Filters








34 Hits in 5.8 sec

VoxNet: A 3D Convolutional Neural Network for real-time object recognition

Daniel Maturana, Sebastian Scherer
2015 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
Range sensors such as LiDAR and RGBD cameras are increasingly found in modern robotic systems, providing a rich source of 3D information that can aid in this task.  ...  We evaluate our approach on publicly available benchmarks using LiDAR, RGBD, and CAD data. VoxNet achieves accuracy beyond the state of the art while labeling hundreds of instances per second.  ...  The Tesla K40 used for this research was donated by the NVIDIA Corporation. We thank the reviewers for their feedback.  ... 
doi:10.1109/iros.2015.7353481 dblp:conf/iros/MaturanaS15 fatcat:ychckypd2bhtpfttlunn27jqvu

Semantically Derived Geometric Constraints for MVS Reconstruction of Textureless Areas

Elisavet Konstantina Stathopoulou, Roberto Battisti, Dan Cernea, Fabio Remondino, Andreas Georgopoulos
2021 Remote Sensing  
Conventional multi-view stereo (MVS) approaches based on photo-consistency measures are generally robust, yet often fail in calculating valid depth pixel estimates in low textured areas of the scene.  ...  In this study, a novel approach is proposed to tackle this challenge by leveraging semantic priors into a PatchMatch-based MVS in order to increase confidence and support depth and normal map estimation  ...  Acknowledgments: The authors would like to thank Andrea Romanoni and Qingshan Xu for running our custom datasets on their software TAPA-MVS and ACMM/ACMP respectively.  ... 
doi:10.3390/rs13061053 fatcat:bz6w3femwbgedma2fzpj54346a

Pedestrian Models for Autonomous Driving Part I: Low-Level Models, From Sensing to Tracking

Fanta Camara, Nicola Bellotto, Serhan Cosar, Dimitris Nathanael, Matthias Althoff, Jingyuan Wu, Johannes Ruenz, Andre Dietrich, Charles Fox
2020 IEEE transactions on intelligent transportation systems (Print)  
Technologies at these levels are found to be mature and available as foundations for use in high-level systems, such as behaviour modelling, prediction and interaction control.  ...  Planning AV actions in the presence of pedestrians thus requires modelling of their probable future behaviour as well as detecting and tracking them.  ...  MHT is generally considered to be too slow and memoryexpensive for multi-target tracking methods as pruning and priming have to be applied in order to keep the size of the tree manageable [121] .  ... 
doi:10.1109/tits.2020.3006768 fatcat:awa5dgk4rbazteetyyqrndbgxq

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
Departments and other items may also be covered if they have been judged to have archival value. The Author Index contains the primary entry for each item, listed under the first author's name.  ...  The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  ., +, TIP 2021 121-133 Spatial Information Guided Convolution for Real-Time RGBD Semantic Segmentation.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu

Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art [article]

Joel Janai, Fatma Güney, Aseem Behl, Andreas Geiger
2021 arXiv   pre-print
, scene understanding, and end-to-end learning for autonomous driving.  ...  While several survey papers on particular sub-problems have appeared, no comprehensive survey on problems, datasets, and methods in computer vision for autonomous vehicles has been published.  ...  The best performing reconstruction method, ACMM [736] , proposes an adaptive checkerboard sampling scheme and a multi-hypothesis joint view selection approach (ACMH) for improved propagation of hypotheses  ... 
arXiv:1704.05519v3 fatcat:xiintiarqjbfldheeg2hsydyra

Pedestrian Models for Autonomous Driving Part I: low level models, from sensing to tracking [article]

Fanta Camara, Nicola Bellotto, Serhan Cosar, Dimitris Nathanael, Matthias Althoff, Jingyuan Wu, Johannes Ruenz, André Dietrich, Charles W. Fox
2020 arXiv   pre-print
Technologies at these levels are found to be mature and available as foundations for use in higher level systems such as behaviour modelling, prediction and interaction control.  ...  This self-contained Part I covers the lower levels of this stack, from sensing, through detection and recognition, up to tracking of pedestrians.  ...  MHT is generally considered to be too slow and memory expensive for multi-tracking methods as pruning and priming have to be applied in order to keep the size of the tree manageable [117] .  ... 
arXiv:2002.11669v1 fatcat:fgg5j5jdwrbujjgtj2uhgrx2am

Data-Driven Shape Analysis and Processing [article]

Kai Xu, Vladimir G. Kim, Qixing Huang, Evangelos Kalogerakis
2015 arXiv   pre-print
We provide an overview of the main concepts and components of these techniques, and discuss their application to shape classification, segmentation, matching, reconstruction, modeling and exploration,  ...  as well as scene analysis and synthesis, through reviewing the literature and relating the existing works with both qualitative and numerical comparisons.  ...  for object and scene understanding [ZSSS13, SLH12] , and information transfer between multi-modal data [WGW * 13, SHM * 14].  ... 
arXiv:1502.06686v1 fatcat:upajios4y5a6dgf2zw7faqai4a

Automatic visual detection of human behavior: A review from 2000 to 2014

Palwasha Afsar, Paulo Cortez, Henrique Santos
2015 Expert systems with applications  
The detection techniques were divided into four categories (initialization, tracking, pose estimation and recognition). The list of datasets includes eight examples (e.g., Hollywood action).  ...  Our analysis provides a road map to guide future research for designing automatic visual human behavior detection systems.  ...  Acknowledgments This work is funded by the Portuguese Foundation for Science and Technology (FCT -Fundação para a Ciência e a Tecnologia) under research grant SFRH/BD/84939/2012.  ... 
doi:10.1016/j.eswa.2015.05.023 fatcat:3f7nze4slnhavkhin45jfe5bwi

Vision-based Robotic Grasp Detection From Object Localization, Object Pose Estimation To Grasp Estimation: A Review [article]

Guoguang Du, Kai Wang, Shiguo Lian, Kaiyong Zhao
2020 arXiv   pre-print
In detail, object localization task contains object localization without classification, object detection and object instance segmentation.  ...  Some object pose estimation methods need not object localization, and they conduct object localization and object pose estimation jointly.  ...  ., 2017] trained a CNN-based model which fuses different low level saliency cues into hierarchical features for detecting salient objects in RGBD images. Chen et al.  ... 
arXiv:1905.06658v2 fatcat:6u3k2ltwifaanjpp2nkayyj2f4

Challenges in Multi-modal Gesture Recognition [chapter]

Sergio Escalera, Vassilis Athitsos, Isabelle Guyon
2017 Gesture Recognition  
We also overview recent state of the art works on gesture recognition based on a proposed taxonomy for gesture recognition, discussing challenges and future lines of research.  ...  Notably, we organized a series of challenges and made available several datasets we recorded for that purpose, including tens of thousands of videos, which are available to conduct further research.  ...  Our sponsors include Microsoft and Texas Instrument who donated prizes and provided technical support. The challenges were hosted by Kaggle.com and Coralab.org who are gratefully acknowledged.  ... 
doi:10.1007/978-3-319-57021-1_1 fatcat:vfeijghqtvffllogw2tium3pwa

Data-driven shape analysis and processing

Kai Xu, Vladimir G. Kim, Qixing Huang, Niloy Mitra, Evangelos Kalogerakis
2016 SIGGRAPH ASIA 2016 Courses on - SA '16  
, etc.), offer great opportunities for developing data-driven approaches for 3D shape analysis and processing.  ...  Such examples include heuristicsbased shape segmentation [Shamir 2008] and procedural shape modeling [Müller et al. 2006 ].  ...  Acknowledgements We thank Zimo Li for proofreading this survey and the anonymous reviewers for helpful suggestions. Kalogerakis gratefully acknowledges support from NSF (CHS-1422441).  ... 
doi:10.1145/2988458.2988473 dblp:conf/siggraph/0004KHMK16 fatcat:tefja76ijnclzmpux2iaj45zgu

A Comprehensive Review on 3D Object Detection and 6D Pose Estimation with Deep Learning

Sabera Hoque, MD. Yasir Arafat, Shuxiang Xu, Ananda Maiti, Yuchen Wei
2021 IEEE Access  
A further up to date survey for 3D object understanding, classification, identification, defining size and shape, and 230 tracking with 3D visualization and segmentation is present by Guo et al.  ...  [172] , where they reviewed 194 documents and worked on on-road-based vehicle detection and tracking systems for collision avoidance systems.  ... 
doi:10.1109/access.2021.3114399 fatcat:kvdwsslqxff3lkh27tsdsciqma

ARtwin: Map pivot format specification

Nam Duong Duong, Jérôme Royan, Michal Polic, Nischita Sudharsan
2020 Zenodo  
This project has received funding from the European Union's Horizon 2020 Framework Programme for research and Innovation under Grant Agreement no 856994.  ...  [120] makes use of both points and line segments (segment feature being based on the features of a points sampling) to achieve more robust relocalization in poorly textured areas and/or in case of motion  ...  The factory personnel can provide sample 3D data for point clouds and also 3D files.  ... 
doi:10.5281/zenodo.4381408 fatcat:pn2ioshymfcrrkbuhxg72kr7zy

Multiple-Robot Simultaneous Localization and Mapping: A Review

Sajad Saeedi, Michael Trentini, Mae Seto, Howard Li
2015 Journal of Field Robotics  
Various issues and problems in multiple-robot SLAM are introduced, current solutions for these problems are reviewed, and their advantages and disadvantages are discussed.  ...  Various SLAM algorithms can be categorized based on the algorithm used for map representation and data processing.  ...  Acknowledgments This research is supported by Natural Sciences and Engineering Research Council of Canada (NSERC) and Canada Foundation for Innovation (CFI).  ... 
doi:10.1002/rob.21620 fatcat:d7aboins2fdpvlz4eou6ra4lx4

Recovering 3D Human Mesh from Monocular Images: A Survey [article]

Yating Tian, Hongwen Zhang, Yebin Liu, Limin Wang
2022 arXiv   pre-print
Meanwhile, continuous efforts are devoted to improving the quality of 3D mesh labels for a wide range of datasets.  ...  We start with the introduction of body models and then elaborate recovery frameworks and training objectives by providing in-depth analyses of their strengths and weaknesses.  ...  [127] learn a multi-hypothesis neural network to generate multiple sets of parameters that are plausible estimates and consistent with the ambiguous views. Sengupta et al.  ... 
arXiv:2203.01923v2 fatcat:vb6xa5wdsrhdxd2ebvg54qq2m4
« Previous Showing results 1 — 15 out of 34 results