Journal articles: '2D/3D object discovery'

1

Mahmud, Bahar Uddin, Guan Yue Hong, Abdullah Al Mamun, Em Poh Ping, and Qingliu Wu. "Deep Learning-Based Segmentation of 3D Volumetric Image and Microstructural Analysis." Sensors 23, no. 5 (February 27, 2023): 2640. http://dx.doi.org/10.3390/s23052640.

Full text

Abstract:

As a fundamental but difficult topic in computer vision, 3D object segmentation has various applications in medical image analysis, autonomous vehicles, robotics, virtual reality, lithium battery image analysis, etc. In the past, 3D segmentation was performed using hand-made features and design techniques, but these techniques could not generalize to vast amounts of data or reach acceptable accuracy. Deep learning techniques have lately emerged as the preferred method for 3D segmentation jobs as a result of their extraordinary performance in 2D computer vision. Our proposed method used a CNN-based architecture called 3D UNET, which is inspired by the famous 2D UNET that has been used to segment volumetric image data. To see the internal changes of composite materials, for instance, in a lithium battery image, it is necessary to see the flow of different materials and follow the directions analyzing the inside properties. In this paper, a combination of 3D UNET and VGG19 has been used to conduct a multiclass segmentation of publicly available sandstone datasets to analyze their microstructures using image data based on four different objects in the samples of volumetric data. In our image sample, there are a total of 448 2D images, which are then aggregated as one 3D volume to examine the 3D volumetric data. The solution involves the segmentation of each object in the volume data and further analysis of each object to find its average size, area percentage, total area, etc. The open-source image processing package IMAGEJ is used for further analysis of individual particles. In this study, it was demonstrated that convolutional neural networks can be trained to recognize sandstone microstructure traits with an accuracy of 96.78% and an IOU of 91.12%. According to our knowledge, many prior works have applied 3D UNET for segmentation, but very few papers extend it further to show the details of particles in the sample. The proposed solution offers a computational insight for real-time implementation and is discovered to be superior to the current state-of-the-art methods. The result has importance for the creation of an approximately similar model for the microstructural analysis of volumetric data.

APA, Harvard, Vancouver, ISO, and other styles

2

Atick, Joseph J., Paul A. Griffin, and A. Norman Redlich. "Statistical Approach to Shape from Shading: Reconstruction of Three-Dimensional Face Surfaces from Single Two-Dimensional Images." Neural Computation 8, no. 6 (August 1996): 1321–40. http://dx.doi.org/10.1162/neco.1996.8.6.1321.

Full text

Abstract:

The human visual system is proficient in perceiving three-dimensional shape from the shading patterns in a two-dimensional image. How it does this is not well understood and continues to be a question of fundamental and practical interest. In this paper we present a new quantitative approach to shape-from-shading that may provide some answers. We suggest that the brain, through evolution or prior experience, has discovered that objects can be classified into lower-dimensional object-classes as to their shape. Extraction of shape from shading is then equivalent to the much simpler problem of parameter estimation in a low-dimensional space. We carry out this proposal for an important class of three-dimensional (3D) objects: human heads. From an ensemble of several hundred laser-scanned 3D heads, we use principal component analysis to derive a low-dimensional parameterization of head shape space. An algorithm for solving shape-from-shading using this representation is presented. It works well even on real images where it is able to recover the 3D surface for a given person, maintaining facial detail and identity, from a single 2D image of his face. This algorithm has applications in face recognition and animation.

APA, Harvard, Vancouver, ISO, and other styles

3

Mahima, K. T. Yasas, Asanka Perera, Sreenatha Anavatti, and Matt Garratt. "Exploring Adversarial Robustness of LiDAR Semantic Segmentation in Autonomous Driving." Sensors 23, no. 23 (December 2, 2023): 9579. http://dx.doi.org/10.3390/s23239579.

Full text

Abstract:

Deep learning networks have demonstrated outstanding performance in 2D and 3D vision tasks. However, recent research demonstrated that these networks result in failures when imperceptible perturbations are added to the input known as adversarial attacks. This phenomenon has recently received increased interest in the field of autonomous vehicles and has been extensively researched on 2D image-based perception tasks and 3D object detection. However, the adversarial robustness of 3D LiDAR semantic segmentation in autonomous vehicles is a relatively unexplored topic. This study expands the adversarial examples to LiDAR-based 3D semantic segmentation. We developed and analyzed three LiDAR point-based adversarial attack methods on different networks developed on the SemanticKITTI dataset. The findings illustrate that the Cylinder3D network has the highest adversarial susceptibility to the analyzed attacks. We investigated how the class-wise point distribution influences the adversarial robustness of each class in the SemanticKITTI dataset and discovered that ground-level points are extremely vulnerable to point perturbation attacks. Further, the transferability of each attack strategy was assessed, and we found that networks relying on point data representation demonstrate a notable level of resistance. Our findings will enable future research in developing more complex and specific adversarial attacks against LiDAR segmentation and countermeasures against adversarial attacks.

APA, Harvard, Vancouver, ISO, and other styles

4

Kello, Martin, Michal Goga, Klaudia Kotorova, Dominika Sebova, Richard Frenak, Ludmila Tkacikova, and Jan Mojzis. "Screening Evaluation of Antiproliferative, Antimicrobial and Antioxidant Activity of Lichen Extracts and Secondary Metabolites In Vitro." Plants 12, no. 3 (January 30, 2023): 611. http://dx.doi.org/10.3390/plants12030611.

Full text

Abstract:

Lichen metabolites represent a wide range of substances with a variety of biological effects. The present study was designed to analyze the potential antiproliferative, antimicrobial and antioxidative effects of several extracts from lichens (Pseudevernia furfuracea, Lobaria pulmonaria, Cetraria islandica, Evernia prunastri, Stereocaulon tomentosum, Xanthoria elegans and Umbilicaria hirsuta) and their secondary metabolites (atranorin, physodic acid, evernic acid and gyrophoric acid). The crude extract, as well as the isolated metabolites, showed potent antiproliferative, cytotoxic activity on a broad range of cancer cell lines in 2D (monolayer) and 3D (spheroid) models. Furthermore, antioxidant (2,2-diphenyl-1-picryl-hydrazylhydrate (DPPH) and in vitro antimicrobial activities were assessed. Data showed that the lichen extracts, as well as the compounds present, possessed biological potential in the studied assays. It was also observed that the extracts were more efficient and their major compounds showed strong effects as antiproliferative, antioxidant and antibacterial agents. Moreover, we demonstrated the 2D and 3D models’ importance to drug discovery for further in vivo studies. Despite the fact that lichen compounds have been neglected by the scientific community for long periods, nowadays they are objects of investigation based on their promising effects.

APA, Harvard, Vancouver, ISO, and other styles

5

Mazur, O. A., L. M. Hrubyak, O. V. Kupchynskyi, and N. V. Bankovska. "Case Study: Using 3D Speckle Tracking Echocardiography for Left Ventricular Aneurysm Diagnosis." Ukrainian journal of cardiovascular surgery, no. 4 (41) (December 16, 2020): 90–95. http://dx.doi.org/10.30702/ujcvs/20.4112/061090-095/073.7.

Full text

Abstract:

Nowadays magnetic resonance imaging (MRI) is a gold standard for diagnosing abnormalities of left ventricular geometry and function, however, it is not universally accessible. Furthermore, MRI is not compatible with pacemakers and similar devices. 3D speckle tracking echocardiography (3D STE) is a cutting-edge echocardiography imaging technique for myocardial deformation assessment. As such, 3D STE looks very promising for diagnosing structural complications of myocardial infarction (MI) and choosing the optimal surgical techniques. In this case study, we used 3D STE to assess left ventricular function in a patient with left ventricular aneurysm. The patient was admitted to National Amosov Institute of Cardiovascular Surgery three weeks after having a second MI (the first MI was reported 4 years ago). His coronary angiography showed diffuse coronary artery disease. 2D echocardiography (performed on Toshiba Artida) results: end-diastolic volume (EDV) 206 ml, end-systolic volume (ESV) 141 ml, ejection fraction (EF) (Simpson’s method) 31%. An object sized 2.2*1.6 cm was discovered in the apical region (left ventricular thrombus). 3D STE results: EDV 209 ml, ESV 182 ml, EF 13%. Global area strain (GAS) was considerably decreased (–13.7 %) showing the pattern of ischemic cardiomyopathy with multivessel disease. Due to several reasons, it was impossible to obtain an MRI scan, so a CT coronary angiography was performed (Toshiba Aquilion One). The results of multi-slice computed tomography (MSCT) were consistent with those of echocardiography. According to the results, the initial plan to resect the apical akinesia region was ruled out. The patient underwent coronary artery bypass grafting (CABG) (4 shunts), the removal of thrombi from the left ventricle (additional fresh thrombi were discovered during the surgical intervention), and left ventricular aneurysm repair under cardiopulmonary bypass. Post-treatment 3D STE results: EDV dropped to 135 ml, EF rose from 13% to 32%. GAS increased up to –20.4 %, while the strains of all segments increased to subnormal levels. The overall dynamics was positive, and the patient was discharged to undergo postoperative rehabilitation. The case shows that 3D STE data is consistent with CT data in patients with abnormal ventricular remodeling. 3D STE is a good method for differentiation between akinetic scar tissue and a dyskinetic left ventricular aneurysm.

APA, Harvard, Vancouver, ISO, and other styles

6

Seggie, R. J., R. B. Ainsworth, D.A.Johnson, J. P. M. Koninx, B. Spaargaren, and P. M. Stephenson. "AWAKENING OF A SLEEPING GIANT: SUNRISE- TROUBADOUR GAS-CONDENSATE FIELD." APPEA Journal 40, no. 1 (2000): 417. http://dx.doi.org/10.1071/aj99024.

Full text

Abstract:

The Sunrise and Troubadour fields form a complex of giant gas-condensate accumulations located in the Timor Sea some 450 km northwest of Darwin. Left unappraised for almost a quarter of a century since discovery, recently renewed attention has brought these stranded hydrocarbon accumulations to the point of comm-ercialisation.A focussed appraisal program during 1997–1999 driven by expectations of growth in LNG and domestic gas markets, involved the acquisition and processing of an extensive grid of modern 2D seismic and the drilling, coring and testing of three wells. The aim of this program was to quantify better both in-place hydrocarbon volumes (reservoir properties and their distribution) and hydrocarbon recovery efficiency (gas quality and deliverability). Maximum value has been extracted from these data via a combination of deterministic and probabilistic methods, and the integration of analyses across all disciplines.This paper provides an overview of these efforts, describes the fields and details major subsurface uncertainties. Key aspects are:3D, object-based geological modelling of the reservoir, covering the spectrum of plausible sedimentological interpretations.Convolution of rock properties, derived from seismic (AVO) inversion, with 3D geological model realisations to define reservoir properties in inter-well areas.Incorporation of faults (both seismically mapped and probabilistically modelled sub-seismic faults) into both the static 3D reservoir models and the dynamic reservoir simulations.Interpretation of a tilted gas-water contact apparently arising from flow of water in the Plover aquifer away from active tectonism to the north.Extensive gas and condensate fluid analysis and modelling.Scenario-based approach to dynamic modelling.In summary, acquisition of an extensive suite of quality data during the past two-three years coupled with novel, integrated, state-of-the-art analysis of the subsurface has led to a major increase in estimates of potentially recoverable gas and condensate. Improved volumetric confidence in conjunction with both traditional and innovative engineering design (e.g. Floating Liquefied Natural Gas technology) has made viable a range of possible commercial developments from 2005 onwards.

APA, Harvard, Vancouver, ISO, and other styles

7

Bastin, J. C., T. Boycott-Brown, A. Sims, and R. Woodhouse. "The South Morecambe Gas Field, Blocks 110/2a, 110/3a, 110/7a and 110/8a, East Irish Sea." Geological Society, London, Memoirs 20, no. 1 (2003): 107–18. http://dx.doi.org/10.1144/gsl.mem.2003.020.01.09.

Full text

Abstract:

AbstractSouth Morecambe Gas Field is situated in the East Irish Sea and produces gas from the Triassic Sherwood Sandstone Group. Exploration of the basin commenced in 1966 and the discovery well, 110/2-1, was drilled in 1974. Appraisal was complete by 1983 and development was carried out in two phases with the object of providing deliverability to help to satisfy the winter peak in demand. First gas was produced in January 1985 and production during the winter can be sustained at 50MMCMD (1750mmscfd). The stratigraphic succession of the East Irish Sea Basin (EISB) consists of Carboniferous (Dinantian to Westphalian) strata unconformably overlain by 15000 to 20000 feet of continental Permo-Triassic strata. The Triassic Sherwood Sandstone Group contains reservoir rocks and the overlying Mercia Mudstone Group evaporites provide a seal. Seismic cover of the area includes 2D and 3D data, the latter providing good images that form the basis of the current structural interpretation. The structural development of the basin commenced with extension in the Permo-Triassic followed by inversions in the late Jurassic and early Tertiary. The reservoir has been zoned using a scheme that recognizes primary depositional facies as the main criterion for correlation. The petrophysical evaluation has introduced new methods of calculating porosity, Sw and net pay. The latest reservoir pressure data has been used in a material balance study and a two tank simulation model, both give GIIP estimates which are in line with earlier estimates. The new petrophysically derived reservoir parameters were also used to make a volumetric estimate of GIIP. Remaining recoverable reserves are at least 3 Tcf.

APA, Harvard, Vancouver, ISO, and other styles

8

Sawada, Tadamasa. "Influence of 3D Centro-Symmetry on a 2D Retinal Image." Symmetry 12, no. 11 (November 12, 2020): 1863. http://dx.doi.org/10.3390/sym12111863.

Full text

Abstract:

An object is 3D centro-symmetrical if the object can be segmented into two halves and the relationship between them can be represented by a combination of reflection about a plane and a rotation through 180° about an axis that is normal to the plane. A 2D orthographic image of the 3D centro-symmetrical object is always 2D rotation-symmetrical. Note that the human visual system is known to be sensitive to 2D rotational symmetry. This human sensitivity to 2D rotational symmetry might also be used to detect 3D centro-symmetry. If it is, can this detection of 3D centro-symmetry be helpful for the perception of 3D? In this study, the geometrical properties of 3D centro-symmetry and its 2D orthographic and perspective projections were examined to find out whether 3D centro-symmetry plays any role in the perception of 3D. I found that, from a theoretical point-of-view, it is unlikely that 3D centro-symmetry can be used by the human visual system to organize a 2D image of an object in a way that makes it possible to recover the 3D shape of an object from its 2D image.

APA, Harvard, Vancouver, ISO, and other styles

9

Passarella, Rossi, and Osvari Arsalan. "Object Reconstruction from 2D Drawing sketch to 3D Object." Computer Engineering and Applications Journal 5, no. 3 (October 26, 2016): 119–26. http://dx.doi.org/10.18495/comengapp.v5i3.183.

Full text

Abstract:

Design engineer in the early phase of building up another product is Â typically using a freehand sketching to communicate or illustrate the idea in the form of orthographic projection. This orthographic projection is based on viewpoint. A translation from 2D drawingÂ view point to 3D models is needed to help engineer to imagine the product preview in 3D. This procedure includes a tedious, so that automation is needed. The way to deal with this reproduction issue begin straightforwardly from 2D freehand portraying, by using the camera, the 2D drawing is captured and then transferred to a Personal Computer. Inside the computer, the image is processed withÂ filtering to find the view point zones. The view point zone than separate to 3 zones, each zone consists of the pixel coordinate. This coordinates are used to generated and processing of 3D voxel Image according to the form of geometries. A case study is presented in order to emphasize and discuss the proposed method

APA, Harvard, Vancouver, ISO, and other styles

10

Fujiyoshi, Hironobu, and Manabu Hashimoto. "2D and 3D Feature for Object Recognition." Journal of the Robotics Society of Japan 35, no. 1 (2017): 22–27. http://dx.doi.org/10.7210/jrsj.35.22.

Full text

APA, Harvard, Vancouver, ISO, and other styles

11

Amara, Kahina, Oualid Djekoune, Nouara Achour, Mahmoud Belhocine, and Rima Narimene Bellal. "A Combined 2D–3D Object Detection Framework." IETE Journal of Research 63, no. 5 (April 19, 2017): 607–15. http://dx.doi.org/10.1080/03772063.2017.1313141.

Full text

APA, Harvard, Vancouver, ISO, and other styles

12

Liu, Zili, and Daniel Kersten. "2D observers for human 3D object recognition?" Vision Research 38, no. 15-16 (August 1998): 2507–19. http://dx.doi.org/10.1016/s0042-6989(98)00063-7.

Full text

APA, Harvard, Vancouver, ISO, and other styles

13

Vajda, Peter, Ivan Ivanov, Lutz Goldmann, Jong-Seok Lee, and Touradj Ebrahimi. "Robust Duplicate Detection of 2D and 3D Objects." International Journal of Multimedia Data Engineering and Management 1, no. 3 (July 2010): 19–40. http://dx.doi.org/10.4018/jmdem.2010070102.

Full text

Abstract:

In this paper, the authors analyze their graph-based approach for 2D and 3D object duplicate detection in still images. A graph model is used to represent the 3D spatial information of the object based on the features extracted from training images to avoid explicit and complex 3D object modeling. Therefore, improved performance can be achieved in comparison to existing methods in terms of both robustness and computational complexity. Different limitations of this approach are analyzed by evaluating performance with respect to the number of training images and calculation of optimal parameters in a number of applications. Furthermore, effectiveness of object duplicate detection algorithm is measured over different object classes. The authors’ method is shown to be robust in detecting the same objects even when images with objects are taken from different viewpoints or distances.

APA, Harvard, Vancouver, ISO, and other styles

14

Naf’an, Emil, Riza Sulaiman, and Nazlena Mohamad Ali. "Optimization of Trash Identification on the House Compound Using a Convolutional Neural Network (CNN) and Sensor System." Sensors 23, no. 3 (January 29, 2023): 1499. http://dx.doi.org/10.3390/s23031499.

Full text

Abstract:

This study aims to optimize the object identification process, especially identifying trash in the house compound. Most object identification methods cannot distinguish whether the object is a real image (3D) or a photographic image on paper (2D). This is a problem if the detected object is moved from one place to another. If the object is 2D, the robot gripper only clamps empty objects. In this study, the Sequential_Camera_LiDAR (SCL) method is proposed. This method combines a Convolutional Neural Network (CNN) with LiDAR (Light Detection and Ranging), with an accuracy of ±2 mm. After testing 11 types of trash on four CNN architectures (AlexNet, VGG16, GoogleNet, and ResNet18), the accuracy results are 80.5%, 95.6%, 98.3%, and 97.5%. This result is perfect for object identification. However, it needs to be optimized using a LiDAR sensor to determine the object in 3D or 2D. Trash will be ignored if the fast scanning process with the LiDAR sensor detects non-real (2D) trash. If Real (3D), the trash object will be scanned in detail to determine the robot gripper position in lifting the trash object. The time efficiency generated by fast scanning is between 13.33% to 59.26% depending on the object’s size. The larger the object, the greater the time efficiency. In conclusion, optimization using the combination of a CNN and a LiDAR sensor can identify trash objects correctly and determine whether the object is real (3D) or not (2D), so a decision may be made to move the trash object from the detection location.

APA, Harvard, Vancouver, ISO, and other styles

15

Latief, Fourier Dzar Eljabbar, and Umar Fauzi. "Performance Analysis of 2D and 3D Fluid Flow Modelling Using Lattice Boltzmann Method." Indonesian Journal of Physics 18, no. 2 (November 3, 2016): 47–52. http://dx.doi.org/10.5614/itb.ijp.2007.18.2.2.

Full text

Abstract:

Several studies have been conducted to observe properties of fluid flow in materials using the Lattice Boltzman Method (LBM). There are two widely used lattice model, the D2Q9 for the 2D simulation, and the D3Q19 for the 3D simulation. Our particular interest is to study the velocity map both using the 2D and the 3D simulation, using the same object. The aim of this study is to evaluate effectiveness and efficiency of both methods. In our simulation, the velocity profile between the 2D and 3D models differs greatly (mean error 30.4%) if the object has complex lateral structure (the shape along the z-axes differs greatly), while for the less complex object, the profile has only 1.4% of mean error. The computing time for the 3D model took 13 times longer than the simulation of the 2D model. The result from the comparison of both methods concludes that the simplification of fluid flow simulation of 3D objects into 2D objects should be taken carefully, for in some cases, the simplification is not quite appropriate.

APA, Harvard, Vancouver, ISO, and other styles

16

Zhang, Zhikang, Zhongjie Zhu, Yongqiang Bai, Yiwen Jin, and Ming Wang. "Multi-Scale Feature Fusion Point Cloud Object Detection Based on Original Point Cloud and Projection." Electronics 13, no. 11 (June 6, 2024): 2213. http://dx.doi.org/10.3390/electronics13112213.

Full text

Abstract:

Existing point cloud object detection algorithms struggle to effectively capture spatial features across different scales, often resulting in inadequate responses to changes in object size and limited feature extraction capabilities, thereby affecting detection accuracy. To solve this problem, we present a point cloud object detection method based on multi-scale feature fusion of the original point cloud and projection, which aims to improve the multi-scale performance and completeness of feature extraction in point cloud object detection. First, we designed a 3D feature extraction module based on the 3D Swin Transformer. This module pre-processes the point cloud using a 3D Patch Partition approach and employs a self-attention mechanism within a 3D sliding window, along with a downsampling strategy, to effectively extract features at different scales. At the same time, we convert the 3D point cloud to a 2D image using projection technology and extract 2D features using the Swin Transformer. A 2D/3D feature fusion module is then built to integrate 2D and 3D features at the channel level through point-by-point addition and vector concatenation to improve feature completeness. Finally, the integrated feature maps are fed into the detection head to facilitate efficient object detection. Experimental results show that our method has improved the average precision of vehicle detection by 1.01% on the KITTI dataset over three levels of difficulty compared to Voxel-RCNN. In addition, visualization analyses show that our proposed algorithm also exhibits superior performance in object detection.

APA, Harvard, Vancouver, ISO, and other styles

17

Ye, Zixun, Hongying Zhang, Jingliang Gu, and Xue Li. "YOLOv7-3D: A Monocular 3D Traffic Object Detection Method from a Roadside Perspective." Applied Sciences 13, no. 20 (October 17, 2023): 11402. http://dx.doi.org/10.3390/app132011402.

Full text

Abstract:

Current autonomous driving systems predominantly focus on 3D object perception from the vehicle’s perspective. However, the single-camera 3D object detection algorithm in the roadside monitoring scenario provides stereo perception of traffic objects, offering more accurate collection and analysis of traffic information to ensure reliable support for urban traffic safety. In this paper, we propose the YOLOv7-3D algorithm specifically designed for single-camera 3D object detection from a roadside viewpoint. Our approach utilizes various information, including 2D bounding boxes, projected corner keypoints, and offset vectors relative to the center of the 2D bounding boxes, to enhance the accuracy of 3D object bounding box detection. Additionally, we introduce a 5-layer feature pyramid network (FPN) structure and a multi-scale spatial attention mechanism to improve feature saliency for objects of different scales, thereby enhancing the detection accuracy of the network. Experimental results demonstrate that our YOLOv7-3D network achieved significantly higher detection accuracy on the Rope3D dataset while reducing computational complexity by 60%.

APA, Harvard, Vancouver, ISO, and other styles

18

Lee, Wang-Ro, Keun-Ho Kang, and Ji-Sang Yoo. "Object-based Conversion of 2D Image to 3D." Journal of Korea Information and Communications Society 36, no. 9C (September 30, 2011): 555–63. http://dx.doi.org/10.7840/kics.2011.36c.9.555.

Full text

APA, Harvard, Vancouver, ISO, and other styles

19

Domokos, Csaba, and Zoltan Kato. "Realigning 2D and 3D Object Fragments without Correspondences." IEEE Transactions on Pattern Analysis and Machine Intelligence 38, no. 1 (January 1, 2016): 195–202. http://dx.doi.org/10.1109/tpami.2015.2450726.

Full text

APA, Harvard, Vancouver, ISO, and other styles

20

Polat, Ediz, Mohammed Yeasin, and Rajeev Sharma. "A 2D/3D model-based object tracking framework." Pattern Recognition 36, no. 9 (September 2003): 2127–41. http://dx.doi.org/10.1016/s0031-3203(03)00041-4.

Full text

APA, Harvard, Vancouver, ISO, and other styles

21

Bordbar, Behzad, Haowen Zhou, and Partha P. Banerjee. "3D object recognition through processing of 2D holograms." Applied Optics 58, no. 34 (October 23, 2019): G197. http://dx.doi.org/10.1364/ao.58.00g197.

Full text

APA, Harvard, Vancouver, ISO, and other styles

22

Zhang, Nengyu. "A new Electron Microscopy tomography: Least squares pseudoimage reconstruction technique." Proceedings, annual meeting, Electron Microscopy Society of America 49 (August 1991): 538–39. http://dx.doi.org/10.1017/s0424820100087008.

Full text

Abstract:

The least square pseudoimage (LSP) Reconstruction technique is based on matrix inversion. Due to the absence of information in electron microscopy, usually in an angle range from 60° to 90°, the matrix is degraded. The degraded matrix is used to compute two-dimensional (2D) projections of the three-dimensional (3D) object along the Z-axis (direction of the electron beam) and tilted around the Y-axis (tilt axis). Applying the pseudoinverse of the degraded matrix to electron micrographs, which are 2D projections of the 3D object, gives the pseudoimage.Since all of the slices which are perpendicular to the Y axis are related to the same degraded matrix, the 3D reconstruction problem can be simplified as series 2D reconstruction problems. All of the 2D pseudoimages are formed by the same pseudoinverse of a degraded matrix. In this case, however, the degraded matrix projects a 2D object onto an ID projection along the Z axis. Each slice is computed from a single line in all of the electron micrographs.

APA, Harvard, Vancouver, ISO, and other styles

23

Gupta, Neetika, and Naimul Mefraz Khan. "Efficient and Scalable Object Localization in 3D on Mobile Device." Journal of Imaging 8, no. 7 (July 8, 2022): 188. http://dx.doi.org/10.3390/jimaging8070188.

Full text

Abstract:

Two-Dimensional (2D) object detection has been an intensely discussed and researched field of computer vision. With numerous advancements made in the field over the years, we still need to identify a robust approach to efficiently conduct classification and localization of objects in our environment by just using our mobile devices. Moreover, 2D object detection limits the overall understanding of the detected object and does not provide any additional information in terms of its size and position in the real world. This work proposes an object localization solution in Three-Dimension (3D) for mobile devices using a novel approach. The proposed method works by combining a 2D object detection Convolutional Neural Network (CNN) model with Augmented Reality (AR) technologies to recognize objects in the environment and determine their real-world coordinates. We leverage the in-built Simultaneous Localization and Mapping (SLAM) capability of Google’s ARCore to detect planes and know the camera information for generating cuboid proposals from an object’s 2D bounding box. The proposed method is fast and efficient for identifying everyday objects in real-world space and, unlike mobile offloading techniques, the method is well designed to work with limited resources of a mobile device.

APA, Harvard, Vancouver, ISO, and other styles

24

Cai, Yingjie, Buyu Li, Zeyu Jiao, Hongsheng Li, Xingyu Zeng, and Xiaogang Wang. "Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (April 3, 2020): 10478–85. http://dx.doi.org/10.1609/aaai.v34i07.6618.

Full text

Abstract:

Monocular 3D object detection task aims to predict the 3D bounding boxes of objects based on monocular RGB images. Since the location recovery in 3D space is quite difficult on account of absence of depth information, this paper proposes a novel unified framework which decomposes the detection problem into a structured polygon prediction task and a depth recovery task. Different from the widely studied 2D bounding boxes, the proposed novel structured polygon in the 2D image consists of several projected surfaces of the target object. Compared to the widely-used 3D bounding box proposals, it is shown to be a better representation for 3D detection. In order to inversely project the predicted 2D structured polygon to a cuboid in the 3D physical world, the following depth recovery task uses the object height prior to complete the inverse projection transformation with the given camera projection matrix. Moreover, a fine-grained 3D box refinement scheme is proposed to further rectify the 3D detection results. Experiments are conducted on the challenging KITTI benchmark, in which our method achieves state-of-the-art detection accuracy.

APA, Harvard, Vancouver, ISO, and other styles

25

Ibrahim Shujaa, Mohamed, and Ammar Alauldeen Abdulmajeed. "Implementing bezier surface interpolation and N.N in shape reconstruction and depth estimation of a 2D image." Indonesian Journal of Electrical Engineering and Computer Science 16, no. 3 (December 1, 2019): 1609. http://dx.doi.org/10.11591/ijeecs.v16.i3.pp1609-1616.

Full text

Abstract:

<p>This paper considers a 2D image depth estimation of an object and reconstructed it into a 3D object image. The 2D image is defined by slices contains asset of points that are located along the object contours and within the object body. The depth of these slices are estimated using the neural network technique (N.N), where five factors (slice length, angle of incident light and illumination of some of point that located along the 2D object, namely control points)are used as inputs to the network the estimated depth of the slice are mapped into a 3D surface using the interpolation technique of the Bezier spleen surface. The experimental results showed an effective performance of the proposed approach.</p>

APA, Harvard, Vancouver, ISO, and other styles

26

Orlovskyi, Bronislav, O. P. Manoilenko, and Dmytro Bezuhlyi. "Object-Oriented Analysis of Frame 3D Textile Structures." Journal of Engineering Sciences 10, no. 2 (2023): C26—C35. http://dx.doi.org/10.21272/jes.2023.10(2).c4.

Full text

Abstract:

The article applied an object-oriented approach to analyze complex mechanical and technological objects based on an example of frame 3D textile structure development for objects from composite materials. Based on the research, the principle of global class inheritance of objects was analyzed and summarized using the object-oriented approach for the mechanical-technological structure of 3D fabrics using mechanical technology of sewing, weaving, knitting, and knitting productions. The design scheme of a generalized topology of object-oriented design for mechanical and technological systems of 3D fabrics of sewing, knitting, weaving, and weaving productions was developed. Methods and equipment for manufacturing mechanical-technological frame structures of 3D objects from textile materials were presented. Novel concepts of object = 3D micro-model, object = 2D mini-model, and object = 3D macro-model for frame 3D textile structures were introduced. Principles of inheritance, encapsulation, and polymorphism were applied to applicable models. For anisotropic textile 2D models, typical diagrams are given in polar coordinates for dynamic modulus of elasticity and logarithmic damping decrement.

APA, Harvard, Vancouver, ISO, and other styles

27

Mushtaq, Husnain, Xiaoheng Deng, Fizza Azhar, Mubashir Ali, and Hafiz Husnain Raza Sherazi. "PLC-Fusion: Perspective-Based Hierarchical and Deep LiDAR Camera Fusion for 3D Object Detection in Autonomous Vehicles." Information 15, no. 11 (November 19, 2024): 739. http://dx.doi.org/10.3390/info15110739.

Full text

Abstract:

Accurate 3D object detection is essential for autonomous driving, yet traditional LiDAR models often struggle with sparse point clouds. We propose perspective-aware hierarchical vision transformer-based LiDAR-camera fusion (PLC-Fusion) for 3D object detection to address this. This efficient, multi-modal 3D object detection framework integrates LiDAR and camera data for improved performance. First, our method enhances LiDAR data by projecting them onto a 2D plane, enabling the extraction of object perspective features from a probability map via the Object Perspective Sampling (OPS) module. It incorporates a lightweight perspective detector, consisting of interconnected 2D and monocular 3D sub-networks, to extract image features and generate object perspective proposals by predicting and refining top-scored 3D candidates. Second, it leverages two independent transformers—CamViT for 2D image features and LidViT for 3D point cloud features. These ViT-based representations are fused via the Cross-Fusion module for hierarchical and deep representation learning, improving performance and computational efficiency. These mechanisms enhance the utilization of semantic features in a region of interest (ROI) to obtain more representative point features, leading to a more effective fusion of information from both LiDAR and camera sources. PLC-Fusion outperforms existing methods, achieving a mean average precision (mAP) of 83.52% and 90.37% for 3D and BEV detection, respectively. Moreover, PLC-Fusion maintains a competitive inference time of 0.18 s. Our model addresses computational bottlenecks by eliminating the need for dense BEV searches and global attention mechanisms while improving detection range and precision.

APA, Harvard, Vancouver, ISO, and other styles

28

Tahir, Rohan, Allah Bux Sargano, and Zulfiqar Habib. "Voxel-Based 3D Object Reconstruction from Single 2D Image Using Variational Autoencoders." Mathematics 9, no. 18 (September 17, 2021): 2288. http://dx.doi.org/10.3390/math9182288.

Full text

Abstract:

In recent years, learning-based approaches for 3D reconstruction have gained much popularity due to their encouraging results. However, unlike 2D images, 3D cannot be represented in its canonical form to make it computationally lean and memory-efficient. Moreover, the generation of a 3D model directly from a single 2D image is even more challenging due to the limited details available from the image for 3D reconstruction. Existing learning-based techniques still lack the desired resolution, efficiency, and smoothness of the 3D models required for many practical applications. In this paper, we propose voxel-based 3D object reconstruction (V3DOR) from a single 2D image for better accuracy, one using autoencoders (AE) and another using variational autoencoders (VAE). The encoder part of both models is used to learn suitable compressed latent representation from a single 2D image, and a decoder generates a corresponding 3D model. Our contribution is twofold. First, to the best of the authors’ knowledge, it is the first time that variational autoencoders (VAE) have been employed for the 3D reconstruction problem. Second, the proposed models extract a discriminative set of features and generate a smoother and high-resolution 3D model. To evaluate the efficacy of the proposed method, experiments have been conducted on a benchmark ShapeNet data set. The results confirm that the proposed method outperforms state-of-the-art methods.

APA, Harvard, Vancouver, ISO, and other styles

29

Li, Yinhai, Fei Wang, and Xinhua Hu. "Deep-Learning-Based 3D Reconstruction: A Review and Applications." Applied Bionics and Biomechanics 2022 (September 15, 2022): 1–6. http://dx.doi.org/10.1155/2022/3458717.

Full text

Abstract:

In recent years, deep learning models have been widely used in 3D reconstruction fields and have made remarkable progress. How to stimulate deep academic interest to effectively manage the explosive augmentation of 3D models has been a research hotspot. This work shows mainstream 3D model retrieval algorithm programs based on deep learning currently developed remotely, and further subdivides their advantages and disadvantages according to the behavior evaluation of the algorithm programs obtained by trial. According to other restoration applications, the main 3D model retrieval algorithms can be divided into two categories: (1) 3D standard restoration methods supported by the model, i.e., both the restored object and the recalled object are 3D models. It can be further divided into voxel-based, point coloring-based, and appearance-based methods, and (2) cross-domain 3D model recovery methods supported by 2D replicas, that is, the retrieval motivation is 2D images, and the recovery appearance is 3D models, including retrieval methods supported by 2D display, 2D depiction-based realistic replication and 3D mold recovery methods. Finally, the work proposed novel 3D fashion retrieval algorithms supported by deep science that are analyzed and ventilated, and the unaccustomed directions of future development are prospected.

APA, Harvard, Vancouver, ISO, and other styles

30

Zhang, Maomao, Ao Li, Honglei Liu, and Minghui Wang. "Coarse-to-Fine Hand–Object Pose Estimation with Interaction-Aware Graph Convolutional Network." Sensors 21, no. 23 (December 3, 2021): 8092. http://dx.doi.org/10.3390/s21238092.

Full text

Abstract:

The analysis of hand–object poses from RGB images is important for understanding and imitating human behavior and acts as a key factor in various applications. In this paper, we propose a novel coarse-to-fine two-stage framework for hand–object pose estimation, which explicitly models hand–object relations in 3D pose refinement rather than in the process of converting 2D poses to 3D poses. Specifically, in the coarse stage, 2D heatmaps of hand and object keypoints are obtained from RGB image and subsequently fed into pose regressor to derive coarse 3D poses. As for the fine stage, an interaction-aware graph convolutional network called InterGCN is introduced to perform pose refinement by fully leveraging the hand–object relations in 3D context. One major challenge in 3D pose refinement lies in the fact that relations between hand and object change dynamically according to different HOI scenarios. In response to this issue, we leverage both general and interaction-specific relation graphs to significantly enhance the capacity of the network to cover variations of HOI scenarios for successful 3D pose refinement. Extensive experiments demonstrate state-of-the-art performance of our approach on benchmark hand–object datasets.

APA, Harvard, Vancouver, ISO, and other styles

31

Imad, Muhammad, Oualid Doukhi, and Deok-Jin Lee. "Transfer Learning Based Semantic Segmentation for 3D Object Detection from Point Cloud." Sensors 21, no. 12 (June 8, 2021): 3964. http://dx.doi.org/10.3390/s21123964.

Full text

Abstract:

Three-dimensional object detection utilizing LiDAR point cloud data is an indispensable part of autonomous driving perception systems. Point cloud-based 3D object detection has been a better replacement for higher accuracy than cameras during nighttime. However, most LiDAR-based 3D object methods work in a supervised manner, which means their state-of-the-art performance relies heavily on a large-scale and well-labeled dataset, while these annotated datasets could be expensive to obtain and only accessible in the limited scenario. Transfer learning is a promising approach to reduce the large-scale training datasets requirement, but existing transfer learning object detectors are primarily for 2D object detection rather than 3D. In this work, we utilize the 3D point cloud data more effectively by representing the birds-eye-view (BEV) scene and propose a transfer learning based point cloud semantic segmentation for 3D object detection. The proposed model minimizes the need for large-scale training datasets and consequently reduces the training time. First, a preprocessing stage filters the raw point cloud data to a BEV map within a specific field of view. Second, the transfer learning stage uses knowledge from the previously learned classification task (with more data for training) and generalizes the semantic segmentation-based 2D object detection task. Finally, 2D detection results from the BEV image have been back-projected into 3D in the postprocessing stage. We verify results on two datasets: the KITTI 3D object detection dataset and the Ouster LiDAR-64 dataset, thus demonstrating that the proposed method is highly competitive in terms of mean average precision (mAP up to 70%) while still running at more than 30 frames per second (FPS).

APA, Harvard, Vancouver, ISO, and other styles

32

Pegna, Alan J., Alexandra Darque, Mark V. Roberts, and E. Charles Leek. "Effects of stereoscopic disparity on early ERP components during classification of three-dimensional objects." Quarterly Journal of Experimental Psychology 71, no. 6 (January 1, 2018): 1419–30. http://dx.doi.org/10.1080/17470218.2017.1333129.

Full text

Abstract:

This study investigates the effects of stereo disparity on the perception of three-dimensional (3D) object shape. We tested the hypothesis that stereo input modulates the brain activity related to perceptual analyses of 3D shape configuration during image classification. High-density (256-channel) electroencephalogram (EEG) was used to record the temporal dynamics of visual shape processing under conditions of two-dimensional (2D) and 3D visual presentation. On each trial, observers made image classification judgements (‘Same’/’Different’) to two briefly presented, multi-part, novel objects. On different-object trials, stimuli could either share volumetric parts but not the global 3D shape configuration and have different parts but the same global 3D shape configuration or differ on both aspects. Analyses using mass univariate contrasts showed that the earliest sensitivity to 2D versus 3D viewing appeared as a negative deflection over posterior locations on the N1 component between 160 and 220 ms post-stimulus onset. Subsequently, event-related potential (ERP) modulations during the N2 time window between 240 and 370 ms were linked to image classification. N2 activity reflected two distinct components – an early N2 (240-290 ms) and a late N2 (290-370 ms) – that showed different patterns of responses to 2D and 3D input and differential sensitivity to 3D object structure. The results revealed that stereo input modulates the neural correlates of 3D object shape. We suggest that this reflects differential perceptual processing of object shape under conditions of stereo or mono input. These findings challenge current theories that attribute no functional role for stereo input during 3D shape perception.

APA, Harvard, Vancouver, ISO, and other styles

33

Rukhovich, D. D. "2D-to-3D Projection for Monocular and Multi-View 3D Object Detection in Outdoor Scenes." Programmnaya Ingeneria 12, no. 7 (October 11, 2021): 373–84. http://dx.doi.org/10.17587/prin.12.373-384.

Full text

Abstract:

In this article, we introduce the task of multi-view RGB-based 3D object detection as an end-to-end optimization problem. In a multi-view formulation of the 3D object detection problem, several images of a static scene are used to detect objects in the scene. To address the 3D object detection problem in a multi-view formulation, we propose a novel 3D object detection method named ImVoxelNet. ImVoxelNet is based on a fully convolutional neural network. Unlike existing 3D object detection methods, ImVoxelNet works directly with 3D representations and does not mediate 3D object detection through 2D object detection. The proposed method accepts multi-view inputs. The number of monocular images in each multi-view input can vary during training and inference; actually, this number might be unique for each multi-view input. Moreover, we propose to treat a single RGB image as a special case of a multi-view input. Accordingly, the proposed method can also accept monocular inputs with no modifications. Through extensive evaluation, we demonstrate that the proposed method successfully handles a variety of outdoor scenes. Specifically, it achieves state-of-the-art results in car detection on KITTI (monocular) and nuScenes (multi-view) benchmarks among all methods that accept RGB images. The proposed method operates in real-time, which makes it possible to integrate it into the navigation systems of autonomous devices. The results of this study can be used to address tasks of navigation, path planning, and semantic scene mapping.

APA, Harvard, Vancouver, ISO, and other styles

34

Rzepka, Karol, Michał Kulczykowski, and Paweł Wittels. "Point Cloud Filtering Using 2D-3D Matching Method." Pomiary Automatyka Robotyka 26, no. 2 (June 30, 2022): 15–21. http://dx.doi.org/10.14313/par_244/15.

Full text

Abstract:

Precision is a key feature for the development of 3D measurement systems. Time-of-flight cameras used for such measurements create point clouds containing a lot of noise, which may not be useful for further analysis. In our research to solve this problem, we propose a new method for precise point cloud filtering. We use 2D information from a telecentric lens camera to remove outlier points from 3D measurements recorded with a Time-of-Flight camera. The use of a telecentric camera allows us to obtain the most precise information about the contour of an object, which allows us to accurately filter the object reconstruction in 3D.

APA, Harvard, Vancouver, ISO, and other styles

35

Song, Wei, Dechao Li, Su Sun, Lingfeng Zhang, Yu Xin, Yunsick Sung, and Ryong Choi. "2D&3DHNet for 3D Object Classification in LiDAR Point Cloud." Remote Sensing 14, no. 13 (June 30, 2022): 3146. http://dx.doi.org/10.3390/rs14133146.

Full text

Abstract:

Accurate semantic analysis of LiDAR point clouds enables the interaction between intelligent vehicles and the real environment. This paper proposes a hybrid 2D and 3D Hough Net by combining 3D global Hough features and 2D local Hough features with a classification deep learning network. Firstly, the 3D object point clouds are mapped into the 3D Hough space to extract the global Hough features. The generated global Hough features are input into the 3D convolutional neural network for training global features. Furthermore, a multi-scale critical point sampling method is designed to extract critical points in the 2D views projected from the point clouds to reduce the computation of redundant points. To extract local features, a grid-based dynamic nearest neighbors algorithm is designed by searching the neighbors of the critical points. Finally, the two networks are connected to the full connection layer, which is input into fully connected layers for object classification.

APA, Harvard, Vancouver, ISO, and other styles

36

Liu, Leyuan, Jian He, Keyan Ren, Zhonghua Xiao, and Yibin Hou. "A LiDAR–Camera Fusion 3D Object Detection Algorithm." Information 13, no. 4 (March 26, 2022): 169. http://dx.doi.org/10.3390/info13040169.

Full text

Abstract:

3D object detection with LiDAR and camera fusion has always been a challenge for autonomous driving. This work proposes a deep neural network (namely FuDNN) for LiDAR–camera fusion 3D object detection. Firstly, a 2D backbone is designed to extract features from camera images. Secondly, an attention-based fusion sub-network is designed to fuse the features extracted by the 2D backbone and the features extracted from 3D LiDAR point clouds by PointNet++. Besides, the FuDNN, which uses the RPN and the refinement work of PointRCNN to obtain 3D box predictions, was tested on the public KITTI dataset. Experiments on the KITTI validation set show that the proposed FuDNN achieves AP values of 92.48, 82.90, and 80.51 at easy, moderate, and hard difficulty levels for car detection. The proposed FuDNN improves the performance of LiDAR–camera fusion 3D object detection in the car category of the public KITTI dataset.

APA, Harvard, Vancouver, ISO, and other styles

37

Huang, Hua Dong, Xiao Yong Fang, Zheng Chen, Jun Hong, and Ying Huang. "OpenGL Based Intuitive Interaction Technology for 3D Graphical System by 2D Devices." Applied Mechanics and Materials 373-375 (August 2013): 447–53. http://dx.doi.org/10.4028/www.scientific.net/amm.373-375.447.

Full text

Abstract:

We address the problem of how to intuitive interacts with 3D graphic system by 2D devices, and present a general interactive framework for developing human computer interaction interface for graphical system. We consider the subclass of interaction situations in which 2D devices such as mouse and windows intuitively control scene observation, select and manipulate 3D object. Based above, an object-oriented software architecture is presented to construct the virtual world, OpenGL is used to render and control 3D graphic scene and Visual C++ 6.0 platform and Windows system are combined to build the underlying structure of the software. First, compare to OpenGL select mechanism, a novel select mechanism is presented. Second, with common 2D devices, we introduced an intuitive and precise mechanism for scene observation and object manipulation. Experimental examples prove that our interactive technology is feasible and practical.

APA, Harvard, Vancouver, ISO, and other styles

38

Rodrigues, João, Roberto Lam, and Hans du Buf. "Cortical 3D Face and Object Recognition Using 2D Projections." International Journal of Creative Interfaces and Computer Graphics 3, no. 1 (January 2012): 45–62. http://dx.doi.org/10.4018/jcicg.2012010104.

Full text

Abstract:

Empirical studies concerning face recognition suggest that faces may be stored in memory by a few canonical representations. In cortical area V1 exist double-opponent colour blobs, also simple, complex and end-stopped cells which provide input for a multiscale line/edge representation, keypoints for dynamic feature routing, and saliency maps for Focus-of-Attention. All these combined allow faces to be segregated. Events of different facial views are stored in memory and combined to identify the view and recognise a face, including its expression. In this paper, the authors show that with five 2D views and their cortical representations it is possible to determine the left-right and frontal-lateral-profile views, achieving a view-invariant recognition rate of 91%. The authors also show that the same principle with eight views can be applied to 3D object recognition when they are mainly rotated about the vertical axis.

APA, Harvard, Vancouver, ISO, and other styles

39

Liu, Cheng-Hsiung, and Wen-Hsiang Tsai. "3D curved object recognition from multiple 2D camera views." Computer Vision, Graphics, and Image Processing 50, no. 2 (May 1990): 177–87. http://dx.doi.org/10.1016/0734-189x(90)90040-3.

Full text

APA, Harvard, Vancouver, ISO, and other styles

40

Liu, Cheng-Hsiung, and Wen-Hsiang Tsai. "3D curved object recognition from multiple 2D camera views." Computer Vision, Graphics, and Image Processing 49, no. 2 (February 1990): 280. http://dx.doi.org/10.1016/0734-189x(90)90146-m.

Full text

APA, Harvard, Vancouver, ISO, and other styles

41

Sinha, Pawan. "Use of 2D Similarity Metrics for 3D Object Recognition." IETE Journal of Research 49, no. 2-3 (March 2003): 113–25. http://dx.doi.org/10.1080/03772063.2003.11416330.

Full text

APA, Harvard, Vancouver, ISO, and other styles

42

Gavrila, D. M., and F. C. A. Groen. "3D object recognition from 2D images using geometric hashing." Pattern Recognition Letters 13, no. 4 (April 1992): 263–78. http://dx.doi.org/10.1016/0167-8655(92)90077-d.

Full text

APA, Harvard, Vancouver, ISO, and other styles

43

Unel, Mustafa, Octavian Soldea, Erol Ozgur, and Alp Bassa. "3D object recognition using invariants of 2D projection curves." Pattern Analysis and Applications 13, no. 4 (May 22, 2010): 451–68. http://dx.doi.org/10.1007/s10044-010-0179-5.

Full text

APA, Harvard, Vancouver, ISO, and other styles

44

Angelopoulou, Anastassia, Jose Garcia Rodriguez, Sergio Orts-Escolano, Gaurav Gupta, and Alexandra Psarrou. "Fast 2D/3D object representation with growing neural gas." Neural Computing and Applications 29, no. 10 (September 22, 2016): 903–19. http://dx.doi.org/10.1007/s00521-016-2579-y.

Full text

APA, Harvard, Vancouver, ISO, and other styles

45

Huang, H., H. Jiang, C. Brenner, and H. Mayer. "Object-level Segmentation of RGBD Data." ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences II-3 (August 7, 2014): 73–78. http://dx.doi.org/10.5194/isprsannals-ii-3-73-2014.

Full text

Abstract:

We propose a novel method to segment Microsoft™Kinect data of indoor scenes with the emphasis on freeform objects. We use the full 3D information for the scene parsing and the segmentation of potential objects instead of treating the depth values as an additional channel of the 2D image. The raw RGBD image is first converted to a 3D point cloud with color. We then group the points into patches, which are derived from a 2D superpixel segmentation. With the assumption that every patch in the point cloud represents (a part of) the surface of an underlying solid body, a hypothetical quasi-3D model – the "synthetic volume primitive" (SVP) is constructed by extending the patch with a synthetic extrusion in 3D. The SVPs vote for a common object via intersection. By this means, a freeform object can be "assembled" from an unknown number of SVPs from arbitrary angles. Besides the intersection, two other criteria, i.e., coplanarity and color coherence, are integrated in the global optimization to improve the segmentation. Experiments demonstrate the potential of the proposed method.

APA, Harvard, Vancouver, ISO, and other styles

46

TO, F. W., and K. M. TSANG. "THREE-DIMENSIONAL OBJECT RECOGNITION USING AN ORTHOGONAL COMPLEX AR MODEL APPROACH." International Journal of Pattern Recognition and Artificial Intelligence 14, no. 02 (March 2000): 93–112. http://dx.doi.org/10.1142/s021800140000009x.

Full text

Abstract:

The analysis and recognition of 2D shapes using the orthogonal complex AR model has been extended for the recognition of arbitrary 3D objects. A 3D object is placed at one of its stable orientation and sectioned into a fixed number of "slices" of equal thickness in such a way that the "slices" are parallel to the object's stable plane. The surface of an object can be represented by a sequence of these parallel 2D closed contours. A complex AR model is then fitted to each of these contours. An orthogonal estimator is implemented to determine the correct model order and to estimate the associated model parameters. The estimated AR model parameters, magnitude ratios and the relative centroid associated with each 2D contour are used as essential features for 3D object recognition. An algorithm with hierarchical structure for the recognition of 3D objects is derived based on matching the sequence of 2D contours. Simulation studies are included to show the effectiveness of different criteria being applied at different stages of the recognition process. Test results have shown that the proposed approach can provide a feasible and effective means for recognizing arbitrary 3D objects which can be self-occluded and have a number of stable orientation.

APA, Harvard, Vancouver, ISO, and other styles

47

Liu, Xiaoyang. "Research on 3D Object Reconstruction Method based on Deep Learning." Highlights in Science, Engineering and Technology 39 (April 1, 2023): 1221–27. http://dx.doi.org/10.54097/hset.v39i.6732.

Full text

Abstract:

3D reconstruction is a classic task in the field of computer graphics. More and more researchers try to replicate the success of deep learning in 2D image processing tasks to 3D reconstruction tasks, so 3D reconstruction related research based on deep learning has gradually become a research hotspot. Compared with the traditional 3D reconstruction methods that require precision acquisition equipment and strict calibration of image information, the 3D reconstruction method based on deep learning completes the matching of 2D images to 3D models through deep neural networks, and can reconstruct 3D models of various categories of objects from RGB images obtained by ordinary acquisition equipment in a large number and quickly. This paper introduces the state of the art of 3D voxel reconstruction, 3D points cloud reconstruction and 3D mesh reconstruction, respectively. According to the different representation methods of 3D objects, the 3D object reconstruction methods based on deep learning are classified and reviewed, the characteristics and shortcomings of existing methods are analyzed, and three important research trends are summarized.

APA, Harvard, Vancouver, ISO, and other styles

48

Hu, Ke, Tongbo Cao, Yuan Li, Song Chen, and Yi Kang. "DALDet: Depth-Aware Learning Based Object Detection for Autonomous Driving." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 3 (March 24, 2024): 2229–37. http://dx.doi.org/10.1609/aaai.v38i3.27996.

Full text

Abstract:

3D object detection achieves good detection performance in autonomous driving. However, it requires substantial computational resources, which prevents its practical application. 2D object detection has less computational burden but lacks spatial and geometric information embedded in depth. Therefore, we present DALDet, an efficient depth-aware learning based 2D detector, achieving high-performance object detection for autonomous driving. We design an efficient one-stage detection framework and seamlessly integrate depth cues into convolutional neural network by introducing depth-aware convolution and depth-aware average pooling, which effectively improve the detector's ability to perceive 3D space. Moreover, we propose a depth-guided loss function for training DALDet, which effectively improves the localization ability of the detector. Due to the use of depth map, DALDet can also output the distance of the object, which is of great importance for driving applications such as obstacle avoidance. Extensive experiments demonstrate the superiority and efficiency of DALDet. In particular, our DALDet ranks 1st on both KITTI Car and Cyclist 2D detection test leaderboards among all 2D detectors with high efficiency as well as yielding competitive performance among many leading 3D detectors. Code will be available at https://github.com/hukefy/DALDet.

APA, Harvard, Vancouver, ISO, and other styles

49

Shen, Xiaoke, and Ioannis Stamos. "3D Object Detection and Instance Segmentation from 3D Range and 2D Color Images." Sensors 21, no. 4 (February 9, 2021): 1213. http://dx.doi.org/10.3390/s21041213.

Full text

Abstract:

Instance segmentation and object detection are significant problems in the fields of computer vision and robotics. We address those problems by proposing a novel object segmentation and detection system. First, we detect 2D objects based on RGB, depth only, or RGB-D images. A 3D convolutional-based system, named Frustum VoxNet, is proposed. This system generates frustums from 2D detection results, proposes 3D candidate voxelized images for each frustum, and uses a 3D convolutional neural network (CNN) based on these candidates voxelized images to perform the 3D instance segmentation and object detection. Results on the SUN RGB-D dataset show that our RGB-D-based system’s 3D inference is much faster than state-of-the-art methods, without a significant loss of accuracy. At the same time, we can provide segmentation and detection results using depth only images, with accuracy comparable to RGB-D-based systems. This is important since our methods can also work well in low lighting conditions, or with sensors that do not acquire RGB images. Finally, the use of segmentation as part of our pipeline increases detection accuracy, while providing at the same time 3D instance segmentation.

APA, Harvard, Vancouver, ISO, and other styles

50

Guo, Jing, Ming Quan Zhou, Chao Li, and Zhe Shi. "3D Object Classification Using a Two-Dimensional Hidden Markov Model." Applied Mechanics and Materials 411-414 (September 2013): 2041–46. http://dx.doi.org/10.4028/www.scientific.net/amm.411-414.2041.

Full text

Abstract:

In this paper, we develop a novel method of 3D object classification based on a Two-Dimensional Hidden Markov Model (2D HMM). Hidden Markov Models are a widely used methodology for sequential data modeling, of growing importance in the last years. In the proposed approach, each object is decomposed by a spiderweb model and a shape function D2 is computed for each bin. These feature vectors are then arranged in a sequential fashion to compose a sequence vector, which is used to train HMMs. In 2D HMM, we assume that feature vectors are statistically dependent on an underlying state process which has transition probabilities conditioning the states of two neighboring bins. Thus the dependency of two dimensions is reflected simultaneously. To classify an object, the maximized posteriori probability is calculated by a given model and the observed sequence of an unknown object. Comparing with 1D HMM, the 2D HMM gets more information from the neighboring bins. Analysis and experimental results show that the proposed approach performs better than existing ones in database.

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic '2D/3D object discovery'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles