To see the other types of publications on this topic, follow the link: 3D model-Driven reconstruction.
Journal articles on the topic '3D model-Driven reconstruction'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic '3D model-Driven reconstruction.'
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 journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Huang, Wei, San Jiang, and Wanshou Jiang. "A Model-Driven Method for Pylon Reconstruction from Oblique UAV Images." Sensors 20, no. 3 (February 4, 2020): 824. http://dx.doi.org/10.3390/s20030824.
Full textAbstract:
Pylons play an important role in the safe operation of power transmission grids. Directly reconstructing pylons from UAV images is still a great challenge due to problems of weak texture, hollow-carved structure, and self-occlusion. This paper presents an automatic model-driven method for pylon reconstruction from oblique UAV images. The pylons are reconstructed with the aid of the 3D parametric model library, which is represented by connected key points based on symmetry and coplanarity. First, an efficient pylon detection method is applied to detect the pylons in the proposed region, which are obtained by clustering the line segment intersection points. Second, the pylon model library is designed to assist in pylon reconstruction. In the predefined pylon model library, a pylon is divided into two parts: pylon body and pylon head. Before pylon reconstruction, the pylon type is identified by the inner distance shape context (IDSC) algorithm, which matches the shape contours of pylon extracted from UAV images and the projected pylon model. With the a priori shape and coplanar constraint, the line segments on pylon body are matched and the pylon body is modeled by fitting four principle legs and four side planes. Then a Markov Chain Monte Carlo (MCMC) sampler is used to estimate the parameters of the pylon head by computing the maximum probability between the projected model and the extracted line segments in images. Experimental results on several UAV image datasets show that the proposed method is a feasible way of automatically reconstructing the pylon.
2
Troccaz, J., and P. Cinquin. "Model Driven Therapy." Methods of Information in Medicine 42, no. 02 (2003): 169–76. http://dx.doi.org/10.1055/s-0038-1634329.
Full textAbstract:
Summary Objectives: Taking into account a priori knowledge is a key issue to meet the medical, scientific and industrial challenges of the progresses of Minimally Invasive Surgery. We propose an overview of these challenges. Methods: Models play a major role in representing the relevant knowledge to plan and realize complex medical and surgical interventions. We analyze the three basic steps of Perception, Decision and Action, and illustrate by some instances how models may be integrated in these steps. Results: We propose a selection of the results obtained in Model Driven Therapy. These results illustrate the issues of Perception (models allow accurate reconstruction of 3D objects from a limited set of X-ray projections), Decision (models allow to take into account elastic and dynamic characteristics of muscles), and Action (models allow to design innovative navigational and robotics aids to the realization of complex interventions). Likewise, models play a major role in the process of surgeon’s education, which leads to the concept of Virtual Orthopedic University. Conclusions: Model Driven Therapy emerges as the way to perform optimal medical and surgical interventions, providing physicians and surgeons with the possibility to augment their capacities of sensing multi-modal information, of combining them to define optimal strategies, and of performing accurate and safe actions.
3
Pistellato, Mara, Filippo Bergamasco, Andrea Torsello, Francesco Barbariol, Jeseon Yoo, Jin-Yong Jeong, and Alvise Benetazzo. "A Physics-Driven CNN Model for Real-Time Sea Waves 3D Reconstruction." Remote Sensing 13, no. 18 (September 21, 2021): 3780. http://dx.doi.org/10.3390/rs13183780.
Full textAbstract:
One of the most promising techniques for the analysis of Spatio-Temporal ocean wave fields is stereo vision. Indeed, the reconstruction accuracy and resolution typically outperform other approaches like radars, satellites, etc. However, it is computationally expensive so its application is typically restricted to the analysis of short pre-recorded sequences. What prevents such methodology from being truly real-time is the final 3D surface estimation from a scattered, non-equispaced point cloud. Recently, we studied a novel approach exploiting the temporal dependence of subsequent frames to iteratively update the wave spectrum over time. Albeit substantially faster, the unpredictable convergence time of the optimization involved still prevents its usage as a continuously running remote sensing infrastructure. In this work, we build upon the same idea, but investigating the feasibility of a fully data-driven Machine Learning (ML) approach. We designed a novel Convolutional Neural Network that learns how to produce an accurate surface from the scattered elevation data of three subsequent frames. The key idea is to embed the linear dispersion relation into the model itself to physically relate the sparse points observed at different times. Assuming that the scattered data are uniformly distributed in the spatial domain, this has the same effect of increasing the sample density of each single frame. Experiments demonstrate how the proposed technique, even if trained with purely synthetic data, can produce accurate and physically consistent surfaces at five frames per second on a modern PC.
4
Nguyen, Duc-Phong, Tan-Nhu Nguyen, Stéphanie Dakpé, Marie-Christine Ho Ba Ho Ba Tho, and Tien-Tuan Dao. "Fast 3D Face Reconstruction from a Single Image Using Different Deep Learning Approaches for Facial Palsy Patients." Bioengineering 9, no. 11 (October 27, 2022): 619. http://dx.doi.org/10.3390/bioengineering9110619.
Full textAbstract:
The 3D reconstruction of an accurate face model is essential for delivering reliable feedback for clinical decision support. Medical imaging and specific depth sensors are accurate but not suitable for an easy-to-use and portable tool. The recent development of deep learning (DL) models opens new challenges for 3D shape reconstruction from a single image. However, the 3D face shape reconstruction of facial palsy patients is still a challenge, and this has not been investigated. The contribution of the present study is to apply these state-of-the-art methods to reconstruct the 3D face shape models of facial palsy patients in natural and mimic postures from one single image. Three different methods (3D Basel Morphable model and two 3D Deep Pre-trained models) were applied to the dataset of two healthy subjects and two facial palsy patients. The reconstructed outcomes were compared to the 3D shapes reconstructed using Kinect-driven and MRI-based information. As a result, the best mean error of the reconstructed face according to the Kinect-driven reconstructed shape is 1.5 ± 1.1 mm. The best error range is 1.9 ± 1.4 mm when compared to the MRI-based shapes. Before using the procedure to reconstruct the 3D faces of patients with facial palsy or other facial disorders, several ideas for increasing the accuracy of the reconstruction can be discussed based on the results. This present study opens new avenues for the fast reconstruction of the 3D face shapes of facial palsy patients from a single image. As perspectives, the best DL method will be implemented into our computer-aided decision support system for facial disorders.
5
Liu, Yilin, Liqiang Lin, Yue Hu, Ke Xie, Chi-Wing Fu, Hao Zhang, and Hui Huang. "Learning Reconstructability for Drone Aerial Path Planning." ACM Transactions on Graphics 41, no. 6 (November 30, 2022): 1–17. http://dx.doi.org/10.1145/3550454.3555433.
Full textAbstract:
We introduce the first learning-based reconstructability predictor to improve view and path planning for large-scale 3D urban scene acquisition using unmanned drones. In contrast to previous heuristic approaches, our method learns a model that explicitly predicts how well a 3D urban scene will be reconstructed from a set of viewpoints. To make such a model trainable and simultaneously applicable to drone path planning, we simulate the proxy-based 3D scene reconstruction during training to set up the prediction. Specifically, the neural network we design is trained to predict the scene reconstructability as a function of the proxy geometry , a set of viewpoints, and optionally a series of scene images acquired in flight. To reconstruct a new urban scene, we first build the 3D scene proxy, then rely on the predicted reconstruction quality and uncertainty measures by our network, based off of the proxy geometry, to guide the drone path planning. We demonstrate that our data-driven reconstructability predictions are more closely correlated to the true reconstruction quality than prior heuristic measures. Further, our learned predictor can be easily integrated into existing path planners to yield improvements. Finally, we devise a new iterative view planning framework, based on the learned reconstructability, and show superior performance of the new planner when reconstructing both synthetic and real scenes.
6
Deng, Yujuan. "Fluid Equation-Based and Data-Driven Simulation of Special Effects Animation." Advances in Mathematical Physics 2021 (November 22, 2021): 1–11. http://dx.doi.org/10.1155/2021/7480422.
Full textAbstract:
This paper analyzes the simulation of special effects animation through fluid equations and data-driven methods. This paper also considers the needs of computer fluid animation simulation in terms of computational accuracy and simulation efficiency, takes high real-time, high interactivity, and high physical accuracy of simulation algorithm as the research focus and target, and proposes a solution algorithm and acceleration scheme based on deep neural network framework for the key problems of simulation of natural phenomena including smoke and liquid. With the deep development of artificial intelligence technology, deep neural network models are widely used in research fields such as computer image classification, speech recognition, and fluid detail synthesis with their powerful data learning capability. Its stable and efficient computational model provides a new problem-solving approach for computerized fluid animation simulation. In terms of time series reconstruction, this paper adopts a tracking-based reconstruction method, including target tracking, 2D trajectory fitting and repair, and 3D trajectory reconstruction. For continuous image sequences, a linear dynamic model algorithm based on pyramidal optical flow is used to track the feature centers of the objects, and the spatial coordinates and motion parameters of the feature points are obtained by reconstructing the motion trajectories. The experimental results show that in terms of spatial reconstruction, the matching method proposed in this paper is more accurate compared with the traditional stereo matching algorithm; in terms of time series reconstruction, the error of target tracking reduced. Finally, the 3D motion trajectory of the point feature object and the motion pattern at a certain moment are shown, and the method in this paper obtains more ideal results, which proves the effectiveness of the method.
7
Hou, Yaohui, Jianwen Song, and Lijun Wang. "P‐2.27: Application of 3D reconstruction technology in VR industry." SID Symposium Digest of Technical Papers 54, S1 (April 2023): 588–90. http://dx.doi.org/10.1002/sdtp.16361.
Full textAbstract:
VR content is a key link in building a VR ecosystem, but the extreme lack of high-quality content has become the core shortcoming restricting the development of the VR industry, so in the medium and long term, the VR industry will shift from hardware technology upgrades to high-quality content-oriented, and is expected to usher in a new round of growth driven by business model innovation and content explosion. With 3D reconstruction, users can experience virtual scenes visually and audibly. The development of 3D reconstruction technology will bring great changes to existing players, and also greatly promote the rapid development of metaverse content Through continuous algorithm improvement, 3D reconstruction continues to be applied to all aspects of life.
8
Du, Xiaofu, Qiuming Zhu, Guoru Ding, Jie Li, Qihui Wu, Tianxu Lan, Zhipeng Lin, Weizhi Zhong, and Lu Han. "UAV-Assisted Three-Dimensional Spectrum Mapping Driven by Spectrum Data and Channel Model." Symmetry 13, no. 12 (December 3, 2021): 2308. http://dx.doi.org/10.3390/sym13122308.
Full textAbstract:
As the number of civil aerial vehicles increase explosively, spectrum scarcity and security become an increasingly challenge in both the airspace and terrestrial space. To address this difficulty, this paper presents an unmanned aerial vehicle-assisted (UAV-assisted) spectrum mapping system and a spectrum data reconstruction algorithm driven by spectrum data and channel model are proposed. The reconstruction algorithm, which includes a model-driven spectrum data inference method and a spectrum data completion method with uniformity decision mechanism, can reconstruct limited and incomplete spectrum data to a three-dimensional (3D) spectrum map. As a result, spectrum scarcity and security can be achieved. Spectrum mapping is a symmetry-based digital twin technology. By employing an uniformity decision mechanism, the proposed completion method can effectively interpolate spatial data even when the collected data are unevenly distributed. The effectiveness of the proposed mapping scheme is evaluated by comparing its results with the ray-tracing simulated data of the campus scenario. Simulation results show that the proposed reconstruction algorithm outperforms the classical inverse distance weighted (IDW) interpolation method and the tensor completion method by about 12.5% and 92.3%, respectively, in terms of reconstruction accuracy when the collected spectrum data are regularly missing, unevenly distributed and limited.
9
Tripodi, S., L. Duan, F. Trastour, V. Poujad, L. Laurore, and Y. Tarabalka. "AUTOMATED CHAIN FOR LARGE-SCALE 3D RECONSTRUCTION OF URBAN SCENES FROM SATELLITE IMAGES." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-2/W16 (September 17, 2019): 243–50. http://dx.doi.org/10.5194/isprs-archives-xlii-2-w16-243-2019.
Full textAbstract:
<p><strong>Abstract.</strong> Automatic city modeling from satellite imagery is a popular yet challenging topic in remote sensing, driven by numerous applications such as telecommunications, defence and urban mamagement. In this paper, we present an automated chain for large-scale 3D reconstruction of urban scenes with a Level of Detail 1 from satellite images. The proposed framework relies on two key ingredient. First, from a stereo pair of images, we estimate a digital terrain model and a digital height model, by using a novel set of feature descriptors based on multiscale morphological analysis. Second, inspired by recent works in machine learning, we extract in an automatic way contour polygons of buildings, by adopting a fully convolutional network U-Net followed by a polygonization of the predicted mask of buildings. We demonstrate the potential of our chain by reconstructing in an automated way different areas of the world.</p>
10
Sadeghi, F., H. Arefi, A. Fallah, and M. Hahn. "3D BUILDING FAÇADE RECONSTRUCTION USING HANDHELD LASER SCANNING DATA." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XL-1-W5 (December 11, 2015): 625–30. http://dx.doi.org/10.5194/isprsarchives-xl-1-w5-625-2015.
Full textAbstract:
3D The three dimensional building modelling has been an interesting topic of research for decades and it seems that photogrammetry methods provide the only economic means to acquire truly 3D city data. According to the enormous developments of 3D building reconstruction with several applications such as navigation system, location based services and urban planning, the need to consider the semantic features (such as windows and doors) becomes more essential than ever, and therefore, a 3D model of buildings as block is not any more sufficient. To reconstruct the façade elements completely, we employed the high density point cloud data that obtained from the handheld laser scanner. The advantage of the handheld laser scanner with capability of direct acquisition of very dense 3D point clouds is that there is no need to derive three dimensional data from multi images using structure from motion techniques. This paper presents a grammar-based algorithm for façade reconstruction using handheld laser scanner data. The proposed method is a combination of bottom-up (data driven) and top-down (model driven) methods in which, at first the façade basic elements are extracted in a bottom-up way and then they are served as pre-knowledge for further processing to complete models especially in occluded and incomplete areas. The first step of data driven modelling is using the conditional RANSAC (RANdom SAmple Consensus) algorithm to detect façade plane in point cloud data and remove noisy objects like trees, pedestrians, traffic signs and poles. Then, the façade planes are divided into three depth layers to detect protrusion, indentation and wall points using density histogram. Due to an inappropriate reflection of laser beams from glasses, the windows appear like holes in point cloud data and therefore, can be distinguished and extracted easily from point cloud comparing to the other façade elements. Next step, is rasterizing the indentation layer that holds the windows and doors information. After rasterization process, the morphological operators are applied in order to remove small irrelevant objects. Next, the horizontal splitting lines are employed to determine floors and vertical splitting lines are employed to detect walls, windows, and doors. The windows, doors and walls elements which are named as terminals are clustered during classification process. Each terminal contains a special property as width. Among terminals, windows and doors are named the geometry tiles in definition of the vocabularies of grammar rules. Higher order structures that inferred by grouping the tiles resulted in the production rules. The rules with three dimensional modelled façade elements constitute formal grammar that is named façade grammar. This grammar holds all the information that is necessary to reconstruct façades in the style of the given building. Thus, it can be used to improve and complete façade reconstruction in areas with no or limited sensor data. Finally, a 3D reconstructed façade model is generated that the accuracy of its geometry size and geometry position depends on the density of the raw point cloud.
11
Mahphood, A., and H. Arefi. "A DATA DRIVEN METHOD FOR FLAT ROOF BUILDING RECONSTRUCTION FROM LiDAR POINT CLOUDS." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-4/W4 (September 26, 2017): 167–72. http://dx.doi.org/10.5194/isprs-archives-xlii-4-w4-167-2017.
Full textAbstract:
3D building modeling is one of the most important applications in photogrammetry and remote sensing. Airborne LiDAR (Light Detection And Ranging) is one of the primary information sources for building modeling. In this paper, a new data-driven method is proposed for 3D building modeling of flat roofs. First, roof segmentation is implemented using region growing method. The distance between roof points and the height difference of the points are utilized in this step. Next, the building edge points are detected using a new method that employs grid data, and then roof lines are regularized using the straight line approximation. The centroid point and direction for each line are estimated in this step. Finally, 3D model is reconstructed by integrating the roof and wall models. In the end, a qualitative and quantitative assessment of the proposed method is implemented. The results show that the proposed method could successfully model the flat roof buildings using LiDAR point cloud automatically.
12
Ilarionov, Raycho, and Krasimir Krastev. "А System for Input of 3D Objects into Computing Environment." Environment. Technology. Resources. Proceedings of the International Scientific and Practical Conference 2 (August 8, 2015): 17. http://dx.doi.org/10.17770/etr2013vol2.849.
Full textAbstract:
This paper proposes an approach for design and implementation of automated 3D scanner used for input of mechanical 3D objects into computing environment. The presented model of 3D scanner is based on kinematic diagram of positioning system with 5 degree of freedom – 3 linear and 2 rotational, each driven by servo motors. For distance measuring is used laser scanning head with rotational triangulation. The paper describes also algorithms for functional control of the scanning process, obtaining of point cloud, object reconstruction and export to standard CAD format. Keywords
13
Zavar, H., H. Arefi, S. Malihi, and M. Maboudi. "TOPOLOGY-AWARE 3D MODELLING OF INDOOR SPACES FROM POINT CLOUDS." International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLIII-B4-2021 (June 30, 2021): 267–74. http://dx.doi.org/10.5194/isprs-archives-xliii-b4-2021-267-2021.
Full textAbstract:
Abstract. In this paper we introduce a topology-aware data-driven approach for 3D reconstruction of indoor spaces, which is an active research topic with several practical applications. After separating floor and ceiling, segmentation is followed by computing the α-shapes of the segment. The adjacency graph of all α-shapes is used to find the intersecting planes. By employing a B-rep approach, an initial 3D model is computed. Afterwards, adjacency graph of the intersected planes which constitute the initial model is analyzed in order to refine the 3D model. This leads to a water-tight and topologically correct 3D model. The performance of our proposed approach is qualitatively and quantitatively evaluated on an ISPRS benchmark data set. On this dataset, we achieved 77% completeness, 53% correctness and 1.7–5 cm accuracy with comparison of the final 3D model to the ground truth.
14
Orthuber, E., and J. Avbelj. "3D BUILDING RECONSTRUCTION FROM LIDAR POINT CLOUDS BY ADAPTIVE DUAL CONTOURING." ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences II-3/W4 (March 11, 2015): 157–64. http://dx.doi.org/10.5194/isprsannals-ii-3-w4-157-2015.
Full textAbstract:
This paper presents a novel workflow for data-driven building reconstruction from Light Detection and Ranging (LiDAR) point clouds. The method comprises building extraction, a detailed roof segmentation using region growing with adaptive thresholds, segment boundary creation, and a structural 3D building reconstruction approach using adaptive 2.5D Dual Contouring. First, a 2D-grid is overlain on the segmented point cloud. Second, in each grid cell 3D vertices of the building model are estimated from the corresponding LiDAR points. Then, the number of 3D vertices is reduced in a quad-tree collapsing procedure, and the remaining vertices are connected according to their adjacency in the grid. Roof segments are represented by a Triangular Irregular Network (TIN) and are connected to each other by common vertices or - at height discrepancies - by vertical walls. Resulting 3D building models show a very high accuracy and level of detail, including roof superstructures such as dormers. The workflow is tested and evaluated for two data sets, using the evaluation method and test data of the “ISPRS Test Project on Urban Classification and 3D Building Reconstruction” (Rottensteiner et al., 2012). Results show that the proposed method is comparable with the state of the art approaches, and outperforms them regarding undersegmentation and completeness of the scene reconstruction.
15
Yang, Hao, An Qing You, Wen Wu Pan, and Hai Long Tang. "An Automatic Collision Avoidance System Based on LiDAR." Applied Mechanics and Materials 644-650 (September 2014): 952–56. http://dx.doi.org/10.4028/www.scientific.net/amm.644-650.952.
Full textAbstract:
For vehicle-borne LiDAR, a mathematical model is built for the computation and reconstruction of laser point cloud with the scanning data, GPS data and IMU data. 3D point cloud of the road and the scenery on the both sides of the road is obtained. Then according to the trajectory of the vehicle, 3D roaming for the scenery on the both sides of the road is realized using OpenGL 3D engine technology. This technology provides a probably feasible way for anti-collision of vehicles and aircrafts when driven at night, in the heavy fog or flying between the mountains.
16
Tran, Ha, and Kourosh Khoshelham. "Procedural Reconstruction of 3D Indoor Models from Lidar Data Using Reversible Jump Markov Chain Monte Carlo." Remote Sensing 12, no. 5 (March 5, 2020): 838. http://dx.doi.org/10.3390/rs12050838.
Full textAbstract:
Automated reconstruction of Building Information Models (BIMs) from point clouds has been an intensive and challenging research topic for decades. Traditionally, 3D models of indoor environments are reconstructed purely by data-driven methods, which are susceptible to erroneous and incomplete data. Procedural-based methods such as the shape grammar are more robust to uncertainty and incompleteness of the data as they exploit the regularity and repetition of structural elements and architectural design principles in the reconstruction. Nevertheless, these methods are often limited to simple architectural styles: the so-called Manhattan design. In this paper, we propose a new method based on a combination of a shape grammar and a data-driven process for procedural modelling of indoor environments from a point cloud. The core idea behind the integration is to apply a stochastic process based on reversible jump Markov Chain Monte Carlo (rjMCMC) to guide the automated application of grammar rules in the derivation of a 3D indoor model. Experiments on synthetic and real data sets show the applicability of the method to efficiently generate 3D indoor models of both Manhattan and non-Manhattan environments with high accuracy, completeness, and correctness.
17
Mahmoud, Mostafa, Wu Chen, Yang Yang, Tianxia Liu, and Yaxin Li. "Leveraging Deep Learning for Automated Reconstruction of Indoor Unstructured Elements in Scan-to-BIM." International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLVIII-1-2024 (May 10, 2024): 479–86. http://dx.doi.org/10.5194/isprs-archives-xlviii-1-2024-479-2024.
Full textAbstract:
Abstract. Achieving automatic 3D reconstruction for indoor scenes is extremely useful in the field of scene understanding. Building information modeling (BIM) models are essential for lowering project costs, assisting in building planning and renovations, as well as improving building management efficiency. However, nearly all current available scan-to-BIM approaches employ manual or semi-automatic methods. These approaches concentrate solely on significant structured objects, neglecting other unstructured elements such as furniture. The limitation arises from challenges in modeling incomplete point clouds of obstructed objects and capturing indoor scene details. Therefore, this research introduces an innovative and effective reconstruction framework based on deep learning semantic segmentation and model-driven techniques to address these limitations. The proposed framework utilizes wall segment recognition, feature extraction, opening detection, and automatic modeling to reconstruct 3D structured models of point clouds with different room layouts in both Manhattan and non-Manhattan architectures. Moreover, it provides 3D BIM models of actual unstructured elements by detecting objects, completing point clouds, establishing bounding boxes, determining type and orientation, and automatically generating 3D BIM models with a parametric algorithm implemented into the Revit software. We evaluated this framework using publicly available and locally generated point cloud datasets with varying furniture combinations and layout complexity. The results demonstrate the proposed framework's efficiency in reconstructing structured indoor elements, exhibiting completeness and geometric accuracy, and achieving precision and recall values greater than 98%. Furthermore, the generated unstructured 3D BIM models keep essential real-scene characteristics such as geometry, spatial locations, numerical aspects, various shapes, and orientations compared to literature methods.
18
Qiao, Yiya, Xiaohuan Xi, Sheng Nie, Pu Wang, Hao Guo, and Cheng Wang. "Power Pylon Reconstruction from Airborne LiDAR Data Based on Component Segmentation and Model Matching." Remote Sensing 14, no. 19 (September 30, 2022): 4905. http://dx.doi.org/10.3390/rs14194905.
Full textAbstract:
In recent years, with the rapid growth of State Grid digitization, it has become necessary to perform three-dimensional (3D) reconstruction of power elements with high efficiency and precision to achieve full coverage when simulating important transmission lines. Limited by the performance of acquisition equipment and the environment, the actual scanned point cloud usually has problems such as noise interference and data loss, presenting a great challenge for 3D reconstruction. This study proposes a model-driven 3D reconstruction method based on Airborne LiDAR point cloud data. Firstly, power pylon redirection is realized based on the Principal Component Analysis (PCA) algorithm. Secondly, the vertical and horizontal distribution characteristics of the power pylon point cloud and the graphical characteristics of the overall two-dimensional (2D) orthographic projection are analyzed to determine segmentation positions and the key segmentation position of the power pylon. The 2D alpha shape algorithm is adopted to obtain the pylon body contour points, and then the pylon feature points are extracted and corrected. Based on feature points, the components of original pylon and model pylon are registered, and the distance between the original point cloud and the model point cloud is calculated at the same time. Finally, the model with the highest matching degree is regarded as the reconstructed model of the pylon. The main advantages of the proposed method include: (1) identifying the key segmentation position according to the graphical characteristics; (2) for some pylons with much missing data, the complete model can be accurately reconstructed. The average RMSE (Root-Mean-Square Error) of all power pylon components in this study was 15.4 cm. The experimental results reveal that the effects of power pylon structure segmentation and reconstruction are satisfactory, which provides method and model support for digital management and security analysis of transmission lines.
19
Mwangangi, K. K., P. O. Mc’Okeyo, S. J. Oude Elberink, and F. Nex. "EXPLORING THE POTENTIALS OF UAV PHOTOGRAMMETRIC POINT CLOUDS IN FAÇADE DETECTION AND 3D RECONSTRUCTION OF BUILDINGS." International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLIII-B2-2022 (May 30, 2022): 433–40. http://dx.doi.org/10.5194/isprs-archives-xliii-b2-2022-433-2022.
Full textAbstract:
Abstract. The use of Airborne Laser Scanner (ALS) point clouds has dominated 3D buildings reconstruction research, thus giving photogrammetric point clouds less attention. Point cloud density, occlusion and vegetation cover are some of the concerns that promote the necessity to understand and question the completeness and correctness of UAV photogrammetric point clouds for 3D buildings reconstruction. This research explores the potentials of modelling 3D buildings from nadir and oblique UAV image data vis a vis airborne laser data. Optimal parameter settings for dense matching and reconstruction are analysed for both UAV image-based and lidar point clouds. This research employs an automatic data driven model approach to 3D building reconstruction. A proper segmentation into planar roof faces is crucial, followed by façade detection to capture the real extent of the buildings’ roof overhang. An analysis of the quality of point density and point noise, in relation to setting parameter indicates that with a minimum of 50 points/m2, most of the planar surfaces are reconstructed comfortably. But for smaller features than dormers on the roof, a denser point cloud than 80 points/m2 is needed. 3D buildings from UAVs point cloud can be improved by enhancing roof boundary by use of edge information from images. It can also be improved by merging the imagery building outlines, point clouds roof boundary and the walls outline to extract the real extent of the building.
20
Wang, Cheng-Wei, and Chao-Chung Peng. "3D Face Point Cloud Reconstruction and Recognition Using Depth Sensor." Sensors 21, no. 8 (April 7, 2021): 2587. http://dx.doi.org/10.3390/s21082587.
Full textAbstract:
Facial recognition has attracted more and more attention since the rapid growth of artificial intelligence (AI) techniques in recent years. However, most of the related works about facial reconstruction and recognition are mainly based on big data collection and image deep learning related algorithms. The data driven based AI approaches inevitably increase the computational complexity of CPU and usually highly count on GPU capacity. One of the typical issues of RGB-based facial recognition is its applicability in low light or dark environments. To solve this problem, this paper presents an effective procedure for facial reconstruction as well as facial recognition via using a depth sensor. For each testing candidate, the depth camera acquires a multi-view of its 3D point clouds. The point cloud sets are stitched for 3D model reconstruction by using the iterative closest point (ICP). Then, a segmentation procedure is designed to separate the model set into a body part and head part. Based on the segmented 3D face point clouds, certain facial features are then extracted for recognition scoring. Taking a single shot from the depth sensor, the point cloud data is going to register with other 3D face models to determine which is the best candidate the data belongs to. By using the proposed feature-based 3D facial similarity score algorithm, which composes of normal, curvature, and registration similarities between different point clouds, the person can be labeled correctly even in a dark environment. The proposed method is suitable for smart devices such as smart phones and smart pads with tiny depth camera equipped. Experiments with real-world data show that the proposed method is able to reconstruct denser models and achieve point cloud-based 3D face recognition.
21
Kada, M. "3D RECONSTRUCTION OF SIMPLE BUILDINGS FROM POINT CLOUDS USING NEURAL NETWORKS WITH CONTINUOUS CONVOLUTIONS (CONVPOINT)." International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLVIII-4/W4-2022 (October 14, 2022): 61–66. http://dx.doi.org/10.5194/isprs-archives-xlviii-4-w4-2022-61-2022.
Full textAbstract:
Abstract. The automatic reconstruction of 3D building models from airborne laser scanning point clouds or aerial imagery data in a model-driven fashion most often consists of a recognition of standardized building primitives with typically rectangular footprints and parameterized roof shapes based on a pre-defined collection, and a parameter estimation so that the selected primitives best fit the input data. For more complex buildings that consist of multiple parts, several such primitives need to be combined. This paper focuses on the reconstruction of such simple buildings, and explores the potential of Deep Learning by presenting a neural network architecture that takes a 3D point cloud of a single building as input and outputs the geometric information needed to construct a 3D building model in half-space representation with up to four roof faces like saddleback, hip, and pyramid roof. The proposed neural network architecture consists of a roof face segmentation module implemented with continuous convolutions as used in ConvPoint, which performs feature extraction directly from a set of 3D points, and four PointNet modules that predict from sampled subsets of the feature-enriched points the presence of four roof faces and their slopes. Trained with the RoofN3D dataset, which contains roof point segmentations and geometric information for 3D reconstruction purposes for about 118,000 simple buildings, the neural network achieves a performance of about 80% intersection over union (IoU) for roof face segmentation, 1.8° mean absolute error (MAE) for roof slope angles, and 95% overall accuracy (OA) for predicting the presence of faces.
22
Asdar, Sarah, Daniele Ciani, and Bruno Buongiorno Nardelli. "3D reconstruction of horizontal and vertical quasi-geostrophic currents in the North Atlantic Ocean." Earth System Science Data 16, no. 2 (February 26, 2024): 1029–46. http://dx.doi.org/10.5194/essd-16-1029-2024.
Full textAbstract:
Abstract. In this paper we introduce a new high-resolution (1/10°) data-driven dataset of 3D ocean currents developed by the National Research Council of Italy in the framework of the European Space Agency World Ocean Circulation project: the WOC-NATL3D dataset. The product domain extends over a wide portion of the North Atlantic Ocean from the surface down to 1500 m depth, and the dataset covers the period between 2010 and 2019. To generate this product, a diabatic quasi-geostrophic diagnostic model is applied to data-driven 3D temperature and salinity fields obtained through a deep learning technique, along with ERA5 fluxes and empirical estimates of the horizontal Ekman currents based on input provided by the European Copernicus Marine Service. The assessment of WOC-NATL3D currents is performed by direct validation of the total horizontal velocities with independent drifter estimates at various depths (0, 15 and 1000 m) and by comparing them with existing reanalyses that are obtained through the assimilation of observations into ocean general circulation numerical models. Our estimates of the ageostrophic components of the flow improve the total horizontal velocity reconstruction, being more accurate and closer to observations than model reanalyses in the upper layers, also providing an indirect proof of the reliability of the resulting vertical velocities. The reconstructed WOC-NATL3D currents are freely available at https://doi.org/10.12770/0aa7daac-43e6-42f3-9f95-ef7da46bc702 (Buongiorno Nardelli, 2022).
23
Yang, Xueyuan, Chao Yao, and Xiaojuan Ban. "Spatial-Related Sensors Matters: 3D Human Motion Reconstruction Assisted with Textual Semantics." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 9 (March 24, 2024): 10225–33. http://dx.doi.org/10.1609/aaai.v38i9.28888.
Full textAbstract:
Leveraging wearable devices for motion reconstruction has emerged as an economical and viable technique. Certain methodologies employ sparse Inertial Measurement Units (IMUs) on the human body and harness data-driven strategies to model human poses. However, the reconstruction of motion based solely on sparse IMU data is inherently fraught with ambiguity, a consequence of numerous identical IMU readings corresponding to different poses. In this paper, we explore the spatial importance of sparse sensors, supervised by text that describes specific actions. Specifically, uncertainty is introduced to derive weighted features for each IMU. We also design a Hierarchical Temporal Transformer (HTT) and apply contrastive learning to achieve precise temporal and feature alignment of sensor data with textual semantics. Experimental results demonstrate our proposed approach achieves significant improvements in multiple metrics compared to existing methods. Notably, with textual supervision, our method not only differentiates between ambiguous actions such as sitting and standing but also produces more precise and natural motion.
24
Fu, Chuanyu, Nan Huang, Zijie Huang, Yongjian Liao, Xiaoming Xiong, Xuexi Zhang, and Shuting Cai. "Confidence-Guided Planar-Recovering Multiview Stereo for Weakly Textured Plane of High-Resolution Image Scenes." Remote Sensing 15, no. 9 (May 8, 2023): 2474. http://dx.doi.org/10.3390/rs15092474.
Full textAbstract:
Multiview stereo (MVS) achieves efficient 3D reconstruction on Lambertian surfaces and strongly textured regions. However, the reconstruction of weakly textured regions, especially planar surfaces in weakly textured regions, still faces significant challenges due to the fuzzy matching problem of photometric consistency. In this paper, we propose a multiview stereo for recovering planar surfaces guided by confidence calculations, resulting in the construction of large-scale 3D models for high-resolution image scenes. Specifically, a confidence calculation method is proposed to express the reliability degree of plane hypothesis. It consists of multiview consistency and patch consistency, which characterize global contextual information and local spatial variation, respectively. Based on the confidence of plane hypothesis, the proposed plane supplementation generates new reliable plane hypotheses. The new planes are embedded in the confidence-driven depth estimation. In addition, an adaptive depth fusion approach is proposed to allow regions with insufficient visibility to be effectively fused into the dense point clouds. The experimental results illustrate that the proposed method can lead to a 3D model with competitive completeness and high accuracy compared with state-of-the-art methods.
25
Yuan, Zhenlong, Jiakai Cao, Zhaoxin Li, Hao Jiang, and Zhaoqi Wang. "SD-MVS: Segmentation-Driven Deformation Multi-View Stereo with Spherical Refinement and EM Optimization." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 7 (March 24, 2024): 6871–80. http://dx.doi.org/10.1609/aaai.v38i7.28512.
Full textAbstract:
In this paper, we introduce Segmentation-Driven Deformation Multi-View Stereo (SD-MVS), a method that can effectively tackle challenges in 3D reconstruction of textureless areas. We are the first to adopt the Segment Anything Model (SAM) to distinguish semantic instances in scenes and further leverage these constraints for pixelwise patch deformation on both matching cost and propagation. Concurrently, we propose a unique refinement strategy that combines spherical coordinates and gradient descent on normals and pixelwise search interval on depths, significantly improving the completeness of reconstructed 3D model. Furthermore, we adopt the Expectation-Maximization (EM) algorithm to alternately optimize the aggregate matching cost and hyperparameters, effectively mitigating the problem of parameters being excessively dependent on empirical tuning. Evaluations on the ETH3D high-resolution multi-view stereo benchmark and the Tanks and Temples dataset demonstrate that our method can achieve state-of-the-art results with less time consumption.
26
Lekadir, Karim, Matthias Lange, Veronika A. Zimmer, Corné Hoogendoorn, and Alejandro F. Frangi. "Statistically-driven 3D fiber reconstruction and denoising from multi-slice cardiac DTI using a Markov random field model." Medical Image Analysis 27 (January 2016): 105–16. http://dx.doi.org/10.1016/j.media.2015.03.006.
Full text
27
Özdemir, E., and F. Remondino. "CLASSIFICATION OF AERIAL POINT CLOUDS WITH DEEP LEARNING." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-2/W13 (June 4, 2019): 103–10. http://dx.doi.org/10.5194/isprs-archives-xlii-2-w13-103-2019.
Full textAbstract:
<p><strong>Abstract.</strong> Due to their usefulness in various implementations, such as energy evaluation, visibility analysis, emergency response, 3D cadastre, urban planning, change detection, navigation, etc., 3D city models have gained importance over the last decades. Point clouds are one of the primary data sources for the generation of realistic city models. Beside model-driven approaches, 3D building models can be directly produced from classified aerial point clouds. This paper presents an ongoing research for 3D building reconstruction based on the classification of aerial point clouds without given ancillary data (e.g. footprints, etc.). The work includes a deep learning approach based on specific geometric features extracted from the point cloud. The methodology was tested on the ISPRS 3D Semantic Labeling Contest (Vaihingen and Toronto point clouds) showing promising results, although partly affected by the low density and lack of points on the building facades for the available clouds.</p>
28
Camacho, P. H. T., V. M. R. Santiago, and C. J. S. Sarmiento. "SEMI-AUTOMATIC GENERATION OF AN LOD1 AND LOD2 3D CITY MODEL OF TANAUAN CITY, BATANGAS USING OPENSTREETMAP AND TAAL OPEN LIDAR DATA IN QGIS." International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLVI-4/W6-2021 (November 18, 2021): 77–84. http://dx.doi.org/10.5194/isprs-archives-xlvi-4-w6-2021-77-2021.
Full textAbstract:
Abstract. 3D city models have found purpose beyond simple visualization of space by serving as building blocks of digital twins and smart cities. These are useful to urban areas in the Philippines through diversified applications: urban planning, disaster mitigation, environmental monitoring, and policy making. This study explored the use of free and open-source software to generate an LOD1 and LOD2 3D city model of Tanauan City, Batangas using building footprints from OpenStreetMap and elevation models from Taal Open LiDAR data. The proposed approach consists of GIS-based methods including data pre-processing, building height extraction, roof identification, building reconstruction, and visualization. The study adopted methods from previous studies for building detection and from Zheng et al. (2017) for LOD2 building reconstruction. For LOD1, a decision tree classifier was devised to determine the appropriate height for building extrusion. For LOD2, a model-driven approach using multipatch surfaces was utilized for building reconstruction. The workflow was able to reconstruct 70.66% LOD1 building models and 55.87% LOD2 building models with 44.37% overall accuracy. The RMSE and MAE between the extracted heights from the workflow and from manual digitization has an accuracy lower than 1 m which was within the standards of CityGML. The processing time in test bench 1 and test bench 2 for LOD1 took 00:12:54.5 and 00:09:27.2 while LOD2 took 02:50:29.1 and 01:27:48.2, respectively. The results suggest that the efficient generation of LOD1 and LOD2 3D city models from open data can be achieved in the FOSS environment using less computationally intensive GIS-based algorithms.
29
Kumar, Haribalan, Dragoş M. Vasilescu, Youbing Yin, Eric A. Hoffman, Merryn H. Tawhai, and Ching-Long Lin. "Multiscale imaging and registration-driven model for pulmonary acinar mechanics in the mouse." Journal of Applied Physiology 114, no. 8 (April 15, 2013): 971–78. http://dx.doi.org/10.1152/japplphysiol.01136.2012.
Full textAbstract:
A registration-based multiscale method to obtain a deforming geometric model of mouse acinus is presented. An intact mouse lung was fixed by means of vascular perfusion at a hydrostatic inflation pressure of 20 cmH2O. Microcomputed tomography (μCT) scans were obtained at multiple resolutions. Substructural morphometric analysis of a complete acinus was performed by computing a surface-to-volume (S/V) ratio directly from the 3D reconstruction of the acinar geometry. A geometric similarity is observed to exist in the acinus where S/V is approximately preserved anywhere in the model. Using multiscale registration, the shape of the acinus at an elevated inflation pressure of 25 cmH2O is estimated. Changes in the alveolar geometry suggest that the deformation within the acinus is not isotropic. In particular, the expansion of the acinus (from 20 to 25 cmH2O) is accompanied by an increase in both surface area and volume in such a way that the S/V ratio is not significantly altered. The developed method forms a useful tool in registration-driven fluid and solid mechanics studies as displacement of the alveolar wall becomes available in a discrete sense.
30
Yasin, Hashim, and Björn Krüger. "An Efficient 3D Human Pose Retrieval and Reconstruction from 2D Image-Based Landmarks." Sensors 21, no. 7 (April 1, 2021): 2415. http://dx.doi.org/10.3390/s21072415.
Full textAbstract:
We propose an efficient and novel architecture for 3D articulated human pose retrieval and reconstruction from 2D landmarks extracted from a 2D synthetic image, an annotated 2D image, an in-the-wild real RGB image or even a hand-drawn sketch. Given 2D joint positions in a single image, we devise a data-driven framework to infer the corresponding 3D human pose. To this end, we first normalize 3D human poses from Motion Capture (MoCap) dataset by eliminating translation, orientation, and the skeleton size discrepancies from the poses and then build a knowledge-base by projecting a subset of joints of the normalized 3D poses onto 2D image-planes by fully exploiting a variety of virtual cameras. With this approach, we not only transform 3D pose space to the normalized 2D pose space but also resolve the 2D-3D cross-domain retrieval task efficiently. The proposed architecture searches for poses from a MoCap dataset that are near to a given 2D query pose in a definite feature space made up of specific joint sets. These retrieved poses are then used to construct a weak perspective camera and a final 3D posture under the camera model that minimizes the reconstruction error. To estimate unknown camera parameters, we introduce a nonlinear, two-fold method. We exploit the retrieved similar poses and the viewing directions at which the MoCap dataset was sampled to minimize the projection error. Finally, we evaluate our approach thoroughly on a large number of heterogeneous 2D examples generated synthetically, 2D images with ground-truth, a variety of real in-the-wild internet images, and a proof of concept using 2D hand-drawn sketches of human poses. We conduct a pool of experiments to perform a quantitative study on PARSE dataset. We also show that the proposed system yields competitive, convincing results in comparison to other state-of-the-art methods.
31
Xiao, Wang, Yifan Chen, Huisheng Zhang, and Denghai Shen. "Remaining Useful Life Prediction Method for High Temperature Blades of Gas Turbines Based on 3D Reconstruction and Machine Learning Techniques." Applied Sciences 13, no. 19 (October 8, 2023): 11079. http://dx.doi.org/10.3390/app131911079.
Full textAbstract:
Turbine blades are crucial components exposed to harsh conditions, such as high temperatures, high pressures, and high rotational speeds. It is of great significance to accurately predict the life of blades for reducing maintenance cost and improving the reliability of gas turbine systems. A rapid and accurate blade life assessment method holds significant importance in the maintenance plan of gas turbine engines. In this paper, a novel on-line remaining useful life (RUL) prediction method for high-temperature blades is proposed based on 3D reconstruction technology and data-driven surrogate mode. Firstly, the 3D reconstruction technology was employed to establish the geometric model of real turbine blades, and the fluid–thermal–solid analysis under actual operational conditions was carried out in ANSYS software. Six checkpoints were selected to estimate the RUL according to the stress–strain distribution of the blade surface. The maximum equivalent stress was 1481.51 MPa and the highest temperature was 1393.42 K. Moreover, the fatigue-creep lifetime was calculated according to the parameters of the selected checkpoints. The RUL error between the simulation model and commercial software (Control and Engine Health Management (CEHM)) was less than 0.986%. Secondly, different data-driven surrogate models (BP, DNN, and LSTM algorithms) were developed according to the results from numerical simulation. The maximum relative errors of BP, DNN, and LSTM models were 0.030%, 0.019%, and 0.014%. LSTM demonstrated the best performance in predicting the RUL of turbine blades with time-series characteristics. Finally, the LSTM model was utilized for predicting the RUL within a gas turbine real operational process that involved five start–stop cycles.
32
He, Y., C. Zhang, and C. S. Fraser. "An energy minimization approach to automated extraction of regular building footprints from airborne LiDAR data." ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences II-3 (August 7, 2014): 65–72. http://dx.doi.org/10.5194/isprsannals-ii-3-65-2014.
Full textAbstract:
This paper presents an automated approach to the extraction of building footprints from airborne LiDAR data based on energy minimization. Automated 3D building reconstruction in complex urban scenes has been a long-standing challenge in photogrammetry and computer vision. Building footprints constitute a fundamental component of a 3D building model and they are useful for a variety of applications. Airborne LiDAR provides large-scale elevation representation of urban scene and as such is an important data source for object reconstruction in spatial information systems. However, LiDAR points on building edges often exhibit a jagged pattern, partially due to either occlusion from neighbouring objects, such as overhanging trees, or to the nature of the data itself, including unavoidable noise and irregular point distributions. The explicit 3D reconstruction may thus result in irregular or incomplete building polygons. In the presented work, a vertex-driven Douglas-Peucker method is developed to generate polygonal hypotheses from points forming initial building outlines. The energy function is adopted to examine and evaluate each hypothesis and the optimal polygon is determined through energy minimization. The energy minimization also plays a key role in bridging gaps, where the building outlines are ambiguous due to insufficient LiDAR points. In formulating the energy function, hard constraints such as parallelism and perpendicularity of building edges are imposed, and local and global adjustments are applied. The developed approach has been extensively tested and evaluated on datasets with varying point cloud density over different terrain types. Results are presented and analysed. The successful reconstruction of building footprints, of varying structural complexity, along with a quantitative assessment employing accurate reference data, demonstrate the practical potential of the proposed approach.
33
Ishii, Shin, Sehyung Lee, Hidetoshi Urakubo, Hideaki Kume, and Haruo Kasai. "Generative and discriminative model-based approaches to microscopic image restoration and segmentation." Microscopy 69, no. 2 (March 26, 2020): 79–91. http://dx.doi.org/10.1093/jmicro/dfaa007.
Full textAbstract:
Abstract Image processing is one of the most important applications of recent machine learning (ML) technologies. Convolutional neural networks (CNNs), a popular deep learning-based ML architecture, have been developed for image processing applications. However, the application of ML to microscopic images is limited as microscopic images are often 3D/4D, that is, the image sizes can be very large, and the images may suffer from serious noise generated due to optics. In this review, three types of feature reconstruction applications to microscopic images are discussed, which fully utilize the recent advancements in ML technologies. First, multi-frame super-resolution is introduced, based on the formulation of statistical generative model-based techniques such as Bayesian inference. Second, data-driven image restoration is introduced, based on supervised discriminative model-based ML technique. In this application, CNNs are demonstrated to exhibit preferable restoration performance. Third, image segmentation based on data-driven CNNs is introduced. Image segmentation has become immensely popular in object segmentation based on electron microscopy (EM); therefore, we focus on EM image processing.
34
Wu, Xianyu, Penghao Li, Xin Zhang, Jiangtao Chen, and Feng Huang. "Three Dimensional Shape Reconstruction via Polarization Imaging and Deep Learning." Sensors 23, no. 10 (May 9, 2023): 4592. http://dx.doi.org/10.3390/s23104592.
Full textAbstract:
Deep-learning-based polarization 3D imaging techniques, which train networks in a data-driven manner, are capable of estimating a target’s surface normal distribution under passive lighting conditions. However, existing methods have limitations in restoring target texture details and accurately estimating surface normals. Information loss can occur in the fine-textured areas of the target during the reconstruction process, which can result in inaccurate normal estimation and reduce the overall reconstruction accuracy. The proposed method enables extraction of more comprehensive information, mitigates the loss of texture information during object reconstruction, enhances the accuracy of surface normal estimation, and facilitates more comprehensive and precise reconstruction of objects. The proposed networks optimize the polarization representation input by utilizing the Stokes-vector-based parameter, in addition to separated specular and diffuse reflection components. This approach reduces the impact of background noise, extracts more relevant polarization features of the target, and provides more accurate cues for restoration of surface normals. Experiments are performed using both the DeepSfP dataset and newly collected data. The results show that the proposed model can provide more accurate surface normal estimates. Compared to the UNet architecture-based method, the mean angular error is reduced by 19%, calculation time is reduced by 62%, and the model size is reduced by 11%.
35
Zhang, Longwen, Chuxiao Zeng, Qixuan Zhang, Hongyang Lin, Ruixiang Cao, Wei Yang, Lan Xu, and Jingyi Yu. "Video-Driven Neural Physically-Based Facial Asset for Production." ACM Transactions on Graphics 41, no. 6 (November 30, 2022): 1–16. http://dx.doi.org/10.1145/3550454.3555445.
Full textAbstract:
Production-level workflows for producing convincing 3D dynamic human faces have long relied on an assortment of labor-intensive tools for geometry and texture generation, motion capture and rigging, and expression synthesis. Recent neural approaches automate individual components but the corresponding latent representations cannot provide artists with explicit controls as in conventional tools. In this paper, we present a new learning-based, video-driven approach for generating dynamic facial geometries with high-quality physically-based assets. For data collection, we construct a hybrid multiview-photometric capture stage, coupling with ultra-fast video cameras to obtain raw 3D facial assets. We then set out to model the facial expression, geometry and physically-based textures using separate VAEs where we impose a global MLP based expression mapping across the latent spaces of respective networks, to preserve characteristics across respective attributes. We also model the delta information as wrinkle maps for the physically-based textures, achieving high-quality 4K dynamic textures. We demonstrate our approach in high-fidelity performer-specific facial capture and cross-identity facial motion retargeting. In addition, our multi-VAE-based neural asset, along with the fast adaptation schemes, can also be deployed to handle in-the-wild videos. Besides, we motivate the utility of our explicit facial disentangling strategy by providing various promising physically-based editing results with high realism. Comprehensive experiments show that our technique provides higher accuracy and visual fidelity than previous video-driven facial reconstruction and animation methods.
36
Dippold, Elisabeth Johanna, and Fuan Tsai. "Enhancing Building Point Cloud Reconstruction from RGB UAV Data with Machine-Learning-Based Image Translation." Sensors 24, no. 7 (April 8, 2024): 2358. http://dx.doi.org/10.3390/s24072358.
Full textAbstract:
The performance of three-dimensional (3D) point cloud reconstruction is affected by dynamic features such as vegetation. Vegetation can be detected by near-infrared (NIR)-based indices; however, the sensors providing multispectral data are resource intensive. To address this issue, this study proposes a two-stage framework to firstly improve the performance of the 3D point cloud generation of buildings with a two-view SfM algorithm, and secondly, reduce noise caused by vegetation. The proposed framework can also overcome the lack of near-infrared data when identifying vegetation areas for reducing interferences in the SfM process. The first stage includes cross-sensor training, model selection and the evaluation of image-to-image RGB to color infrared (CIR) translation with Generative Adversarial Networks (GANs). The second stage includes feature detection with multiple feature detector operators, feature removal with respect to the NDVI-based vegetation classification, masking, matching, pose estimation and triangulation to generate sparse 3D point clouds. The materials utilized in both stages are a publicly available RGB-NIR dataset, and satellite and UAV imagery. The experimental results indicate that the cross-sensor and category-wise validation achieves an accuracy of 0.9466 and 0.9024, with a kappa coefficient of 0.8932 and 0.9110, respectively. The histogram-based evaluation demonstrates that the predicted NIR band is consistent with the original NIR data of the satellite test dataset. Finally, the test on the UAV RGB and artificially generated NIR with a segmentation-driven two-view SfM proves that the proposed framework can effectively translate RGB to CIR for NDVI calculation. Further, the artificially generated NDVI is able to segment and classify vegetation. As a result, the generated point cloud is less noisy, and the 3D model is enhanced.
37
Sun, Qian, Yueran Xu, Yidan Sun, Changhua Yao, Jeannie Su Ann Lee, and Kan Chen. "GN-CNN: A Point Cloud Analysis Method for Metaverse Applications." Electronics 12, no. 2 (January 5, 2023): 273. http://dx.doi.org/10.3390/electronics12020273.
Full textAbstract:
Metaverse applications often require many new 3D point cloud models that are unlabeled and that have never been seen before; this limited information results in difficulties for data-driven model analyses. In this paper, we propose a novel data-driven 3D point cloud analysis network GN-CNN that is suitable for such scenarios. We tackle the difficulties with a few-shot learning (FSL) approach by proposing an unsupervised generative adversarial network GN-GAN to generate prior knowledge and perform warm start pre-training for GN-CNN. Furthermore, the 3D models in the Metaverse are mostly acquired with a focus on the models’ visual appearances instead of the exact positions. Thus, conceptually, we also propose to augment the information by unleashing and incorporating local variance information, which conveys the appearance of the model. This is realized by introducing a graph convolution-enhanced combined multilayer perceptron operation (CMLP), namely GCMLP, to capture the local geometric relationship as well as a local normal-aware GeoConv, namely GNConv. The GN-GAN adopts an encoder–decoder structure and the GCMLP is used as the core operation of the encoder. It can perform the reconstruction task. The GNConv is used as the convolution-like operation in GN-CNN. The classification performance of GN-CNN is evaluated on ModelNet10 with an overall accuracy of 95.9%. Its few-shot learning performance is evaluated on ModelNet40, when the training set size is reduced to 30%, the overall classification accuracy can reach 91.8%, which is 2.5% higher than Geo-CNN. Experiments show that the proposed method could improve the accuracy in 3D point cloud classification tasks and under few-shot learning scenarios, compared with existing methods such as PointNet, PointNet++, DGCNN, and Geo-CNN, making it a beneficial method for Metaverse applications.
38
Sadeghi, F., and H. Arefi. "OCCLUDED AREA REMOVING FROM HANDHELD LASER SCANNER DATA DURING 3D BUILDING MODELLING." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-4/W18 (October 19, 2019): 935–39. http://dx.doi.org/10.5194/isprs-archives-xlii-4-w18-935-2019.
Full textAbstract:
Abstract. 3D building modelling has been turned to be one of the most interesting and hottest subjects in photogrammetry in last two decades, and it seems that photogrammetry provides the only economic means to acquire truly 3D city-data. Most of the researches proposed methods for 3d building modelling in LoD2 using aerial images and LIDAR data and the produced models will be enriched by oblique images, therefore there is always a demand for a user to interpret the façade or in other manual building reconstruction process the operator should draw boundaries to represent the building model and the process will be too time-consuming for 3d modelling for a whole city. Creating building facade models for a whole city requires considerable work, therefore for decades, much research has been dedicated to the automation of this reconstruction process. Nowadays researchers attempt to recommend a new method which is flexible to model hug variety of buildings and has a solution for several challenges such as irrelevant objects (pedestrians, trees, traffic signs, etc.), occluded areas and non-homogenous data. Based on various 3d building models applications, namely navigation systems, location-based system, city planning and etc. the demand for adding semantic features (such as windows and doors) is increasing and becoming more essential, therefore simple blocks as the representation of 3d buildings aren’t sufficient anymore. Therefore 2.5 models which show the façade details using pixel values have been substituted by LoD3 models recently.The lack of automation in image based approaches can be explained by the difficulties in image interpretation. Specifically, factors like illumination and occlusion can cause considerable confusion for machine understanding and some conditions (relative orientation, feature matching, etc.) need to be accurately determined to transfer image pixels to 3D coordinates. In recent years, terrestrial laser scanning data has been proven as a valuable source for building facade reconstruction. The point density of stationary laser scanning in urban areas can be up to hundreds or thousands of points per square meter, which is high enough for documenting most details on building facades. In comparison with image-based modelling, several steps such as image matching, intersection and resection will be eliminated, while there is no need to image interpret in laser data-based reconstruction approaches, these methods face major challenges such as extracting meaningful structures from a huge amount of data.This paper presents a data-driven algorithm for façade reconstruction, using a handheld laser scanner, Zebedee. The mentioned device is consisting of 2d laser scanner and an inertial measurement unit mounted on one or two springs, it has 270-degree field of view. Its mass is 210 g which makes it ideal for low measurement and it is maximum range is 30 m. The proposed method was implemented by using the Zebedee point cloud in order to determine the challenges of zeb1 data and ensure that the introduced device can be practical for 3d reconstruction.Due to obstacle existence, operator gross errors while data capturing and façade elements arrangement, there will always be occluded area and shadows in produced data. Occluded area cause tribulation in machine understanding and problems for automatic reconstruction algorithms. The proposed method represents a new way to detect occluded area and remove the artificial objects which are produced by them. The 3d point cloud is used to cover all façade elements and details, also image matching and producing 3-dimensional data steps will be omitted from the process.The proposed workflow is indicated in figure 1. Most researches such as road, building or other objects detection and reconstruction put ground points detection in priority in order to decrease data volume and processing time, so as a pre-processing step, point cloud is classified into two separate groups (non-ground and ground points).
39
Wu, Ziling, Ting Yang, Zhifei Deng, Baokun Huang, Han Liu, Yu Wang, Yuan Chen, Mary Caswell Stoddard, Ling Li, and Yunhui Zhu. "Automatic Crack Detection and Analysis for Biological Cellular Materials in X-Ray In Situ Tomography Measurements." Integrating Materials and Manufacturing Innovation 8, no. 4 (November 25, 2019): 559–69. http://dx.doi.org/10.1007/s40192-019-00162-3.
Full textAbstract:
AbstractWe introduce a novel methodology, based on in situ X-ray tomography measurements, to quantify and analyze 3D crack morphologies in biological cellular materials during damage process. Damage characterization in cellular materials is challenging due to the difficulty of identifying and registering cracks from the complicated 3D network structure. In this paper, we develop a pipeline of computer vision algorithms to extract crack patterns from a large volumetric dataset of in situ X-ray tomography measurement obtained during a compression test. Based on a hybrid approach using both model-based feature filtering and data-driven machine learning, the proposed method shows high efficiency and accuracy in identifying the crack pattern from the complex cellular structures and tomography reconstruction artifacts. The identified cracks are registered as 3D tilted planes, where 3D morphology descriptors including crack location, crack opening width, and crack plane orientation are registered to provide quantitative data for future mechanical analysis. This method is applied to two different biological materials with different levels of porosity, i.e., sea urchin (Heterocentrotus mamillatus) spines and emu (Dromaius novaehollandiae) eggshells. The results are verified by experienced human image readers. The methodology presented in this paper can be utilized for crack analysis in many other cellular solids, including both synthetic and natural materials.
40
Chen, Xin, Anqi Pang, Wei Yang, Peihao Wang, Lan Xu, and Jingyi Yu. "TightCap: 3D Human Shape Capture with Clothing Tightness Field." ACM Transactions on Graphics 41, no. 1 (February 28, 2022): 1–17. http://dx.doi.org/10.1145/3478518.
Full textAbstract:
In this article, we present TightCap, a data-driven scheme to capture both the human shape and dressed garments accurately with only a single three-dimensional (3D) human scan, which enables numerous applications such as virtual try-on, biometrics, and body evaluation. To break the severe variations of the human poses and garments, we propose to model the clothing tightness field—the displacements from the garments to the human shape implicitly in the global UV texturing domain. To this end, we utilize an enhanced statistical human template and an effective multi-stage alignment scheme to map the 3D scan into a hybrid 2D geometry image. Based on this 2D representation, we propose a novel framework to predict clothing tightness field via a novel tightness formulation, as well as an effective optimization scheme to further reconstruct multi-layer human shape and garments under various clothing categories and human postures. We further propose a new clothing tightness dataset of human scans with a large variety of clothing styles, poses, and corresponding ground-truth human shapes to stimulate further research. Extensive experiments demonstrate the effectiveness of our TightCap to achieve the high-quality human shape and dressed garments reconstruction, as well as the further applications for clothing segmentation, retargeting, and animation.
41
Xie, Ziyang, Lu Lu, Hanwen Wang, Bingyi Su, Yunan Liu, and Xu Xu. "Mitigating the risk of musculoskeletal disorders during human robot collaboration: a reinforcement learning approach." Proceedings of the Human Factors and Ergonomics Society Annual Meeting 66, no. 1 (September 2022): 1543–47. http://dx.doi.org/10.1177/1071181322661151.
Full textAbstract:
Work-related musculoskeletal disorders (MSDs) are often observed in human-robot collaboration (HRC), a common work configuration in modern factories. In this study, we aim to reduce the risk of MSDs in HRC scenarios by developing a novel model-free reinforcement learning (RL) method to improve workers’ postures. Our approach follows two steps: first, we adopt a 3D human skeleton reconstruction method to calculate workers’ Rapid Upper Limb Assessment (RULA) scores; next, we devise an online gradient-based RL algorithm to dynamically improve the RULA score. Compared with previous model-based studies, the key appeals of the proposed RL algorithm are two-fold: (i) the model-free structure allows it to “learn” the optimal worker postures without need any specific biomechanical models of tasks or workers, and (ii) the data-driven nature makes it accustomed to arbitrary users by providing personalized work configurations. Results of our experiments confirm that the proposed method can significantly improve the workers’ postures.
42
Su, Hua, Jinwen Jiang, An Wang, Wei Zhuang, and Xiao-Hai Yan. "Subsurface Temperature Reconstruction for the Global Ocean from 1993 to 2020 Using Satellite Observations and Deep Learning." Remote Sensing 14, no. 13 (July 3, 2022): 3198. http://dx.doi.org/10.3390/rs14133198.
Full textAbstract:
The reconstruction of the ocean’s 3D thermal structure is essential to the study of ocean interior processes and global climate change. Satellite remote sensing technology can collect large-scale, high-resolution ocean observation data, but only at the surface layer. Based on empirical statistical and artificial intelligence models, deep ocean remote sensing techniques allow us to retrieve and reconstruct the 3D ocean temperature structure by combining surface remote sensing observations with in situ float observations. This study proposed a new deep learning method, Convolutional Long Short-Term Memory (ConvLSTM) neural networks, which combines multisource remote sensing observations and Argo gridded data to reconstruct and produce a new long-time-series global ocean subsurface temperature (ST) dataset for the upper 2000 m from 1993 to 2020, which is named the Deep Ocean Remote Sensing (DORS) product. The data-driven ConvLSTM model can learn the spatiotemporal features of ocean observation data, significantly improves the model’s robustness and generalization ability, and outperforms the LighGBM model for the data reconstruction. The validation results show our DORS dataset has high accuracy with an average R2 and RMSE of 0.99/0.34 °C compared to the Argo gridded dataset, and the average R2 and NRMSE validated by the EN4-Profile dataset over the time series are 0.94/0.05 °C. Furthermore, the ST structure between DORS and Argo has good consistency in the 3D spatial morphology and distribution pattern, indicating that the DORS dataset has high quality and strong reliability, and well fills the pre-Argo data gaps. We effectively track the global ocean warming in the upper 2000 m from 1993 to 2020 based on the DORS dataset, and we further examine and understand the spatial patterns, evolution trends, and vertical characteristics of global ST changes. From 1993 to 2020, the average global ocean temperature warming trend is 0.063 °C/decade for the upper 2000 m. The 3D temperature trends revealed significant spatial heterogeneity across different ocean basins. Since 2005, the warming signal has become more significant in the subsurface and deeper ocean. From a remote sensing standpoint, the DORS product can provide new and robust data support for ocean interior process and climate change studies.
43
Comte, Nicolas, Sergi Pujades, Aurélien Courvoisier, Olivier Daniel, Jean-Sébastien Franco, François Faure, and Edmond Boyer. "Multi-Modal Data Correspondence for the 4D Analysis of the Spine with Adolescent Idiopathic Scoliosis." Bioengineering 10, no. 7 (July 24, 2023): 874. http://dx.doi.org/10.3390/bioengineering10070874.
Full textAbstract:
Adolescent idiopathic scoliosis is a three-dimensional spinal deformity that evolves during adolescence. Combined with static 3D X-ray acquisitions, novel approaches using motion capture allow for the analysis of the patient dynamics. However, as of today, they cannot provide an internal analysis of the spine in motion. In this study, we investigated the use of personalized kinematic avatars, created with observations of the outer (skin) and internal shape (3D spine) to infer the actual anatomic dynamics of the spine when driven by motion capture markers. Towards that end, we propose an approach to create a subject-specific digital twin from multi-modal data, namely, a surface scan of the back of the patient and a reconstruction of the 3D spine (EOS). We use radio-opaque markers to register the inner and outer observations. With respect to the previous work, our method does not rely on a precise palpation for the placement of the markers. We present the preliminary results on two cases, for which we acquired a second biplanar X-ray in a bending position. Our model can infer the spine motion from mocap markers with an accuracy below 1 cm on each anatomical axis and near 5 degrees in orientations.
44
Han, Xin, Juan Wang, and Lian Fei Wang. "Three Dimensional Measurement of Shark Body Based on Monocular and Binocular Vision." Advanced Materials Research 647 (January 2013): 239–44. http://dx.doi.org/10.4028/www.scientific.net/amr.647.239.
Full textAbstract:
To provide precise configuration reference for the engineering bionics, high accuracy detection in large field of view on the natural biological body is a prerequisite. Targeting the streamline body of carcharhinus brachyurous, 3D (three dimensional) measurement was carried out with monocular and binocular vision inspecting system based on sinusoidal structure light. By means of moving the vision sensor driven by a stepper motor, fringe patterns with variable fringe spacing were projected to every parts of the shark body, then the point clouds of different parts of the whole shark body were obtained. Using the quaternion method to joint the edges of these point clouds together, surface reconstruction was conducted. Finally the digital model of the low resistance body of shark was achieved. It would be useful reference for the configuration design of underwater vehicles, especially microminiature biomimetic underwater vehicles.
45
Radhakrishna, Chaithya Giliyar, and Philippe Ciuciu. "Jointly Learning Non-Cartesian k-Space Trajectories and Reconstruction Networks for 2D and 3D MR Imaging through Projection." Bioengineering 10, no. 2 (January 24, 2023): 158. http://dx.doi.org/10.3390/bioengineering10020158.
Full textAbstract:
Compressed sensing in magnetic resonance imaging essentially involves the optimization of (1) the sampling pattern in k-space under MR hardware constraints and (2) image reconstruction from undersampled k-space data. Recently, deep learning methods have allowed the community to address both problems simultaneously, especially in the non-Cartesian acquisition setting. This work aims to contribute to this field by tackling some major concerns in existing approaches. Particularly, current state-of-the-art learning methods seek hardware compliant k-space sampling trajectories by enforcing the hardware constraints through additional penalty terms in the training loss. Through ablation studies, we rather show the benefit of using a projection step to enforce these constraints and demonstrate that the resulting k-space trajectories are more flexible under a projection-based scheme, which results in superior performance in reconstructed image quality. In 2D studies, our novel method trajectories present an improved image reconstruction quality at a 20-fold acceleration factor on the fastMRI data set with SSIM scores of nearly 0.92–0.95 in our retrospective studies as compared to the corresponding Cartesian reference and also see a 3–4 dB gain in PSNR as compared to earlier state-of-the-art methods. Finally, we extend the algorithm to 3D and by comparing optimization as learning-based projection schemes, we show that data-driven joint learning-based method trajectories outperform model-based methods such as SPARKLING through a 2 dB gain in PSNR and 0.02 gain in SSIM.
46
Paasche, Hendrik. "Translating tomographic ambiguity into the probabilistic inference of hydrologic and engineering target parameters." GEOPHYSICS 82, no. 4 (July 1, 2017): EN67—EN79. http://dx.doi.org/10.1190/geo2015-0618.1.
Full textAbstract:
Geophysical tomography allows for spatially continuous imaging of physical parameters. In many hydrological or engineering exploration tasks, other parameters than those imaged by geophysical tomography are of higher interest, but they cannot be measured continuously in space. We have developed a methodology linking multiple tomograms imaging different physical parameters with a sparsely measured target parameter striving to achieve probabilistic, spatially continuous predictions of the target parameter distribution. Building on a fully nonlinear tomographic model reconstruction searching the solution space globally, we translate the tomographic model reconstruction ambiguity into the prediction of the target parameter. In doing so, we structurally integrate physically different tomograms achieved by individual inversion by transforming them into fuzzy sets. In a postinversion analysis, systems of linear equations are then set up and solved linking the fuzzy sets and sparse information about the target parameter, e.g., measured in boreholes. The method is fully data driven and does not require knowledge or assumptions about the expected relations between the tomographically imaged physical parameters and the target parameter. It is applicable to 2D and 3D tomographic data. Practically, the parameter interrelations can be of any complexity, including nonuniqueness. We evaluate the methodology using a synthetic database allowing for maximal control of the achieved predictions. We exemplarily predict 2D probabilistic models of porosity based on sparse porosity logging data and sets of equivalently plausible radar and seismic-velocity tomograms.
47
Budhrani, Tarash, Parth Jain, Neelanjaan De, and Bharat Dedhia. "Virtual Styling and Fitting using AI." International Journal for Research in Applied Science and Engineering Technology 11, no. 12 (December 31, 2023): 712–17. http://dx.doi.org/10.22214/ijraset.2023.57389.
Full textAbstract:
Abstract: The digitization of human forms holds significant relevance across domains like virtual reality, medical imaging, and robot navigation. While sophisticated multi-view systems excel at precise 3D body reconstruction, they remain largely inaccessible to the general consumer market. Seeking more accessible approaches, methods in human digitization explore simpler inputs, such as single images. Among these approaches, pixel-aligned implicit models [1] have garnered attention for their efficiency in capturing intricate geometric details like clothing wrinkles. These models, notably lightweight, employ parametric human body models without necessitating mappings between canonical and posed spaces. PIFu [1], a prime example, translates a parametric body model into pixel-aligned 2D feature maps, offering more comprehensive information than mere (x, y, z) coordinates. This research paper, rooted in PIFu [1], delves into the implementation intricacies of 3D human digitization within a specific domain – 3D digitization for virtual styling and fitting. In today's tech-driven world, online shopping has boomed, offering unparalleled convenience by letting users swiftly browse and buy items from home. However, despite its speed and ease, trying on clothes remains a hurdle. Without a physical store, customers struggle to gauge fit and size, leading to increased returns and order abandonment. To tackle this, a project aims to revolutionize the online clothing shopping experience. By offering a solution that allows virtual try-ons, users can visualize how clothes look and fit before buying, potentially reducing return rates and enhancing the overall shopping journey.
48
Kosk, Robert, Richard Southern, Lihua You, Shaojun Bian, Willem Kokke, and Greg Maguire. "Deep Spectral Meshes: Multi-Frequency Facial Mesh Processing with Graph Neural Networks." Electronics 13, no. 4 (February 9, 2024): 720. http://dx.doi.org/10.3390/electronics13040720.
Full textAbstract:
With the rising popularity of virtual worlds, the importance of data-driven parametric models of 3D meshes has grown rapidly. Numerous applications, such as computer vision, procedural generation, and mesh editing, vastly rely on these models. However, current approaches do not allow for independent editing of deformations at different frequency levels. They also do not benefit from representing deformations at different frequencies with dedicated representations, which would better expose their properties and improve the generated meshes’ geometric and perceptual quality. In this work, spectral meshes are introduced as a method to decompose mesh deformations into low-frequency and high-frequency deformations. These features of low- and high-frequency deformations are used for representation learning with graph convolutional networks. A parametric model for 3D facial mesh synthesis is built upon the proposed framework, exposing user parameters that control disentangled high- and low-frequency deformations. Independent control of deformations at different frequencies and generation of plausible synthetic examples are mutually exclusive objectives. A Conditioning Factor is introduced to leverage these objectives. Our model takes further advantage of spectral partitioning by representing different frequency levels with disparate, more suitable representations. Low frequencies are represented with standardised Euclidean coordinates, and high frequencies with a normalised deformation representation (DR). This paper investigates applications of our proposed approach in mesh reconstruction, mesh interpolation, and multi-frequency editing. It is demonstrated that our method improves the overall quality of generated meshes on most datasets when considering both the L1 norm and perceptual Dihedral Angle Mesh Error (DAME) metrics.
49
Chow, J. C. K., D. D. Lichti, K. D. Ang, K. Al-Durgham, G. Kuntze, G. Sharma, and J. Ronsky. "MODELLING ERRORS IN X-RAY FLUOROSCOPIC IMAGING SYSTEMS USING PHOTOGRAMMETRIC BUNDLE ADJUSTMENT WITH A DATA-DRIVEN SELF-CALIBRATION APPROACH." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-1 (September 26, 2018): 101–6. http://dx.doi.org/10.5194/isprs-archives-xlii-1-101-2018.
Full textAbstract:
<p><strong>Abstract.</strong> X-ray imaging is a fundamental tool of routine clinical diagnosis. Fluoroscopic imaging can further acquire X-ray images at video frame rates, thus enabling non-invasive in-vivo motion studies of joints, gastrointestinal tract, etc. For both the qualitative and quantitative analysis of static and dynamic X-ray images, the data should be free of systematic biases. Besides precise fabrication of hardware, software-based calibration solutions are commonly used for modelling the distortions. In this primary research study, a robust photogrammetric bundle adjustment was used to model the projective geometry of two fluoroscopic X-ray imaging systems. However, instead of relying on an expert photogrammetrist’s knowledge and judgement to decide on a parametric model for describing the systematic errors, a self-tuning data-driven approach is used to model the complex non-linear distortion profile of the sensors. Quality control from the experiment showed that 0.06<span class="thinspace"></span>mm to 0.09<span class="thinspace"></span>mm 3D reconstruction accuracy was achievable post-calibration using merely 15 X-ray images. As part of the bundle adjustment, the location of the virtual fluoroscopic system relative to the target field can also be spatially resected with an RMSE between 3.10<span class="thinspace"></span>mm and 3.31<span class="thinspace"></span>mm.</p>
50
Buongiorno Nardelli, Bruno. "A multi-year time series of observation-based 3D horizontal and vertical quasi-geostrophic global ocean currents." Earth System Science Data 12, no. 3 (August 3, 2020): 1711–23. http://dx.doi.org/10.5194/essd-12-1711-2020.
Full textAbstract:
Abstract. Estimates of 3D ocean circulation are needed to improve our understanding of ocean dynamics and to assess their impact on marine ecosystems and Earth climate. Here we present the OMEGA3D product, an observation-based time series of (quasi-)global 3D ocean currents covering the 1993–2018 period, developed by the Italian Consiglio Nazionale delle Ricerche within the European Copernicus Marine Environment Monitoring Service (CMEMS). This dataset was obtained by applying a diabatic quasi-geostrophic (QG) diagnostic model to the data-driven CMEMS-ARMOR3D weekly reconstruction of temperature and salinity as well as ERA Interim fluxes. Outside the equatorial band, vertical velocities were retrieved in the upper 1500 m at 1∕4∘ nominal resolution and successively used to compute the horizontal ageostrophic components. Root mean square differences between OMEGA3D total horizontal velocities and totally independent drifter observations at two different depths (15 and 1000 m) decrease with respect to corresponding estimates obtained from zero-order geostrophic balance, meaning that estimated vertical velocities can also be deemed reliable. OMEGA3D horizontal velocities are also closer to drifter observations than velocities provided by a set of reanalyses spanning a comparable time period but based on data assimilation in ocean general circulation numerical models. The full OMEGA3D product (released on 31 March 2020) is available upon free registration at https://doi.org/10.25423/cmcc/multiobs_glo_phy_w_rep_015_007 (Buongiorno Nardelli, 2020a). The reduced subset used here for validation and review purposes is openly available at https://doi.org/10.5281/zenodo.3696885 (Buongiorno Nardelli, 2020b).