Academic literature on the topic '3D model-Driven reconstruction'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources 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.
Journal articles on the topic "3D model-Driven reconstruction"
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.
Dissertations / Theses on the topic "3D model-Driven reconstruction"
1
Jin, Nan. "ModSETS : a model-driven stereo eye tracking system : application in the medical field." Electronic Thesis or Diss., Aix-Marseille, 2020. http://www.theses.fr/2020AIXM0339.
Full textAbstract:
La plupart des systèmes de suivi de l’œil existants ne fournissent que des analyses précises et en temps réel des mouvements oculaires 2D (horizontaux et verticaux) dans des conditions de laboratoire. Ils sont en général insuffisants pour les applications du domaine médical, parce que leur robustesse est souvent mise à l'épreuve dans la pratique et la mesure du mouvement torsionnel de l’œil est ignorée la plupart du temps. Cela augmente la difficulté d'interprétation des données collectées et peut donc affecter la qualité du diagnostic médical. Un système de suivi de l’œil en stéréophotogrammétrie piloté par modèle (ModSETS) est proposé dans cette thèse de doctorat, pour offrir une analyse précise, robuste et en temps réel des mouvements oculaires 3D (horizontaux, verticaux et torsionnels) pour les applications médicales. La performance de ModSETS dans le suivi des mouvements oculaires 2D est démontrée par un ⟪gaze test⟫. Il a montré une bonne précision (i.e., d'environ 1 °) dans l'estimation du regard qui est conforme aux exigences de nombreuses applications médicales. La robustesse de ModSETS dans des conditions normales d’utilisation est également confirmée, traduit par un taux de réussite élevé dans la segmentation de la pupille (i.e., 91,4%). Certains résultats encourageants ont été obtenus dans la mesure des mouvements torsionnels de l’œil, même s'il est difficile d’effectuer une évaluation quantitative avec le matériel actuel. Le principe d’un tel système de suivi de l’œil en stéréophotogrammétrie piloté par modèle (ModSETS) est validé. Il montre un grand potentiel dans le suivi des mouvements oculaires 3D pour les applications du domaine médicalMost current eye tracking systems only provide accurate and real-time analysis of 2D (horizontal and vertical) eye movement in laboratory conditions. It is usually insufficient for medical applications, because their robustness is often challenged in practice and the measurement of eye torsion is almost ignored. This increases the difficulty of data interpretation and may thus affect the quality of medical diagnosis. A Model-driven Stereo Eye Tracking System (ModSETS) is proposed in this Ph.D. thesis, to provide accurate, robust, and real-time analysis of 3D (horizontal, vertical and torsional) eye movement for medical applications. The performance of ModSETS in 2D eye movement tracking is proved through a gaze test. It showed a good accuracy (i.e., of about 1°) in gaze estimation that is compliant with the requirements of many medical applications. The robustness of ModSETS in practical conditions is also confirmed, which is reflected by a high success rate in pupil segmentation (i.e., 91.4%). Some encouraging results of eye torsion measurement were obtained, even though it is difficult to make a quantitative assessment with current hardware. Therefore, the principle of ModSETS (Model-driven Stereo Eye Tracking System) is validated and shows great potential in 3D eye movement tracking for medical applications
2
Partovi, Tahmineh. "3D Building Model Reconstruction from Very High Resolution Satellite Stereo Imagery." Doctoral thesis, 2019. https://repositorium.ub.uni-osnabrueck.de/handle/urn:nbn:de:gbv:700-201910022067.
Full textAbstract:
Automatic three-dimensional (3D) building model reconstruction using remote sensing data is crucial in applications which require large-scale and frequent building model updates, such as disaster monitoring and urban management, to avoid huge manual efforts and costs. Recent advances in the availability of very high-resolution satellite data together with efficient data acquisition and large area coverage have led to an upward trend in their applications for 3D building model reconstructions. In this dissertation, a novel multistage hybrid automatic 3D building model reconstruction approach is proposed which reconstructs building models in level of details 2 (LOD2) based on digital surface model (DSM) data generated from the very high-resolution stereo imagery of the WorldView-2 satellite. This approach uses DSM data in combination with orthorectified panchromatic (PAN) and pan-sharpened data of multispectral satellite imagery to overcome the drawbacks of DSM data, such as blurred building boundaries, rough building shapes unwanted failures in the roof geometries. In the first stage, the rough building boundaries in the DSM-based building masks are refined by classifying the geometrical features of the corresponding PAN images. The refined boundaries are then simplified in the second stage through a parameterization procedure which represents the boundaries by a set of line segments. The main orientations of buildings are then determined, and the line segments are regularized accordingly. The regularized line segments are then connected to each other based on a rule-based method to form polygonal building boundaries. In the third stage, a novel technique is proposed to decompose the building polygons into a number of rectangles under the assumption that buildings are usually composed of rectangular structures. In the fourth stage, a roof model library is defined, which includes flat, gable, half-hip, hip, pyramid and mansard roofs. These primitive roof types are then assigned to the rectangles based on a deep learning-based classification method. In the fifth stage, a novel approach is developed to reconstruct watertight parameterized 3D building models based on the results of the previous stages and normalized DSM (nDSM) of satellite imagery. In the final stage, a novel approach is proposed to optimize building parameters based on an exhaustive search, so that the two-dimensional (2D) distance between the 3D building models and the building boundaries (obtained from building masks and PAN image) as well as the 3D normal distance between the 3D building models and the 3D point clouds (obtained from nDSM) are minimized. Different parts of the building blocks are then merged through a newly proposed intersection and merging process. All corresponding experiments were conducted on four areas of the city of Munich including 208 buildings and the results were evaluated qualitatively and quantitatively. According to the results, the proposed approach could accurately reconstruct 3D models of buildings, even the complex ones with several inner yards and multiple orientations. Furthermore, the proposed approach provided a high level of automation by the limited number of primitive roof model types required and by performing automatic parameter initialization. In addition, the proposed boundary refinement method improved the DSM-based building masks specified by 8 % in area accuracy. Furthermore, the ridge line directions and roof types were detected accurately for most of the buildings. The combination of the first three stages improved the accuracy of the building boundaries by 70 % in comparison to using line segments extracted from building masks without refinement. Moreover, the proposed optimization approach could achieve in most cases the best combinations of 2D and 3D geometrical parameters of roof models. Finally, the intersection and merging process could successfully merge different parts of the complex building models.
Book chapters on the topic "3D model-Driven reconstruction"
1
Berretti, Stefano, Alberto Del Bimbo, and Pietro Pala. "3D Face Reconstruction from Two Orthogonal Images for Face Recognition Applications." In Multimedia Storage and Retrieval Innovations for Digital Library Systems, 223–39. IGI Global, 2012. http://dx.doi.org/10.4018/978-1-4666-0900-6.ch012.
Full textAbstract:
In this paper, an original hybrid 2D-3D face recognition approach is proposed using two orthogonal face images, frontal and side views of the face, to reconstruct the complete 3D geometry of the face. This is obtained using a model based solution, in which a 3D template face model is morphed according to the correspondence of a limited set of control points identified on the frontal and side images in addition to the model. Control points identification is driven by an Active Shape Model applied to the frontal image, whereas subsequent manual assistance is required for control points localization on the side view. The reconstructed 3D model is finally matched, using the iso-geodesic regions approach against a gallery of 3D face scans for the purpose of face recognition. Preliminary experimental results are provided on a small database showing the viability of the approach.
Conference papers on the topic "3D model-Driven reconstruction"
1
Hanajik, Milan. "Efficient data-driven algorithm for the model-based 3D scene reconstruction from perspective images." In Spatial Information from Digital Photogrammetry and Computer Vision: ISPRS Commission III Symposium, edited by Heinrich Ebner, Christian Heipke, and Konrad Eder. SPIE, 1994. http://dx.doi.org/10.1117/12.182824.
Full text
2
Partovi, Tahmineh, Thomas Kraus, Hossein Arefi, Mohammad Omidalizarandi, and Peter Reinartz. "Model-driven 3D building reconstruction based on integeration of DSM and spectral information of satellite images." In IGARSS 2014 - 2014 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2014. http://dx.doi.org/10.1109/igarss.2014.6947150.
Full text
3
Xu, Baixin, Jiarui Zhang, Kwan-Yee Lin, Chen Qian, and Ying He. "Deformable Model-Driven Neural Rendering for High-Fidelity 3D Reconstruction of Human Heads Under Low-View Settings." In 2023 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, 2023. http://dx.doi.org/10.1109/iccv51070.2023.01643.
Full text
4
Hu, Yazhe, and Tomonari Furukawa. "A Self-Supervised Learning Technique for Road Defects Detection Based on Monocular Three-Dimensional Reconstruction." In ASME 2019 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. American Society of Mechanical Engineers, 2019. http://dx.doi.org/10.1115/detc2019-98135.
Full textAbstract:
Abstract This paper presents a self-supervised learning technique for road surface defects detection using a monocular camera. The uniqueness of the proposed technique relies on its self-supervised learning structure which is achieved by combining physics-driven three-dimensional (3D) reconstruction with data-driven Convolutional Neural Network (CNN). Only images from one camera are needed as the inputs to the model without human labeling. The 3D point cloud are reconstructed from input images based on a near-planar road 3D reconstruction process to self-supervise the learning process. During testing, the network receives images and predicts the images as defect or non-defect. A refined class prediction is produced by combining the 3D road surface data with the network output when the belief of original network prediction is not strong enough to conclude the classification. Experiments are conducted on real road surface images to find the optimal parameters for this model. The testing results demonstrate the robustness and effectiveness of the proposed self-supervised road surface defects detection technique.
5
"ONTOLOGY-DRIVEN 3D RECONSTRUCTION OF ARCHITECTURAL OBJECTS." In 3D Model Aquisition and Representation. SciTePress - Science and and Technology Publications, 2007. http://dx.doi.org/10.5220/0002047300470054.
Full text
6
Reck, Michaela, Marc Hilbert, René Hilhorst, and Thomas Indinger. "Comparison of Deep Learning Architectures for Dimensionality Reduction of 3D Flow Fields of a Racing Car." In WCX SAE World Congress Experience. 400 Commonwealth Drive, Warrendale, PA, United States: SAE International, 2023. http://dx.doi.org/10.4271/2023-01-0862.
Full textAbstract:
<div class="section abstract"><div class="htmlview paragraph">In motorsports, aerodynamic development processes target to achieve gains in performance. This requires a comprehensive understanding of the prevailing aerodynamics and the capability of analysing large quantities of numerical data. However, manual analysis of a significant amount of Computational Fluid Dynamics (CFD) data is time consuming and complex. The motivation is to optimize the aerodynamic analysis workflow with the use of deep learning architectures. In this research, variants of 3D deep learning models (3D-DL) such as Convolutional Autoencoder (CAE) and U-Net frameworks are applied to flow fields obtained from Reynolds Averaged Navier Stokes (RANS) simulations to transform the high-dimensional CFD domain into a low-dimensional embedding. Consequently, model order reduction enables the identification of inherent flow structures represented by the latent space of the models. The resulting data from the 3D-DL study are compared to a traditional dimensionality reduction method, namely Proper Orthogonal Decomposition (POD). Flow field features are examined by using methods of local feature importance, aiming for awareness of predominant fluidic phenomena. We show that our data-driven models capture aerodynamically relevant zones around the racing car. 3D-DL architectures can represent complex nonlinear dependencies in the flow domain. The U-Net network demonstrates an <i>R</i><sup>2</sup> reconstruction accuracy of 99.94%, outperforming the results achieved from linear POD with an <i>R</i><sup>2</sup> of 99.57%. Efficiently handling numerous CFD simulations leads to improved post-processing and an accelerated investigation procedure for future aerodynamic development. Finally, the discovered findings provide further knowledge for the serial development to increase efficiency, thereby extending, e.g., the range of electric vehicles.</div></div>
7
Amerinatanzi, Amirhesam, Narges Shayesteh Moghaddam, Hamdy Ibrahim, and Mohammad Elahinia. "Evaluating a NiTi Implant Under Realistic Loads: A Simulation Study." In ASME 2016 Conference on Smart Materials, Adaptive Structures and Intelligent Systems. American Society of Mechanical Engineers, 2016. http://dx.doi.org/10.1115/smasis2016-9287.
Full textAbstract:
Additive manufacturing (i.e. 3D printing) has only recently be shown as a well-established technology to create complex shapes and porous structures from different biocompatible metal powder such as titanium, nitinol, and stainless steel alloys. This allows for manufacturing bone fixation hardware with patient-specific geometry and properties (e.g. density and mechanical properties) directly from CAD files. Superelastic NiTi is one of the most biocompatible alloys with high shock absorption and biomimetic hysteresis behavior. More importantly, NiTi has the lowest stiffness (36–68 GPa) among all biocompatible alloys [1]. The stiffness of NiTi can further be reduced, to the level of the cortical bone (10–31.2 GPa), by introducing engineered porosity using additive manufacturing [2–4]. The low level of fixation stiffness allows for bone to receive a stress profile close to that of healthy bone during the healing period. This enhances the bone remodeling process (Wolf’s Law) which primarily driven by the pattern of stress. Also, this match in the stiffness of bone and fixation mitigates the problem of stress shielding and detrimental stress concentrations. Stress shielding is a known problem for the currently in-use Ti-6Al-4V fixation hardware. The high stiffness of Ti-6Al-4V (112 GPa) compared to bone results in the absence of mechanical loading on the adjacent bone that causes loss of bone mass and density and subsequently bone/implant failure. We have proposed additively manufactured porous NiTi fixation hardware with a patient-specific stiffness to be used for the mandibular reconstructive surgery (MRS). In MRS, the use of metallic fixation hardware and double barrel fibula graft is the standard methodology to restore the mandible functionality and aesthetic. A validated finite element model was developed from a dried cadaveric mandible using CT scan data. The model simulated a patient’s mandible after mandibular reconstructive surgery to compare the performance of the conventional Ti-6Al-4V fixation hardware with the proposed one (porous superelastic NiTi fixation plates). An optimized level of porosity was determined to match the NiTi equivalent stiffness to that of a resected bone, then it was imposed to the simulated fixation plates. Moreover, the material property of superelastic NiTi was simulated by using a validated customized code. The code was calibrated by using DSC analysis and mechanical tests on several prepared bulk samples of Ni-rich NiTi. The model was run under common activities such as chewing by considering different levels of the applied fastening torques on screws. The results show a higher level of stress distribution on mandible cortical bone in the case of using NiTi fixation plates. Based on wolf’s law it can lead to a lower level of stress shielding on the grafted bone and over time bone can remodel itself. Moreover, the results suggest an optimum fastening torque for fastening the screws for the superelastic fixations causes more normal distribution of stress on the bone similar to that for the healthy mandible. Finally, we successfully fabricated the stiffness-matched porous NiTi fixation plates using selective laser melting technique, and they were mounted on the dried cadaveric mandible used to create the finite element model.