检索结果-内蒙古大学图书馆

A single 2D pose with context is worth hundreds for 3D human pose estimation 23

学校读者我要写书评

暂无评论

A single 2D pose with context is worth hundreds for 3D human...

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Qitao Zhao Ce Zheng Mengyuan Liu Chen Chen Robotics Institute Carnegie Mellon University Center for Research in Computer Vision University of Central Florida Key Laboratory of Machine Perception Peking University Shenzhen Graduate School

The dominant paradigm in 3D human pose estimation that lifts a 2D pose sequence to 3D heavily relies on long-term temporal clues (i.e., using a daunting number of video frames) for improved accuracy, which incurs performance saturation, intractable computation and the non-causal problem. This can be attributed to their inherent inability to perceive spatial context as plain 2D joint coordinates carry no visual cues. To address this issue, we propose a straightforward yet powerful solution: leveraging the readily available intermediate visual representations produced by off-the-shelf (pre-trained) 2D pose detectors - no finetuning on the 3D task is even needed. The key observation is that, while the pose detector learns to localize 2D joints, such representations (e.g., feature maps) implicitly encode the joint-centric spatial context thanks to the regional operations in backbone networks. We design a simple baseline named Context-Aware PoseFormer to showcase its effectiveness. Without access to any temporal information, the proposed method significantly outperforms its context-agnostic counterpart, PoseFormer [74], and other state-of-the-art methods using up to hundreds of video frames regarding both speed and precision. Project page: ***/ContextAware-PoseFormer

关键词：

Omnidirectional Depth Computation from a Single Image

学校读者我要写书评

暂无评论

Omnidirectional Depth Computation from a Single Image

IEEE International Conference on robotics and Automation (ICRA)

作者： R. Orghidan E.M. Mouaddib J. Salvi Institute of Informatics and Applications Computer Vision and Robotics Group University of Girona Catalonia Spain Centre de Robotique Université de Picardie Jules-Verne Amiens France

Omnidirectional cameras offer a much wider field of view than the perspective ones and alleviate the problems due to occlusions. However, both types of cameras suffer from the lack of depth perception. A practical method for obtaining depth in computer vision is to project a known structured light pattern on the scene avoiding the problems and costs involved by stereo vision. This paper is focused on the idea of combining omnidirectional vision and structured light with the aim to provide 3D information about the scene. The resulting sensor is formed by a single catadioptric camera and an omnidirectional light projector. It is also discussed how this sensor can be used in robot navigation applications.

关键词： Cameras Robot vision systems Layout Navigation Mirrors Image reconstruction Orbital robotics computer vision Optical sensors Lenses

Analytical Estimation of Interaction Force and its Application Point for Collaborative Robots

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2022年第10期55卷 2451-2456页

作者： Dmitry Popov Alexandr Klimchik Anatol Pashkevich Institute of Robotics and Computer Vision Innopolis University Innopolis Russia IMT-Atlantique Nantes Nantes France Laboratoire des Sciences du Numérique de Nantes (LS2N) Nantes France

The paper deals with parameters estimation in the human-robot collaboration scenario. It presents an analytical algorithm for computing of the interaction force and its application point using measurement data obtained from the internal joint torque sensors only. The proposed algorithm is based on a specific extension of static equilibrium equations allowing to find the desired interaction force and action line. Further, this general solution is combined with geometric constraints describing manipulator surfaces and corresponding friction cones. Particular attention is paid to singular cases arising when the interaction force action line intersects one or several joint sensor axes. The developed technique was carefully evaluated via the simulation study.

关键词： robotics in manufacturing Human-Automation Integration Collaborative robots Human-robot interaction collaboration cooperation

Composition loss for counting, density map estimation and localization in dense crowds

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Idrees, Haroon Tayyab, Muhmmad Athrey, Kishan Zhang, Dong Al-Maadeed, Somaya Rajpoot, Nasir Shah, Mubarak Robotics Institute Carnegie Mellon University NVIDIA Inc Computer Science Department Faculty of Engineering Qatar University Department of Computer Science University of Warwick United Kingdom Center for Research in Computer Vision University of Central Florida

With multiple crowd gatherings of millions of people every year in events ranging from pilgrimages to protests, concerts to marathons, and festivals to funerals;visual crowd analysis is emerging as a new frontier in computer vision. In particular, counting in highly dense crowds is a challenging problem with far-reaching applicability in crowd safety and management, as well as gauging political significance of protests and demonstrations. In this paper, we propose a novel approach that simultaneously solves the problems of counting, density map estimation and localization of people in a given dense crowd image. Our formulation is based on an important observation that the three problems are inherently related to each other making the loss function for optimizing a deep CNN decomposable. Since localization requires high-quality images and annotations, we introduce UCF-QNRF dataset that overcomes the shortcomings of previous datasets, and contains 1.25 million humans manually marked with dot annotations. Finally, we present evaluation measures and comparison with recent deep CNN networks, including those developed specifically for crowd counting. Our approach significantly outperforms state-of-the-art on the new dataset, which is the most challenging dataset with the largest number of crowd annotations in the most diverse set of scenes. Copyright © 2018, The Authors. All rights reserved.

关键词： Machine learning

Mobile robot localization using panoramic vision and combinations of feature region detectors

学校读者我要写书评

暂无评论

Mobile robot localization using panoramic vision and combina...

IEEE International Conference on robotics and Automation (ICRA)

作者： Arnau Ramisa Adriana Tapus Ramon Lopez de Mantaras Ricardo Toledo Artificial Intelligence Research Institute Spain Robotics Research Lab Interaction Lab Department of Computer Science University of Southern California Los Angeles USA UAB Campus Computer Vision Center Spain

This paper presents a vision-based approach for mobile robot localization. The environmental model is topological. The new approach uses a constellation of different types of affine covariant regions to characterize a place. This type of representation permits a reliable and distinctive environment modeling. The performance of the proposed approach is evaluated using a database of panoramic images from different rooms. Additionally, we compare different combinations of complementary feature region detectors to find the one that achieves the best results. Our experimental results show promising results for this new localization method. Additionally, similarly to what happens with single detectors, different combinations exhibit different strengths and weaknesses depending on the situation, suggesting that a context-aware method to combine the different detectors would improve the localization results.

关键词： Mobile robots computer vision Detectors Robot kinematics Robot localization Feature extraction Fingerprint recognition robotics and automation USA Councils Image databases

Self-supervised visual representations for cross-modal retrieval

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Patel, Yash Gomez, Lluis Rusiñol, Marçal Karatzas, Dimosthenis Jawahar, C.V. Robotics Institute Carnegie Mellon University PA United States Computer Vision Center Universitat Autonoma de Barcelona Spain CVIT KCIS IIIT Hyderabad India

Cross-modal retrieval methods have been significantly improved in last years with the use of deep neural networks and large-scale annotated datasets such as ImageNet and Places. However, collecting and annotating such datasets requires a tremendous amount of human effort and, besides, their annotations are usually limited to discrete sets of popular visual classes that may not be representative of the richer semantics found on large-scale cross-modal retrieval datasets. In this paper, we present a self-supervised cross-modal retrieval framework that leverages as training data the correlations between images and text on the entire set of Wikipedia articles. Our method consists in training a CNN to predict: (1) the semantic context of the article in which an image is more probable to appear as an illustration (global context), and (2) the semantic context of its caption (local context). Our experiments demonstrate that the proposed method is not only capable of learning discriminative visual representations for solving vision tasks like image classification and object detection, but that the learned representations are better for cross-modal retrieval when compared to supervised pre-training of the network on the ImageNet dataset. Copyright © 2019, The Authors. All rights reserved.

关键词： Large dataset

GraspGPT: Leveraging Semantic Knowledge from a Large Language Model for Task-Oriented Grasping

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tang, Chao Huang, Dehao Ge, Wenqi Liu, Weiyu Zhang, Hong Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China Institute for Robotics and Intelligent Machines Georgia Institute of Technology Atlanta United States

Task-oriented grasping (TOG) refers to the problem of predicting grasps on an object that enable subsequent manipulation tasks. To model the complex relationships between objects, tasks, and grasps, existing methods incorporate semantic knowledge as priors into TOG pipelines. However, the existing semantic knowledge is typically constructed based on closed-world concept sets, restraining the generalization to novel concepts out of the pre-defined sets. To address this issue, we propose GraspGPT, a large language model (LLM) based TOG framework that leverages the open-end semantic knowledge from an LLM to achieve zero-shot generalization to novel concepts. We conduct experiments on Language Augmented TaskGrasp (LA-TaskGrasp) dataset and demonstrate that GraspGPT outperforms existing TOG methods on different held-out settings when generalizing to novel concepts out of the training set. The effectiveness of GraspGPT is further validated in real-robot experiments. Our code, data, appendix, and video are publicly available at https://***/view/graspgpt. Copyright © 2023, The Authors. All rights reserved.

关键词： Zero-shot learning

Microcalcification evaluation in computer assisted diagnosis for digital mammography

学校读者我要写书评

暂无评论

Microcalcification evaluation in computer assisted diagnosis...

IEE Colloquium on Medical Applications of Signal Processing (Ref. No. 1999/107)

作者： J. Marti J. Batlle X. Cufi J. Espanol Computer Vision and Robotics Group-Institute of Iniormatics and ApplicationsL University of Girona Girona Spain Department of Oncology University Hospital Dr. Josep Trueta Girona Spain

FoundationGrasp: Generalizable Task-Oriented Grasping with Foundation Models

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tang, Chao Huang, Dehao Dong, Wenlong Xu, Ruinian Zhang, Hong Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China Institute for Robotics and Intelligent Machines Georgia Institute of Technology Atlanta United States

Task-oriented grasping (TOG), which refers to synthesizing grasps on an object that are configurationally compatible with the downstream manipulation task, is the first milestone towards tool manipulation. Analogous to the activation of two brain regions responsible for semantic and geometric reasoning during cognitive processes, modeling the intricate relationship between objects, tasks, and grasps necessitates rich semantic and geometric prior knowledge about these elements. Existing methods typically restrict the prior knowledge to a closed-set scope, limiting their generalization to novel objects and tasks out of the training set. To address such a limitation, we propose FoundationGrasp, a foundation model-based TOG framework that leverages the open-ended knowledge from foundation models to learn generalizable TOG skills. Extensive experiments are conducted on the contributed Language and vision Augmented TaskGrasp (LaViA-TaskGrasp) dataset, demonstrating the superiority of FoundationGrasp over existing methods when generalizing to novel object instances, object classes, and tasks out of the training set. Furthermore, the effectiveness of FoundationGrasp is validated in real-robot grasping and manipulation experiments on a 7-DoF robotic arm. Our code, data, appendix, and video are publicly available at https://***/view/foundationgrasp. Copyright © 2024, The Authors. All rights reserved.

关键词： Robotic arms