral thesis, Universitat de Girona, 2017. http://hdl.handle.net/10803/403345.
Abstract:
In this thesis, we did an in-depth review of the state of the art of 3D registration, evaluating the most popular methods. Given the lack of standardization in the literature, we also proposed a nomenclature and a classification to unify the evaluation systems and to be able to compare the different algorithms under the same criteria.
The major contribution of the thesis is the Registration Toolbox, which consists of software and a database of 3D models. The software presented here consists of a 3D Registration Pipeline written in C ++ that allows researchers to try different methods, as well as add new ones and compare them. In this Pipeline, we not only implemented the most popular methods of literature, but we also added three new methods that contribute to improving the state of the art. On the other hand, the database provides different 3D models to be able to carry out the tests to validate the performances of the methods. Finally, we presented a new hybrid data structure specially focused on the search for neighbors. We tested our proposal together with other data structures and we obtained very satisfactory results, overcoming in many cases the best current alternatives. All tested structures are also available in our Pipeline.
This Toolbox is intended to be a useful tool for the whole community and is available to researchers under a Creative Commons licenseEn aquesta tesi, hem fet una revisió en profunditat de l'estat de l'art del registre 3D, avaluant els mètodes més populars. Donada la falta d'estandardització de la literatura, també hem proposat una nomenclatura i una classificació per tal d'unificar els sistemes d'avaluació i poder comparar els diferents algorismes sota els mateixos criteris. La contribució més gran de la tesi és el Toolbox de Registre, que consisteix en un software i una base de dades de models 3D. El software presentat aquí consisteix en una Pipeline de registre 3D escrit en C++ que permet als investigadors provar diferents mètodes, així com afegir-n'hi de nous i comparar-los. En aquesta Pipeline, no només hem implementat els mètodes més populars de la literatura, sinó que també hem afegit tres mètodes nous que contribueixen a millorar l'estat de l'art de la tecnologia. D'altra banda, la base de dades proporciona una sèrie de models 3D per poder dur a terme les proves necessàries per validar el bon funcionament dels mètodes. Finalment, també hem presentat una nova estructura de dades híbrida especialment enfocada a la cerca de veïns. Hem testejat la nostra proposta conjuntament amb altres estructures de dades i hem obtingut resultats molt satisfactoris, superant en molts casos les millors alternatives actuals. Totes les estructures testejades estan també disponibles al nostre Pipeline. Aquesta Toolbox està pensada per ésser una eina útil per tota la comunitat i està a disposició dels investigadors sota llicència Creative-Commons
11
Tarcin, Serkan. "Fast Feature Extraction From 3d Point Cloud." Master's thesis, METU, 2013. http://etd.lib.metu.edu.tr/upload/12615659/index.pdf.
Abstract:
To teleoperate an unmanned vehicle a rich set of information should be gathered from surroundings.These systems use sensors which sends high amounts of data and processing the data in CPUs can be time consuming. Similarly, the algorithms that use the data may work slow because of the amount of the data. The solution is, preprocessing the data taken from the sensors on the vehicle and transmitting only the necessary parts or the results of the preprocessing. In this thesis a 180 degree laser scanner at the front end of an unmanned ground vehicle (UGV) tilted up and down on a horizontal axis and point clouds constructed from the surroundings. Instead of transmitting this data directly to the path planning or obstacle avoidance algorithms, a preprocessing stage has been run. In this preprocess rst, the points belonging to the ground plane have been detected and a simplied version of ground has been constructed then the obstacles have been detected. At last, a simplied ground plane as ground and simple primitive geometric shapes as obstacles have been sent to the path planning algorithms instead of sending the whole point cloud.
12
Forsman, Mona. "Point cloud densification." Thesis, Umeå universitet, Institutionen för fysik, 2010. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-39980.
Abstract:
Several automatic methods exist for creating 3D point clouds extracted from 2D photos. In manycases, the result is a sparse point cloud, unevenly distributed over the scene.After determining the coordinates of the same point in two images of an object, the 3D positionof that point can be calculated using knowledge of camera data and relative orientation. A model created from a unevenly distributed point clouds may loss detail and precision in thesparse areas. The aim of this thesis is to study methods for densification of point clouds. This thesis contains a literature study over different methods for extracting matched point pairs,and an implementation of Least Square Template Matching (LSTM) with a set of improvementtechniques. The implementation is evaluated on a set of different scenes of various difficulty. LSTM is implemented by working on a dense grid of points in an image and Wallis filtering isused to enhance contrast. The matched point correspondences are evaluated with parameters fromthe optimization in order to keep good matches and discard bad ones. The purpose is to find detailsclose to a plane in the images, or on plane-like surfaces. A set of extensions to LSTM is implemented in the aim of improving the quality of the matchedpoints. The seed points are improved by Transformed Normalized Cross Correlation (TNCC) andMultiple Seed Points (MSP) for the same template, and then tested to see if they converge to thesame result. Wallis filtering is used to increase the contrast in the image. The quality of the extractedpoints are evaluated with respect to correlation with other optimization parameters and comparisonof standard deviation in x- and y- direction. If a point is rejected, the option to try again with a largertemplate size exists, called Adaptive Template Size (ATS).
13
Gujar, Sanket. "Pointwise and Instance Segmentation for 3D Point Cloud." Digital WPI, 2019. https://digitalcommons.wpi.edu/etd-theses/1290.
Abstract:
The camera is the cheapest and computationally real-time option for detecting or segmenting the environment for an autonomous vehicle, but it does not provide the depth information and is undoubtedly not reliable during the night, bad weather, and tunnel flash outs. The risk of an accident gets higher for autonomous cars when driven by a camera in such situations. The industry has been relying on LiDAR for the past decade to solve this problem and focus on depth information of the environment, but LiDAR also has its shortcoming. The industry methods commonly use projections methods to create a projection image and run detection and localization network for inference, but LiDAR sees obscurants in bad weather and is sensitive enough to detect snow, making it difficult for robustness in projection based methods. We propose a novel pointwise and Instance segmentation deep learning architecture for the point clouds focused on self-driving application. The model is only dependent on LiDAR data making it light invariant and overcoming the shortcoming of the camera in the perception stack. The pipeline takes advantage of both global and local/edge features of points in points clouds to generate high-level feature. We also propose Pointer-Capsnet which is an extension of CapsNet for small 3D point clouds.
14
Chen, Chen. "Semantics Augmented Point Cloud Sampling for 3D Object Detection." Thesis, The University of Sydney, 2021. https://hdl.handle.net/2123/26956.
Abstract:
3D object detection is an emerging topic among both industries and research communities. It aims at discovering objects of interest from 3D scenes and has a strong connection with many real-world scenarios, such as autonomous driving.
Currently, many models have been proposed to detect potential objects from point clouds. Some methods attempt to model point clouds in the unit of point, and then perform detection with acquired point-wise features. These methods are classified as point-based methods. However, we argue that the prevalent sampling algorithm for point-based models is sub-optimal for involving too much potentially unimportant data and may also lose some important information for detecting objects. Hence, it may lead to a significant performance drop.
This thesis manages to improve the current sampling strategy for point-based models in the context of 3D detection. We propose recasting the sampling algorithm by incorporating semantic information to help identify more beneficial data for detection, thus obtaining a semantics augmented sampling strategy. In particular, we introduce a 2-phase augmentation for sampling. In the point feature learning phase, we propose a semantics-guided farthest point sampling (S-FPS) to keep more informative foreground points. In addition, in the box prediction phase, we devise a semantic balance sampling (SBS) to avoid redundant training on easily recognized instances.
We evaluate our proposed strategy on the popular KITTI dataset and the large-scale nuScenes dataset. Extensive experiments show that our method lifts the point-based single-stage detector to surpass all existing point-based models and even achieve comparable performance to state-of-the-art two-stage methods.
15
Dey, Emon Kumar. "Effective 3D Building Extraction from Aerial Point Cloud Data." Thesis, Griffith University, 2022. http://hdl.handle.net/10072/413311.
Abstract:
Building extraction is important for a wider range of applications including smart city planning, disaster management, security, and cadastral mapping. This thesis mainly aims to present an effective data-driven strategy for building extraction using aerial Light Detection And Ranging (LiDAR) point cloud data. The LiDAR data provides highly accurate three-dimensional (3D) positional information. Therefore, studies on building extraction using LiDAR data have broadened in scope over time. Outliers, inharmonious input data behaviour, innumerable building structure possibilities, and heterogeneous environments are major challenges that need to be addressed for an effective 3D building extraction using LiDAR data. Outliers can cause the extraction of erroneous roof planes, incorrect boundaries, and over-segmentation of the extracted buildings. Due to the uneven point densities and heterogeneous building structures, small roof parts often remain undetected. Moreover, finding and using a realistic performance metric to evaluate the extracted buildings is another challenge. Inaccurate identification of sharp features, coplanar points, and boundary feature points often causes inaccurate roof plane segmentation and overall 3D outline generation for a building. To address these challenges, first, this thesis proposes a robust variable point neighbourhood estimation method. Considering the specific scanline properties associated with aerial LiDAR data, the proposed method automatically estimates an optimal and realistic neighbourhood for each point to solve the shortcomings of existing fixed neighbourhood methods in uneven or abrupt point densities. Using the estimated variable neighbourhood, a robust z-score and a distance-based outlier factor are calculated for each point in the input data. Based on these two measurements, an effective outlier detection method is proposed which can preserve more than 98% of inliers and remove outliers with better precision than the existing state-of-the-art methods. Then, individual roof planes are extracted in a robust way from the separated outlier free coplanar points based on the M-estimator SAmple Consensus (MSAC) plane-ftting algorithm. The proposed technique is capable of extracting small real roof planes, while avoiding spurious roof planes caused by the remaining outliers, if any. Individual buildings are then extracted precisely by grouping adjacent roof planes into clusters. Next, to assess the extracted buildings and individual roof plane boundaries, a realistic evaluation metric is proposed based on a new robust corner correspondence algorithm. The metric is defined as the average minimum distance davg from the extracted boundary points to their actual corresponding reference lines. It strictly follows the definition of a standard mathematical metric, and addresses the shortcomings of the existing metrics. In addition, during the evaluation, the proposed metric separately identifies the underlap and extralap areas in an extracted building. Furthermore, finding precise 3D feature points (e.g., fold and boundary) is necessary for tracing feature lines to describe a building outline. It is also important for accurate roof plane extraction and for establishing relationships between the correctly extracted planes so as to facilitate a more robust 3D building extraction. Thus, this thesis presents a robust fold feature point extraction method based on the calculated normal of the individual point. Later, a method to extract the feature points representing the boundaries is also developed based on the distance from a point to the calculated mean of its estimated neighbours. In the context of the accuracy evaluation, the proposed methods show more than 90% F1-scores on the generated ground truth data. Finally, machine learning techniques are applied to circumvent the problems (e.g., selecting manual thresholds for different parameters) of existing rule-based approaches for roof feature point extraction and classification. Seven effective geometric and statistical features are calculated for each point to train and test the machine learning classifiers using the appropriate ground truth data. Four primary classes of building roof point cloud are considered, and promising results for each of the classes have been achieved, confirming the competitive performance of the classification over the state-of-the-art techniques. At the end of this thesis, using the classified roof feature points, a more robust plane segmentation algorithm is demonstrated for extracting the roof planes of individual buildings.Thesis (PhD Doctorate)
Doctor of Philosophy (PhD)
School of Info & Comm Tech
Science, Environment, Engineering and Technology
Full Text
16
Eckart, Benjamin. "Compact Generative Models of Point Cloud Data for 3D Perception." Research Showcase @ CMU, 2017. http://repository.cmu.edu/dissertations/1089.
Abstract:
One of the most fundamental tasks for any robotics application is the ability to adequately assimilate and respond to incoming sensor data. In the case of 3D range sensing, modern-day sensors generate massive quantities of point cloud data that strain available computational resources. Dealing with large quantities of unevenly sampled 3D point data is a great challenge for many fields, including autonomous driving, 3D manipulation, augmented reality, and medical imaging. This thesis explores how carefully designed statistical models for point cloud data can facilitate, accelerate, and unify many common tasks in the area of range-based 3D perception. We first establish a novel family of compact generative models for 3D point cloud data, offering them as an efficient and robust statistical alternative to traditional point-based or voxel-based data structures. We then show how these statistical models can be utilized toward the creation of a unified data processing architecture for tasks such as segmentation, registration, visualization, and mapping. In complex robotics systems, it is common for various concurrent perceptual processes to have separate low-level data processing pipelines. Besides introducing redundancy, these processes may perform their own data processing in conflicting or ad hoc ways. To avoid this, tractable data structures and models need to be established that share common perceptual processing elements. Additionally, given that many robotics applications involving point cloud processing are size, weight, and power-constrained, these models and their associated algorithms should be deployable in low-power embedded systems while retaining acceptable performance. Given a properly flexible and robust point processor, therefore, many low-level tasks could be unified under a common architectural paradigm and greatly simplify the overall perceptual system. In this thesis, a family of compact generative models is introduced for point cloud data based on hierarchical Gaussian Mixture Models. Using recursive, dataparallel variants of the Expectation Maximization algorithm, we construct high fidelity statistical and hierarchical point cloud models that compactly represent the data as a 3D generative probability distribution. In contrast to raw points or voxelbased decompositions, our proposed statistical model provides a better theoretical footing for robustly dealing with noise, constructing maximum likelihood methods, reasoning probabilistically about free space, utilizing spatial sampling techniques, and performing gradient-based optimizations. Further, the construction of the model as a spatial hierarchy allows for Octree-like logarithmic time access. One challenge compared to previous methods, however, is that our model-based approach incurs a potentially high creation cost. To mitigate this problem, we leverage data parallelism in order to design models well-suited for GPU acceleration, allowing them to run at real-time rates for many time-critical applications. We show how our models can facilitate various 3D perception tasks, demonstrating state-of-the-art performance in geometric segmentation, registration, dynamic occupancy map creation, and 3D visualization.
17
Oropallo, William Edward Jr. "A Point Cloud Approach to Object Slicing for 3D Printing." Thesis, University of South Florida, 2018. http://pqdtopen.proquest.com/#viewpdf?dispub=10751757.
Abstract:
Various industries have embraced 3D printing for manufacturing on-demand, custom printed parts. However, 3D printing requires intelligent data processing and algorithms to go from CAD model to machine instructions. One of the most crucial steps in the process is the slicing of the object. Most 3D printers build parts by accumulating material layers by layer. 3D printing software needs to calculate these layers for manufacturing by slicing a model and calculating the intersections. Finding exact solutions of intersections on the original model is mathematically complicated and computationally demanding. A preprocessing stage of tessellation has become the standard practice for slicing models. Calculating intersections with tessellations of the original model is computationally simple but can introduce inaccuracies and errors that can ruin the final print.
This dissertation shows that a point cloud approach to preprocessing and slicing models is robust and accurate. The point cloud approach to object slicing avoids the complexities of directly slicing models while evading the error-prone tessellation stage. An algorithm developed for this dissertation generates point clouds and slices models within a tolerance. The algorithm uses the original NURBS model and converts the model into a point cloud, based on layer thickness and accuracy requirements. The algorithm then uses a gridding structure to calculate where intersections happen and fit B-spline curves to those intersections.
This algorithm finds accurate intersections and can ignore certain anomalies and error from the modeling process. The primary point evaluation is stable and computationally inexpensive. This algorithm provides an alternative to challenges of both the direct and tessellated slicing methods that have been the focus of the 3D printing industry.
18
Lev, Hoang Justin. "A Study of 3D Point Cloud Features for Shape Retrieval." Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM040.
Abstract:
Grâce à l’amélioration et la multiplication des capteurs 3D, la diminution des prix et l’augmentation des puissances de calculs, l’utilisation de donnée3D s’est intensifiée ces dernières années. Les nuages de points 3D (3D pointcloud) sont une des représentations possibles pour de telles données. Elleà l’avantage d’être simple et précise, ainsi que le résultat immédiat de la capture. En tant que structure non-régulière sous forme de liste de points,l’analyse des nuages de points est complexe d’où leur récente utilisation. Cette thèse se concentre sur l’utilisation de nuages de points 3D pourune analyse tridimensionnelle de leur forme. La géométrie des nuages est plus particulièrement étudiée via les courbures des objets. Des descripteursreprésentant la distribution des courbures principales sont proposés: Semantic Point Cloud (SPC) et Multi-Scale Principal Curvature Point Cloud (MPC2).Global Local Point Cloud (GLPC) est un autre descripteur basé sur les courbures mais en combinaison d’autres propriétés. Ces trois descripteurs sontrobustes aux erreurs communes lors d’une capture 3D comme par exemple le bruit ou bien les occlusions. Leurs performances sont supérieures à ceuxde l’état de l’art en ce qui concerne la reconnaissance d’instance avec plus de 90% de précision. La thèse étudie également les récents algorithmes de deep learning qui concernent les nuages de points 3D qui sont apparus au cours de ces trois ans de thèse. Une première approche utilise des descripteurs basé sur les courbures en tant que données d’entrée pour un réseau de perceptron multicouche (MLP). Les résultats ne sont cependant pas au niveau de l’état de l’art mais cette étude montre que ModelNet, la base de données de référence pour laclassification d’objet 3D, n’est pas optimale. En effet, la base de donnéesn’est pas une bonne représentation de la réalité en ne reflétant pas la richesse de courbures des objets réels. Enfin, l’architecture d’un réseau neuronal artificiel est présenté. Inspiré par l’état de l’art en deep learning, Multi-scale PointNet détermine les propriétés d’un objet à différente échelle et les combine afin de le décrire. Encore en développement, le modèle requiert encore des ajustements pour obtenir des résultats concluants. Pour résumer, en s’attaquant au problème complexe de l’utilisation des nuages de points 3D mais aussi à l’évolution rapide du domaine, la thèse contribue à l’état de l’art sur trois aspects majeurs: (i) L’élaboration de nouveaux algorithmes se basant sur les courbures géométrique des objets pour la reconnaissance d’instance. (ii) L’étude qui montre que la construction d’une nouvelle base de données plus réaliste est nécessaire pour correctement poursuivre les études dans le domaine. (iii) La proposition d’une nouvelle architecture de réseau de neurones artificiels pour l’analyse de nuage de points3DWith the improvement and proliferation of 3D sensors, price cut and enhancementof computational power, the usage of 3D data intensifies for the last few years. The3D point cloud is one type amongst the others for 3D representation. This particularlyrepresentation is the direct output of sensors, accurate and simple. As a non-regularstructure of unordered list of points, the analysis on point cloud is challenging andhence the recent usage only.This PhD thesis focuses on the use of 3D point cloud representation for threedimensional shape analysis. More particularly, the geometrical shape is studied throughthe curvature of the object. Descriptors describing the distribution of the principalcurvature is proposed: Principal Curvature Point Cloud and Multi-Scale PrincipalCurvature Point Cloud. Global Local Point Cloud is another descriptor using thecurvature but in combination with other features. These three descriptors are robustto typical 3D scan error like noisy data or occlusion. They outperform state-of-the-artalgorithms in instance retrieval task with more than 90% of accuracy.The thesis also studies deep learning on 3D point cloud which emerges during thethree years of this PhD. The first approach tested, used curvature-based descriptor asthe input of a multi-layer perceptron network. The accuracy cannot catch state-ofthe-art performances. However, they show that ModelNet, the standard dataset for 3Dshape classification is not a good picture of the reality. Indeed, the experiment showsthat the dataset does not reflect the curvature wealth of true objects scans.Ultimately, a new neural network architecture is proposed. Inspired by the state-ofthe-art deep learning network, Multiscale PointNet computes the feature on multiplescales and combines them all to describe an object. Still under development, theperformances are still to be improved.In summary, tackling the challenging use of 3D point clouds but also the quickevolution of the field, the thesis contributes to the state-of-the-art in three majoraspects: (i) Design of new algorithms, relying on geometrical curvature of the objectfor instance retrieval task. (ii) Study and exhibition of the need to build a new standardclassification dataset with more realistic objects. (iii) Proposition of a new deep neuralnetwork for 3D point cloud analysis
19
Kulkarni, Amey S. "Motion Segmentation for Autonomous Robots Using 3D Point Cloud Data." Digital WPI, 2020. https://digitalcommons.wpi.edu/etd-theses/1370.
Abstract:
Achieving robot autonomy is an extremely challenging task and it starts with developing algorithms that help the robot understand how humans perceive the environment around them. Once the robot understands how to make sense of its environment, it is easy to make efficient decisions about safe movement. It is hard for robots to perform tasks that come naturally to humans like understanding signboards, classifying traffic lights, planning path around dynamic obstacles, etc. In this work, we take up one such challenge of motion segmentation using Light Detection and Ranging (LiDAR) point clouds. Motion segmentation is the task of classifying a point as either moving or static. As the ego-vehicle moves along the road, it needs to detect moving cars with very high certainty as they are the areas of interest which provide cues to the ego-vehicle to plan it's motion. Motion segmentation algorithms segregate moving cars from static cars to give more importance to dynamic obstacles. In contrast to the usual LiDAR scan representations like range images and regular grid, this work uses a modern representation of LiDAR scans using permutohedral lattices. This representation gives ease of representing unstructured LiDAR points in an efficient lattice structure. We propose a machine learning approach to perform motion segmentation. The network architecture takes in two sequential point clouds and performs convolutions on them to estimate if 3D points from the first point cloud are moving or static. Using two temporal point clouds help the network in learning what features constitute motion. We have trained and tested our learning algorithm on the FlyingThings3D dataset and a modified KITTI dataset with simulated motion.
20
Aronsson, Oskar, and Julia Nyman. "Boundary Representation Modeling from Point Clouds." Thesis, KTH, Bro- och stålbyggnad, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-278543.
Abstract:
Inspections of bridges are today performed ocularly by an inspector at arm’s lengths distance to evaluate damages and to assess its current condition. Ocular inspections often require specialized equipment to aid the inspector to reach all parts of the bridge. The current state of practice for bridge inspection is therefore considered to be time-consuming, costly, and a safety hazard for the inspector. The purpose of this thesis has been to develop a method for automated modeling of bridges from point cloud data. Point clouds that have been created through photogrammetry from a collection of images acquired with an Unmanned Aerial Vehicle (UAV). This thesis has been an attempt to contribute to the long-term goal of making bridge inspections more efficient by using UAV technology. Several methods for the identification of structural components in point clouds have been evaluated. Based on this, a method has been developed to identify planar surfaces using the model-fitting method Random Sample Consensus (RANSAC). The developed method consists of a set of algorithms written in the programming language Python. The method utilizes intersection points between planes as well as the k-Nearest-Neighbor (k-NN) concept to identify the vertices of the structural elements. The method has been tested both for simulated point cloud data as well as for real bridges, where the images were acquired with a UAV. The results from the simulated point clouds showed that the vertices were modeled with a mean deviation of 0.13− 0.34 mm compared to the true vertex coordinates. For a point cloud of a rectangular column, the algorithms identified all relevant surfaces and were able to reconstruct it with a deviation of less than 2 % for the width and length. The method was also tested on two point clouds of real bridges. The algorithms were able to identify many of the relevant surfaces, but the complexity of the geometries resulted in inadequately reconstructed models.Besiktning av broar utförs i dagsläget okulärt av en inspektör som på en armlängds avstånd bedömer skadetillståndet. Okulär besiktning kräver därmed ofta speciell utrustning för att inspektören ska kunna nå samtliga delar av bron. Detta resulterar i att det nuvarande tillvägagångssättet för brobesiktning beaktas som tidkrävande, kostsamt samt riskfyllt för inspektören. Syftet med denna uppsats var att utveckla en metod för att modellera broar på ett automatiserat sätt utifrån punktmolnsdata. Punktmolnen skapades genom fotogrammetri, utifrån en samling bilder tagna med en drönare. Uppsatsen har varit en insats för att bidra till det långsiktiga målet att effektivisera brobesiktning genom drönarteknik. Flera metoder för att identifiera konstruktionselement i punktmoln har undersökts. Baserat på detta har en metod utvecklats som identifierar plana ytor med regressionsmetoden Random Sample Consensus (RANSAC). Den utvecklade metoden består av en samling algoritmer skrivna i programmeringsspråket Python. Metoden grundar sig i att beräkna skärningspunkter mellan plan samt använder konceptet k-Nearest-Neighbor (k-NN) för att identifiera konstruktionselementens hörnpunkter. Metoden har testats på både simulerade punktmolnsdata och på punktmoln av fysiska broar, där bildinsamling har skett med hjälp av en drönare. Resultatet från de simulerade punktmolnen visade att hörnpunkterna kunde identifieras med en medelavvikelse på 0,13 − 0,34 mm jämfört med de faktiska hörnpunkterna. För ett punktmoln av en rektangulär pelare lyckades algoritmerna identifiera alla relevanta ytor och skapa en rekonstruerad modell med en avvikelse på mindre än 2 % med avseende på dess bredd och längd. Metoden testades även på två punktmoln av riktiga broar. Algoritmerna lyckades identifiera många av de relevanta ytorna, men geometriernas komplexitet resulterade i bristfälligt rekonstruerade modeller.
21
He, Linbo. "Improving 3D Point Cloud Segmentation Using Multimodal Fusion of Projected 2D Imagery Data : Improving 3D Point Cloud Segmentation Using Multimodal Fusion of Projected 2D Imagery Data." Thesis, Linköpings universitet, Datorseende, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-157705.
Abstract:
Semantic segmentation is a key approach to comprehensive image data analysis. It can be applied to analyze 2D images, videos, and even point clouds that contain 3D data points. On the first two problems, CNNs have achieved remarkable progress, but on point cloud segmentation, the results are less satisfactory due to challenges such as limited memory resource and difficulties in 3D point annotation. One of the research studies carried out by the Computer Vision Lab at Linköping University was aiming to ease the semantic segmentation of 3D point cloud. The idea is that by first projecting 3D data points to 2D space and then focusing only on the analysis of 2D images, we can reduce the overall workload for the segmentation process as well as exploit the existing well-developed 2D semantic segmentation techniques. In order to improve the performance of CNNs for 2D semantic segmentation, the study has used input data derived from different modalities. However, how different modalities can be optimally fused is still an open question. Based on the above-mentioned study, this thesis aims to improve the multistream framework architecture. More concretely, we investigate how different singlestream architectures impact the multistream framework with a given fusion method, and how different fusion methods contribute to the overall performance of a given multistream framework. As a result, our proposed fusion architecture outperformed all the investigated traditional fusion methods. Along with the best singlestream candidate and few additional training techniques, our final proposed multistream framework obtained a relative gain of 7.3\% mIoU compared to the baseline on the semantic3D point cloud test set, increasing the ranking from 12th to 5th position on the benchmark leaderboard.
22
Downham, Alexander David. "True 3D Digital Holographic Tomography for Virtual Reality Applications." University of Dayton / OhioLINK, 2017. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1513204001924421.
23
Trowbridge, Michael Aaron. "Autonomous 3D Model Generation of Orbital Debris using Point Cloud Sensors." Thesis, University of Colorado at Boulder, 2014. http://pqdtopen.proquest.com/#viewpdf?dispub=1558774.
Abstract:
A software prototype for autonomous 3D scanning of uncooperatively rotating orbital debris using a point cloud sensor is designed and tested. The software successfully generated 3D models under conditions that simulate some on-orbit orbit challenges including relative motion between observer and target, inconsistent target visibility and a target with more than one plane of symmetry. The model scanning software performed well against an irregular object with one plane of symmetry but was weak against objects with 2 planes of symmetry.
The suitability of point cloud sensors and algorithms for space is examined. Terrestrial Graph SLAM is adapted for an uncooperatively rotating orbital debris scanning scenario. A joint EKF attitude estimate and shape similiarity loop closure heuristic for orbital debris is derived and experimentally tested. The binary Extended Fast Point Feature Histogram (EFPFH) is defined and analyzed as a binary quantization of the floating point EFPFH. Both the binary and floating point EPFH are experimentally tested and compared as part of the joint loop closure heuristic.
24
Hirschmüller, Korbinian. "Development and Evaluation of a 3D Point Cloud Based Attitude Determination System." Thesis, Luleå tekniska universitet, Rymdteknik, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-65910.
25
Blahož, Vladimír. "Vizualizace 3D scény pro ovládání robota." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2012. http://www.nusl.cz/ntk/nusl-236501.
Abstract:
This thesis presents possibilities of 3D point cloud and true colored digital video fusion that can be used in the process of robot teleoperation. Advantages of a 3D environment visualization combining more than one sensor data, tools to facilitate such data fusion, as well as two alternative practical implementations of combined data visualization are discussed. First proposed alternative estimates view frustum of the robot's camera and maps real colored video to a semi-transparent polygon placed in the view frustum. The second option is a direct coloring of the point cloud data creating a colored point cloud representing color as well as depth information about an environment.
26
Burwell, Claire Leonora. "The effect of 2D vs. 3D visualisation on lidar point cloud analysis tasks." Thesis, University of Leicester, 2016. http://hdl.handle.net/2381/37950.
Abstract:
The exploitation of human depth perception is not uncommon in visual analysis of data; medical imagery and geological analysis already rely on stereoscopic 3D visualisation. In contrast, 3D scans of the environment are usually represented on a flat, 2D computer screen, although there is potential to take advantage of both (a) the spatial depth that is offered by the point cloud data, and (b) our ability to see stereoscopically. This study explores whether a stereo 3D analysis environment would add value to visual lidar tasks, compared to the standard 2D display. Forty-six volunteers, all with good stereovision and varying lidar knowledge, viewed lidar data in either 2D or in 3D, on a 4m x 2.4m screen. The first task required 2D and 3D measurement of linear lengths of a planar and a volumetric feature, using an interaction device for point selection. Overall, there was no significant difference in the spread of 2D and 3D measurement distributions for both of the measured features. The second task required interpretation of ten features from individual points. These were highlighted across two areas of interest - a flat, suburban area and a valley slope with a mixture of features. No classification categories were offered to the participant and answers were expressed verbally. Two of the ten features (chimney and cliff-face) were interpreted with a better degree of accuracy using the 3D method and the remaining features had no difference in 2D and 3D accuracy. Using the experiment’s data processing and visualisation approaches, results suggest that stereo 3D perception of lidar data does not add value to manual linear measurement. The interpretation results indicate that immersive stereo 3D visualisation does improve the accuracy of manual point cloud classification for certain features. The findings contribute to wider discussions in lidar processing, geovisualisation, and applied psychology.
27
Kudryavtsev, Andrey. "3D Reconstruction in Scanning Electron Microscope : from image acquisition to dense point cloud." Thesis, Bourgogne Franche-Comté, 2017. http://www.theses.fr/2017UBFCD050/document.
Abstract:
L’objectif de ce travail est d’obtenir un modèle 3D d’un objet à partir d’une série d’images prisesavec un Microscope Electronique à Balayage (MEB). Pour cela, nous utilisons la technique dereconstruction 3D qui est une application bien connue du domaine de vision par ordinateur.Cependant, en raison des spécificités de la formation d’images dans le MEB et dans la microscopieen général, les techniques existantes ne peuvent pas être appliquées aux images MEB. Lesprincipales raisons à cela sont la projection parallèle et les problèmes d’étalonnage de MEB entant que caméra. Ainsi, dans ce travail, nous avons développé un nouvel algorithme permettant deréaliser une reconstruction 3D dans le MEB tout en prenant en compte ces difficultés. De plus,comme la reconstruction est obtenue par auto-étalonnage de la caméra, l’utilisation des mires n’estplus requise. La sortie finale des techniques présentées est un nuage de points dense, pouvant donccontenir des millions de points, correspondant à la surface de l’objetThe goal of this work is to obtain a 3D model of an object from its multiple views acquired withScanning Electron Microscope (SEM). For this, the technique of 3D reconstruction is used which isa well known application of computer vision. However, due to the specificities of image formation inSEM, and in microscale in general, the existing techniques are not applicable to the SEM images. Themain reasons for that are the parallel projection and the problems of SEM calibration as a camera.As a result, in this work we developed a new algorithm allowing to achieve 3D reconstruction in SEMwhile taking into account these issues. Moreover, as the reconstruction is obtained through cameraautocalibration, there is no need in calibration object. The final output of the presented techniques isa dense point cloud corresponding to the surface of the object that may contain millions of points
28
Nurunnabi, Abdul Awal Md. "Robust statistical approaches for feature extraction in laser scanning 3D point cloud data." Thesis, Curtin University, 2014. http://hdl.handle.net/20.500.11937/543.
Abstract:
Three dimensional point cloud data acquired from mobile laser scanning system commonly contain outliers and/or noise. The presence of outliers and noise means most of the frequently used methods for feature extraction produce inaccurate and non-robust results. We investigate the problems of outliers and how to accommodate them for automatic robust feature extraction. This thesis develops algorithms for outlier detection, point cloud denoising, robust feature extraction, segmentation and ground surface extraction.
29
Grankvist, Ola. "Recognition and Registration of 3D Models in Depth Sensor Data." Thesis, Linköpings universitet, Datorseende, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-131452.
Abstract:
Object Recognition is the art of localizing predefined objects in image sensor data. In this thesis a depth sensor was used which has the benefit that the 3D pose of the object can be estimated. This has applications in e.g. automatic manufacturing, where a robot picks up parts or tools with a robot arm. This master thesis presents an implementation and an evaluation of a system for object recognition of 3D models in depth sensor data. The system uses several depth images rendered from a 3D model and describes their characteristics using so-called feature descriptors. These are then matched with the descriptors of a scene depth image to find the 3D pose of the model in the scene. The pose estimate is then refined iteratively using a registration method. Different descriptors and registration methods are investigated. One of the main contributions of this thesis is that it compares two different types of descriptors, local and global, which has seen little attention in research. This is done for two different scene scenarios, and for different types of objects and depth sensors. The evaluation shows that global descriptors are fast and robust for objects with a smooth visible surface whereas the local descriptors perform better for larger objects in clutter and occlusion. This thesis also presents a novel global descriptor, the CESF, which is observed to be more robust than other global descriptors. As for the registration methods, the ICP is shown to perform most accurately and ICP point-to-plane more robust.
30
Digne, Julie. "Inverse geometry : from the raw point cloud to the 3d surface : theory and algorithms." Phd thesis, École normale supérieure de Cachan - ENS Cachan, 2010. http://tel.archives-ouvertes.fr/tel-00610432.
Abstract:
Many laser devices acquire directly 3D objects and reconstruct their surface. Nevertheless, the final reconstructed surface is usually smoothed out as a result of the scanner internal de-noising process and the offsets between different scans. This thesis, working on results from high precision scans, adopts the somewhat extreme conservative position, not to loose or alter any raw sample throughout the whole processing pipeline, and to attempt to visualize them. Indeed, it is the only way to discover all surface imperfections (holes, offsets). Furthermore, since high precision data can capture the slightest surface variation, any smoothing and any sub-sampling can incur in the loss of textural detail.The thesis attempts to prove that one can triangulate the raw point cloud with almost no sample loss. It solves the exact visualization problem on large data sets of up to 35 million points made of 300 different scan sweeps and more. Two major problems are addressed. The first one is the orientation of the complete raw point set, an the building of a high precision mesh. The second one is the correction of the tiny scan misalignments which can cause strong high frequency aliasing and hamper completely a direct visualization.The second development of the thesis is a general low-high frequency decomposition algorithm for any point cloud. Thus classic image analysis tools, the level set tree and the MSER representations, are extended to meshes, yielding an intrinsic mesh segmentation method.The underlying mathematical development focuses on an analysis of a half dozen discrete differential operators acting on raw point clouds which have been proposed in the literature. By considering the asymptotic behavior of these operators on a smooth surface, a classification by their underlying curvature operators is obtained.This analysis leads to the development of a discrete operator consistent with the mean curvature motion (the intrinsic heat equation) defining a remarkably simple and robust numerical scale space. By this scale space all of the above mentioned problems (point set orientation, raw point set triangulation, scan merging, segmentation), usually addressed by separated techniques, are solved in a unified framework.
31
Cheng, Huaining. "Orthogonal Moment-Based Human Shape Query and Action Recognition from 3D Point Cloud Patches." Wright State University / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=wright1452160221.
32
Al, Hakim Ezeddin. "3D YOLO: End-to-End 3D Object Detection Using Point Clouds." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-234242.
Abstract:
For safe and reliable driving, it is essential that an autonomous vehicle can accurately perceive the surrounding environment. Modern sensor technologies used for perception, such as LiDAR and RADAR, deliver a large set of 3D measurement points known as a point cloud. There is a huge need to interpret the point cloud data to detect other road users, such as vehicles and pedestrians. Many research studies have proposed image-based models for 2D object detection. This thesis takes it a step further and aims to develop a LiDAR-based 3D object detection model that operates in real-time, with emphasis on autonomous driving scenarios. We propose 3D YOLO, an extension of YOLO (You Only Look Once), which is one of the fastest state-of-the-art 2D object detectors for images. The proposed model takes point cloud data as input and outputs 3D bounding boxes with class scores in real-time. Most of the existing 3D object detectors use hand-crafted features, while our model follows the end-to-end learning fashion, which removes manual feature engineering. 3D YOLO pipeline consists of two networks: (a) Feature Learning Network, an artificial neural network that transforms the input point cloud to a new feature space; (b) 3DNet, a novel convolutional neural network architecture based on YOLO that learns the shape description of the objects. Our experiments on the KITTI dataset shows that the 3D YOLO has high accuracy and outperforms the state-of-the-art LiDAR-based models in efficiency. This makes it a suitable candidate for deployment in autonomous vehicles.För att autonoma fordon ska ha en god uppfattning av sin omgivning används moderna sensorer som LiDAR och RADAR. Dessa genererar en stor mängd 3-dimensionella datapunkter som kallas point clouds. Inom utvecklingen av autonoma fordon finns det ett stort behov av att tolka LiDAR-data samt klassificera medtrafikanter. Ett stort antal studier har gjorts om 2D-objektdetektering som analyserar bilder för att upptäcka fordon, men vi är intresserade av 3D-objektdetektering med hjälp av endast LiDAR data. Därför introducerar vi modellen 3D YOLO, som bygger på YOLO (You Only Look Once), som är en av de snabbaste state-of-the-art modellerna inom 2D-objektdetektering för bilder. 3D YOLO tar in ett point cloud och producerar 3D lådor som markerar de olika objekten samt anger objektets kategori. Vi har tränat och evaluerat modellen med den publika träningsdatan KITTI. Våra resultat visar att 3D YOLO är snabbare än dagens state-of-the-art LiDAR-baserade modeller med en hög träffsäkerhet. Detta gör den till en god kandidat för kunna användas av autonoma fordon.
33
IRFAN, MUHAMMAD ABEER. "Joint geometry and color denoising for 3D point clouds." Doctoral thesis, Politecnico di Torino, 2021. http://hdl.handle.net/11583/2912976.
34
Dahlin, Johan. "3D Modeling of Indoor Environments." Thesis, Linköpings universitet, Reglerteknik, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-93999.
Abstract:
With the aid of modern sensors it is possible to create models of buildings. These sensorstypically generate 3D point clouds and in order to increase interpretability and usability,these point clouds are often translated into 3D models.In this thesis a way of translating a 3D point cloud into a 3D model is presented. The basicfunctionality is implemented using Matlab. The geometric model consists of floors, wallsand ceilings. In addition, doors and windows are automatically identified and integrated intothe model. The resulting model also has an explicit representation of the topology betweenentities of the model. The topology is represented as a graph, and to do this GraphML isused. The graph is opened in a graph editing program called yEd.The result is a 3D model that can be plotted in Matlab and a graph describing the connectivitybetween entities. The GraphML file is automatically generated in Matlab. An interfacebetween Matlab and yEd allows the user to choose which rooms should be plotted.
35
Hammoudi, Karim. "Contributions to the 3D city modeling : 3D polyhedral building model reconstruction from aerial images and 3D facade modeling from terrestrial 3D point cloud and images." Phd thesis, Université Paris-Est, 2011. http://tel.archives-ouvertes.fr/tel-00682442.
Abstract:
The aim of this work is to develop research on 3D building modeling. In particular, the research in aerial-based 3D building reconstruction is a topic very developed since 1990. However, it is necessary to pursue the research since the actual approaches for 3D massive building reconstruction (although efficient) still encounter problems in generalization, coherency, accuracy. Besides, the recent developments of street acquisition systems such as Mobile Mapping Systems open new perspectives for improvements in building modeling in the sense that the terrestrial data (very dense and accurate) can be exploited with more performance (in comparison to the aerial investigation) to enrich the building models at facade level (e.g., geometry, texturing).Hence, aerial and terrestrial based building modeling approaches are individually proposed. At aerial level, we describe a direct and featureless approach for simple polyhedral building reconstruction from a set of calibrated aerial images. At terrestrial level, several approaches that essentially describe a 3D urban facade modeling pipeline are proposed, namely, the street point cloud segmentation and classification, the geometric modeling of urban facade and the occlusion-free facade texturing
36
Houshiar, Hamidreza [Verfasser], Andreas [Gutachter] Nüchter, and Claus [Gutachter] Brenner. "Documentation and mapping with 3D point cloud processing / Hamidreza Houshiar ; Gutachter: Andreas Nüchter, Claus Brenner." Würzburg : Universität Würzburg, 2017. http://d-nb.info/1127528823/34.
37
Houshiar, Hamidreza Verfasser], Andreas [Gutachter] [Nüchter, and Claus [Gutachter] Brenner. "Documentation and mapping with 3D point cloud processing / Hamidreza Houshiar ; Gutachter: Andreas Nüchter, Claus Brenner." Würzburg : Universität Würzburg, 2017. http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-144493.
38
Fucili, Mattia. "3D object detection from point clouds with dense pose voters." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/17616/.
Abstract:
Il riconoscimento di oggetti è sempre stato un compito sfidante per la Computer Vision. Trova applicazione in molti campi, principalmente nell’industria, come ad esempio per permettere ad un robot di trovare gli oggetti da afferrare. Negli ultimi decenni tali compiti hanno trovato nuovi modi di essere raggiunti grazie alla riscoperta delle Reti Neurali, in particolare le Reti Neurali Convoluzionali. Questo tipo di reti ha raggiunto ottimi risultati in molte applicazioni per il riconoscimento e la classificazione degli oggetti. La tendenza, ora, `e quella di utilizzare tali reti anche nell’industria automobilistica per cercare di rendere reale il sogno delle automobili che guidano da sole. Ci sono molti lavori importanti sul riconoscimento delle auto dalle immagini. In questa tesi presentiamo la nostra architettura di Rete Neurale Convoluzionale per il riconoscimento di automobili e la loro posizione nello spazio, utilizzando solo input lidar. Salvando le informazioni riguardanti le bounding box attorno all’auto a livello del punto ci assicura una buona previsione anche in situazioni in cui le automobili sono occluse. I test vengono eseguiti sul dataset più utilizzato per il riconoscimento di automobili e pedoni nelle applicazioni di guida autonoma.
39
Schubert, Stefan. "Optimierter Einsatz eines 3D-Laserscanners zur Point-Cloud-basierten Kartierung und Lokalisierung im In- und Outdoorbereich." Master's thesis, Universitätsbibliothek Chemnitz, 2015. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-qucosa-161415.
Abstract:
Die Kartierung und Lokalisierung eines mobilen Roboters in seiner Umgebung ist eine wichtige Voraussetzung für dessen Autonomie. In dieser Arbeit wird der Einsatz eines 3D-Laserscanners zur Erfüllung dieser Aufgaben untersucht. Durch die optimierte Anordnung eines rotierenden 2D-Laserscanners werden hochauflösende Bereiche vorgegeben. Zudem wird mit Hilfe von ICP die Kartierung und Lokalisierung im Stillstand durchgeführt. Bei der Betrachtung zur Verbesserung der Bewegungsschätzung wird auch eine Möglichkeit zur Lokalisierung während der Bewegung mit 3D-Scans vorgestellt. Die vorgestellten Algorithmen werden durch Experimente mit realer Hardware evaluiert.
40
Megahed, Fadel M. "The Use of Image and Point Cloud Data in Statistical Process Control." Diss., Virginia Tech, 2012. http://hdl.handle.net/10919/26511.
Abstract:
The volume of data acquired in production systems continues to expand. Emerging imaging technologies, such as machine vision systems (MVSs) and 3D surface scanners, diversify the types of data being collected, further pushing data collection beyond discrete dimensional data. These large and diverse datasets increase the challenge of extracting useful information. Unfortunately, industry still relies heavily on traditional quality methods that are limited to fault detection, which fails to consider important diagnostic information needed for process recovery. Modern measurement technologies should spur the transformation of statistical process control (SPC) to provide practitioners with additional diagnostic information. This dissertation focuses on how MVSs and 3D laser scanners can be further utilized to meet that goal. More specifically, this work: 1) reviews image-based control charts while highlighting their advantages and disadvantages; 2) integrates spatiotemporal methods with digital image processing to detect process faults and estimate their location, size, and time of occurrence; and 3) shows how point cloud data (3D laser scans) can be used to detect and locate unknown faults in complex geometries. Overall, the research goal is to create new quality control tools that utilize high density data available in manufacturing environments to generate knowledge that supports decision-making beyond just indicating the existence of a process issue. This allows industrial practitioners to have a rapid process recovery once a process issue has been detected, and consequently reduce the associated downtime.Ph. D.
41
Stålberg, Martin. "Reconstruction of trees from 3D point clouds." Thesis, Uppsala universitet, Avdelningen för systemteknik, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-316833.
Abstract:
The geometrical structure of a tree can consist of thousands, even millions, of branches, twigs and leaves in complex arrangements. The structure contains a lot of useful information and can be used for example to assess a tree's health or calculate parameters such as total wood volume or branch size distribution. Because of the complexity, capturing the structure of an entire tree used to be nearly impossible, but the increased availability and quality of particularly digital cameras and Light Detection and Ranging (LIDAR) instruments is making it increasingly possible. A set of digital images of a tree, or a point cloud of a tree from a LIDAR scan, contains a lot of data, but the information about the tree structure has to be extracted from this data through analysis. This work presents a method of reconstructing 3D models of trees from point clouds. The model is constructed from cylindrical segments which are added one by one. Bayesian inference is used to determine how to optimize the parameters of model segment candidates and whether or not to accept them as part of the model. A Hough transform for finding cylinders in point clouds is presented, and used as a heuristic to guide the proposals of model segment candidates. Previous related works have mainly focused on high density point clouds of sparse trees, whereas the objective of this work was to analyze low resolution point clouds of dense almond trees. The method is evaluated on artificial and real datasets and works rather well on high quality data, but performs poorly on low resolution data with gaps and occlusions.
42
Monnier, Fabrice. "Amélioration de la localisation 3D de données laser terrestre à l'aide de cartes 2D ou modèles 3D." Thesis, Paris Est, 2014. http://www.theses.fr/2014PEST1114/document.
Abstract:
Les avancées technologiques dans le domaine informatique (logiciel et matériel) et, en particulier, de la géolocalisation ont permis la démocratisation des modèles numériques. L'arrivée depuis quelques années de véhicules de cartographie mobile a ouvert l'accès à la numérisation 3D mobile terrestre. L'un des avantages de ces nouvelles méthodes d'imagerie de l'environnement urbain est la capacité potentielle de ces systèmes à améliorer les bases de données existantes 2D comme 3D, en particulier leur niveau de détail et la diversité des objets représentés. Les bases de données géographiques sont constituées d'un ensemble de primitives géométriques (généralement des lignes en 2D et des plans ou des triangles en 3D) d'un niveau de détail grossier mais ont l'avantage d'être disponibles sur de vastes zones géographiques. Elles sont issues de la fusion d'informations diverses (anciennes campagnes réalisées manuellement, conception automatisée ou encore hybride) et peuvent donc présenter des erreurs de fabrication. Les systèmes de numérisation mobiles, eux, peuvent acquérir, entre autres, des nuages de points laser. Ces nuages laser garantissent des données d'un niveau de détail très fin pouvant aller jusqu'à plusieurs points au centimètre carré. Acquérir des nuages de points laser présente toutefois des inconvénients :- une quantité de données importante sur de faibles étendues géographiques posant des problèmes de stockage et de traitements pouvant aller jusqu'à plusieurs Téraoctet lors de campagnes d'acquisition importantes- des difficultés d'acquisition inhérentes au fait d'imager l'environnement depuis le sol. Les systèmes de numérisation mobiles présentent eux aussi des limites : en milieu urbain, le signal GPS nécessaire au bon géoréférencement des données peut être perturbé par les multi-trajets voire même stoppé lors de phénomènes de masquage GPS liés à la réduction de la portion de ciel visible pour capter assez de satellites pour en déduire une position spatiale. Améliorer les bases de données existantes grâce aux données acquises par un véhicule de numérisation mobile nécessite une mise en cohérence des deux ensembles. L'objectif principal de ce manuscrit est donc de mettre en place une chaîne de traitements automatique permettant de recaler bases de données géographiques et nuages de points laser terrestre (provenant de véhicules de cartographies mobiles) de la manière la plus fiable possible. Le recalage peut se réaliser de manière différentes. Dans ce manuscrit, nous avons développé une méthode permettant de recaler des nuages laser sur des bases de données, notamment, par la définition d'un modèle de dérive particulièrement adapté aux dérives non-linéaires de ces données mobiles. Nous avons également développé une méthode capable d'utiliser de l'information sémantique pour recaler des bases de données sur des nuages laser mobiles. Les différentes optimisations effectuées sur notre approche nous permettent de recaler des données rapidement pour une approche post-traitements, ce qui permet d'ouvrir l'approche à la gestion de grands volumes de données (milliards de points laser et milliers de primitives géométriques).Le problème du recalage conjoint a été abordé. Notre chaîne de traitements a été testée sur des données simulées et des données réelles provenant de différentes missions effectuées par l'IGNTechnological advances in computer science (software and hardware) and particularly, GPS localization made digital models accessible to all people. In recent years, mobile mapping systems has enabled large scale mobile 3D scanning. One advantage of this technology for the urban environment is the potential ability to improve existing 2D or 3D database, especially their level of detail and variety of represented objects. Geographic database consist of a set of geometric primitives (generally 2D lines and plans or triangles in 3D) with a coarse level of detail but with the advantage of being available over wide geographical areas. They come from the fusion of various information (old campaigns performed manually, automated or hybrid design) wich may lead to manufacturing errors. The mobile mapping systems can acquire laser point clouds. These point clouds guarantee a fine level of detail up to more than one points per square centimeter. But there are some disavantages :- a large amount of data on small geographic areas that may cause problems for storage and treatment of up to several Terabyte during major acquisition,- the inherent acquisition difficulties to image the environment from the ground. In urban areas, the GPS signal required for proper georeferencing data can be disturbed by multipath or even stopped when GPS masking phenomena related to the reduction of the portion of the visible sky to capture enough satellites to find a good localization. Improve existing databases through these dataset acquired by a mobile mapping system requires alignment of these two sets. The main objective of this manuscript is to establish a pipeline of automatic processes to register these datasets together in the most reliable manner. Co-registration this data can be done in different ways. In this manuscript we have focused our work on the registration of mobile laser point cloud on geographical database by using a drift model suitable for the non rigid drift of these kind of mobile data. We have also developped a method to register geographical database containing semantics on mobile point cloud. The different optimization step performed on our methods allows to register the data fast enough for post-processing pipeline, which allows the management of large volumes of data (billions of laser points and thousands geometric primitives). We have also discussed on the problem of joint deformation. Our methods have been tested on simulated data and real data from different mission performed by IGN
43
Galante, Annamaria. "Studio di CNNs sferiche per l'apprendimento di descrittori locali su Point Cloud." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/18680/.
Abstract:
Nell'ambito della Computer Vision assume sempre maggiore importanza la 3D Computer Vision.
Diversi sono i task e le applicazioni della 3D CV, così come diverse sono le possibili rappresentazioni dei dati.
Molti di questi task richiedono la ricerca di corrispondenze tra due o più scene\oggetti 3D.
Queste corrispondenze vengono individuate tramite il paradigma di Feature Matching, composto da tre step: detection, description, matching.
Le performance della pipe line di feature matching sono strettamente correlate alle tecniche utilizzate in fase di description. La creazione di descriptor compatti, informativi e invarianti alla rotazione è un problema tutt’altro che risolto in letteratura.
Recentemente sono state proposte delle architetture basate su reti convoluzionali sferiche, per il calcolo di descrittori globali da utilizzare in task come shape classification. Questi approcci, grazie alla loro trattazione matematica, permettono di essere equivarianti alla rotazione.
Lo scopo di questo elaborato di tesi è quello di fornire una panoramica dei metodi presenti allo stato dell’arte e proporre un’architettura basata su spherical cnns per apprendere un descrittore locale da usare su nuvole di punti.
44
Westling, Fredrik Anders. "Pruning of Tree Crops through 3D Reconstruction and Light Simulation using Mobile LiDAR." Thesis, The University of Sydney, 2021. https://hdl.handle.net/2123/27427.
Abstract:
Consistent sunlight access is critical when growing fruit crops, and therefore pruning is a vital operation for tree management as it can be used for controlling shading within and between trees. This thesis focuses on using Light Detection And Ranging (LiDAR) to understand and improve the light distribution of fruit trees. To enable commercial applications, the tools developed aim to provide insights on every individual tree at whole orchard scale.
Since acquisition and labelling of 3D data is difficult at a large scale, a system is developed for simulating LiDAR scans of tree crops for development and validation of techniques using infinite, perfectly-labelled datasets. Furthermore, processing scans at a large scale require rapid and relatively low-cost solutions, but many existing methods for point cloud analysis require a priori information or expensive high quality LiDAR scans. New tools are presented for structural analysis of noisy mobile LiDAR scans using a novel graph-search approach which can operate on unstructured point clouds with significant overlap between trees.
The light available to trees is important for predicting future growth and crop yields as well as making pruning decisions, but many measurement techniques cannot provide branch-level analysis, or are difficult to apply on a large scale. Using mobile LiDAR, which can easily capture large areas, a method is developed to estimate the light available throughout the canopy. A study is then performed to demonstrate the viability of this approach to replace traditional agronomic methods, enabling large-scale adoption.
The main contribution of this thesis is a novel framework for suggesting pruning decisions to improve light availability of individual trees. A full-tree quality metric is proposed and branch-scale light information identifies underexposed areas of the tree to suggest branches whose removal will improve the light distribution. Simulated tree scans are then used to validate a technique for estimating matter removed from the point cloud given specific pruning decisions, and this is used to quantify the improvement of real tree scans. The findings of this iv ABSTRACT v thesis demonstrate the value and application of mobile LiDAR in tree crops, and the tools developed through this work promise usefulness in scientific and commercial contexts.
45
Anadon, Leon Hector. "3D Shape Detection for Augmented Reality." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-231727.
Abstract:
In previous work, 2D object recognition has shown exceptional results. However, it is not possible to sense the environment spatial information, where the objects are and what they are. Having this knowledge could imply improvements in several fields like Augmented Reality by allowing virtual characters to interact more realistically with the environment and Autonomous cars by being able to make better decisions knowing where the objects are in a 3D space. The proposed work shows that it is possible to predict 3D bounding boxes with semantic labels for 3D object detection and a set of primitives for 3D shape recognition from multiple objects in a indoors scene using an algorithm that receives as input an RGB image and its 3D information. It uses Deep Neural Networks with novel architectures for point cloud feature extraction. It uses a unique feature vector capable of representing the latent space of the object that models its shape, position, size and orientation for multi-task prediction trained end-to-end with unbalanced datasets. It runs in real time (5 frames per second) in a live video feed. The method is evaluated in the NYU Depth Dataset V2 using Average Precision for object detection and 3D Intersection over Union and surface-to-surface distance for 3D shape. The results confirm that it is possible to use a shared feature vector for more than one prediction task and it generalizes for unseen objects during the training process achieving state-of-the-art results for 3D object detection and 3D shape prediction for the NYU Depth Dataset V2. Qualitative results are shown in real particular captured data showing that there could be navigation in a real-world indoor environment and that there could be collisions between the animations and the detected objects improving the interaction character-environment in Augmented Reality applications.2D-objektigenkänning har i tidigare arbeten uppvisat exceptionella resultat. Dessa modeller gör det dock inte möjligt att erhålla rumsinformation, så som föremåls position och information om vad föremålen är. Sådan kunskap kan leda till förbättringar inom flera områden så som förstärkt verklighet, så att virtuella karaktärer mer realistiskt kan interagera med miljön, samt för självstyrande bilar, så att de kan fatta bättre beslut och veta var objekt är i ett 3D-utrymme. Detta arbete visar att det är möjligt att modellera täckande rätblock med semantiska etiketter för 3D-objektdetektering, samt underliggande komponenter för 3D-formigenkänning, från flera objekt i en inomhusmiljö med en algoritm som verkar på en RGB-bild och dess 3D-information. Modellen konstrueras med djupa neurala nätverk med nya arkitekturer för Point Cloud-representationsextraktion. Den använder en unik representationsvektor som kan representera det latenta utrymmet i objektet som modellerar dess form, position, storlek och orientering för komplett träning med flera uppgifter, med obalanserade dataset. Den körs i realtid (5 bilder per sekund) i realtidsvideo. Metoden utvärderas med NYU Depth Dataset V2 med Genomsnittlig Precision för objektdetektering, 3D-Skärning över Union, samt avstånd mellan ytorna för 3D-form. Resultaten bekräftar att det är möjligt att använda en delad representationsvektor för mer än en prediktionsuppgift, och generaliserar för föremål som inte observerats under träningsprocessen. Den uppnår toppresultat för 3D-objektdetektering samt 3D-form-prediktion för NYU Depth Dataset V2. Kvalitativa resultat baserade på särskilt anskaffade data visar potential inom navigering i en verklig inomhusmiljö, samt kollision mellan animationer och detekterade objekt, vilka kan förbättra interaktonen mellan karaktär och miljö inom förstärkt verklighet-applikationer.
46
Oboňová, Veronika. "Využití laserového skenování pro 3D modelování." Master's thesis, Vysoké učení technické v Brně. Fakulta stavební, 2017. http://www.nusl.cz/ntk/nusl-390221.
Abstract:
The aim of the diploma thesis is to create a 3D model of the given object using laser scanning technology. Subsequent adjustments of the model and its separate preparation for possible 3D printing will be done through appropriate programs. The next 3D model of the identical object will be made based on the created photos and will be edited and prepared in the same way for possible 3D printing.
47
Bose, Saptak. "An integrated approach encompassing point cloud manipulation and 3D modeling for HBIM establishment: a case of study." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021.
Abstract:
In the case of Cultural Heritage buildings, the need for an effective, exhaustive, efficient method to replicate its state of being in an interactive, three-dimensional environment is today, of paramount importance, both from an engineering as well as a historical point of view. Modern geomatics entails the usage of Terrestrial Laser Scanners (TLS) and photogrammetric modelling from Structure-from-Motion (SfM) techniques to initiate this modelling operation. To realize its eventual existence, the novel Historic Building Information Modelling (HBIM) technique is implemented. A prototype library of parametric objects, based on historic architectural data, HBIM allows the generation of an all-encompassing, three-dimensional model which possesses an extensive array of information pertaining to the structure at hand. This information, be it geometric, architectural, or even structural, can then be used to realize reinforcement requirements, rehabilitation needs, stage of depreciation, method of initial construction, material makeup, historic alterations, etc. In this paper, the study of the San Michele in Acerboli’s church, located in Santarcangelo di Romagna, Italy, is considered. A HBIM model is prepared and its accuracy analyzed. The final model serves as an information repository for the aforementioned Church, able to geometrically define its finest characteristics.
48
Pereira, Nícolas Silva. "Cloud Partitioning Iterative Closest Point (CP-ICP): um estudo comparativo para registro de nuvens de pontos 3D." reponame:Repositório Institucional da UFC, 2016. http://www.repositorio.ufc.br/handle/riufc/22971.
Abstract:
PEREIRA, Nicolas Silva. Cloud Partitioning Iterative Closest Point (CP-ICP): um estudo comparativo para registro de nuvens de pontos 3D. 2016. 69 f. Dissertação (Mestrado em Engenharia de Teleinformática)–Centro de Tecnologia, Universidade Federal do Ceará, Fortaleza, 2016.Submitted by Hohana Sanders (hohanasanders@hotmail.com) on 2017-01-06T18:04:28Z No. of bitstreams: 1 2016_dis_nspereira.pdf: 7889549 bytes, checksum: d5299d9df9b32e2b1189eba97b03f9e1 (MD5)
Approved for entry into archive by Marlene Sousa (mmarlene@ufc.br) on 2017-06-01T18:21:16Z (GMT) No. of bitstreams: 1 2016_dis_nspereira.pdf: 7889549 bytes, checksum: d5299d9df9b32e2b1189eba97b03f9e1 (MD5)
Made available in DSpace on 2017-06-01T18:21:16Z (GMT). No. of bitstreams: 1 2016_dis_nspereira.pdf: 7889549 bytes, checksum: d5299d9df9b32e2b1189eba97b03f9e1 (MD5) Previous issue date: 2016-07-15
In relation to the scientific and technologic evolution of equipment such as cameras and image sensors, the computer vision presents itself more and more as a consolidated engineering solution to issues in diverse fields. Together with it, due to the 3D image sensors dissemination, the improvement and optimization of techniques that deals with 3D point clouds registration, such as the classic algorithm Iterative Closest Point (ICP), appear as fundamental on solving problems such as collision avoidance and occlusion treatment. In this context, this work proposes a sampling technique to be used prior to the ICP algorithm. The proposed method is compared to other five variations of sampling techniques based on three criteria: RMSE (root mean squared error), based also on an Euler angles analysis and an autoral criterion based on structural similarity index (SSIM). The experiments were developed on four distincts 3D models from two databases, and shows that the proposed technique achieves a more accurate point cloud registration in a smaller time than the other techniques.
Com a evolução científica e tecnológica de equipamentos como câmeras e sensores de imagens, a visão computacional se mostra cada vez mais consolidada como solução de engenharia para problemas das mais diversas áreas. Associando isto com a disseminação dos sensores de imagens 3D, o aperfeiçoamento e a otimização de técnicas que lidam com o registro de nuvens de pontos 3D, como o algoritmo clássico Iterative Closest Point (ICP), se mostram fundamentais na resolução de problemas como desvio de colisão e tratamento de oclusão. Nesse contexto, este trabalho propõe um técnica de amostragem a ser utilizada previamente ao algoritmo ICP. O método proposto é comparado com outras cinco varições de amostragem a partir de três critérios: RMSE (root mean squared error ), a partir de uma análise de ângulos de Euler e uma métrica autoral baseada no índice de structural similarity (SSIM). Os experimentos foram desenvolvidos em quatro modelos 3D distintos vindos de dois diferentes databases, e revelaram que a abordagem apresentada alcançou um registro de nuvens mais acuraz num tempo menor que as outras técnicas.
49
Abayowa, Bernard Olushola. "Automatic Registration of Optical Aerial Imagery to a LiDAR Point Cloud for Generation of Large Scale City Models." University of Dayton / OhioLINK, 2013. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1372508452.
50
YUAN, ZEHUI. "Plane-based 3D Mapping for Structured Indoor Environment." Doctoral thesis, Politecnico di Torino, 2013. http://hdl.handle.net/11583/2506288.
Abstract:
Three-dimensional (3D) mapping deals with the problem of building a map of the unknown environments explored by a mobile robot. In contrast to 2D maps, 3D maps contain richer information of the visited places. Besides enabling robot navigation in 3D, a 3D map of the robot surroundings could be of great importance for higher-level robotic tasks, like scene interpretation and object interaction or manipulation, as well as for visualization purposes in general, which are required in surveillance, urban search and rescue, surveying, and others.
Hence, the goal of this thesis is to develop a system which is capable of reconstructing the surrounding environment of a mobile robot as a three-dimensional map.
Microsoft Kinect camera is a novel sensing sensor that captures dense depth images along with RGB images at high frame rate. Recently, it has dominated the stage of 3D robotic sensing, as it is low-cost, low-power. For this work, it is used as the exteroceptive sensor and obtains 3D point clouds of the surrounding environment. Meanwhile, the wheel odometry of the robot is used to initialize the search for correspondences between different observations.
As a single 3D point cloud generated by the Microsoft Kinect sensor is composed of many tens of thousands of data points, it is necessary to compress the raw data to process them efficiently. The method chosen in this work is to use a feature-based representation which simplifies the 3D mapping procedure.
The chosen features are planar surfaces and orthogonal corners, which is based on the fact that indoor
environments are designed such that walls, ground floors,
pillars, and other major parts of the building structures can be modeled as planar surface patches, which are parallel or perpendicular to each other. While orthogonal
corners are presented as higher features which are more distinguishable in indoor environment.
In this thesis, the main idea is to obtain spatial constraints between pairwise frames by building correspondences between the extracted vertical plane features and corner features. A plane matching algorithm is presented that maximizes the similarity metric between a pair of planes within a search space to determine correspondences
between planes. The corner matching result is based on the plane matching results. The estimated spatial
constraints form the edges of a pose graph, referred to as graph-based SLAM front-end.
In order to build a map, however, a robot must be able to recognize places that it has previously visited. Limitations in sensor processing problem, coupled with environmental
ambiguity, make this difficult. In this thesis, we describe a loop closure detection algorithm by compressing point clouds into viewpoint feature histograms, inspired by their strong recognition ability. The estimated roto-translation between detected loop frames is added to the graph representing this newly discovered constraint.
Due to the estimation errors, the estimated edges form a non-globally consistent trajectory. With the aid of a linear pose graph optimizing algorithm, the most likely configuration of the robot poses can be estimated given the edges of the graph, referred to as SLAM back-end. Finally, the 3D map is retrieved by attaching each acquired point cloud to the corresponding pose estimate. The approach is validated through different experiments with a mobile robot in an indoor environment.