中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
Depth-Aware Multi-Person 3D Pose Estimation With Multi-Scale Waterfall Representations

文献类型：期刊论文

作者Shen, Tianyu2; Li, Deqi2; Wang, Fei-Yue1,3; Huang, Hua2
刊名IEEE TRANSACTIONS ON MULTIMEDIA
出版日期2023
卷号25页码:1439-1451
关键词Three-dimensional displays Pose estimation Feature extraction Location awareness Cameras Semantics Solid modeling Human depth perceiving multi-person 3d pose estimation multi-scale representation occlusion handling
ISSN号1520-9210
DOI10.1109/TMM.2022.3233251
通讯作者Huang, Hua(huahuang@bnu.edu.cn)
英文摘要Estimating absolute 3D poses of multiple people from monocular image is challenging due to the presence of occlusions and the scale variation among different persons. Among the existing methods, the top-down paradigms are highly dependent on human detection which is prone to the influence from inter-person occlusions, while the bottom-up paradigms suffer from the difficulties in keypoint feature extraction caused by scale variation and unreliable joint grouping caused by occlusions. To address these challenges, we introduce a novel multi-person 3D pose estimation framework, aided by multi-scale feature representations and human depth perceiving. Firstly, a waterfall-based architecture is incorporated for multi-scale feature representations to achieve a more accurate estimation of occluded joints with a better detection of human shapes. Then the global and local representations are fused for handling the effects of inter-person occlusion and scale variation in depth perceiving and keypoint feature extraction. Finally, with the guidance of the fused multi-scale representations, a depth-aware model is exploited for better 2D joint grouping and 3D pose recovering. Quantitative and qualitative evaluations on benchmark datasets of MuCo-3DHP and MuPoTS-3D prove the effectiveness of our proposed method. Furthermore, we produce an occluded MuPoTS-3D dataset and the experiments on it validate the superiority of our method for overcoming the occlusions.
WOS研究方向Computer Science ; Telecommunications
语种英语
WOS记录号WOS:000987415000004
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://ir.ia.ac.cn/handle/173211/53450]  
专题多模态人工智能系统全国重点实验室
通讯作者Huang, Hua
作者单位1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Beijing Normal Univ, Sch Artificial Intelligence, Beijing 100875, Peoples R China
3.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Shen, Tianyu,Li, Deqi,Wang, Fei-Yue,et al. Depth-Aware Multi-Person 3D Pose Estimation With Multi-Scale Waterfall Representations[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2023,25:1439-1451.
APA Shen, Tianyu,Li, Deqi,Wang, Fei-Yue,&Huang, Hua.(2023).Depth-Aware Multi-Person 3D Pose Estimation With Multi-Scale Waterfall Representations.IEEE TRANSACTIONS ON MULTIMEDIA,25,1439-1451.
MLA Shen, Tianyu,et al."Depth-Aware Multi-Person 3D Pose Estimation With Multi-Scale Waterfall Representations".IEEE TRANSACTIONS ON MULTIMEDIA 25(2023):1439-1451.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。