Deep Reinforcement Learning for Active Human Pose Estimation

被引:0
作者
Gartner, Erik [1 ]
Pirinen, Aleksis [1 ]
Sminchisescu, Cristian [1 ,2 ,3 ]
机构
[1] Lund Univ, Fac Engn, Dept Math, Lund, Sweden
[2] Romanian Acad, Inst Math, Bucharest, Romania
[3] Google Res, Cambridge, MA USA
来源
THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | 2020年 / 34卷
基金
欧盟地平线“2020”; 欧洲研究理事会;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Most 3d human pose estimation methods assume that input be it images of a scene collected from one or several viewpoints, or from a video - is given. Consequently, they focus on estimates leveraging prior knowledge and measurement by fusing information spatially and/or temporally, whenever available. In this paper we address the problem of an active observer with freedom to move and explore the scene spatially - in 'time-freeze' mode - and/or temporally, by selecting informative viewpoints that improve its estimation accuracy. Towards this end, we introduce Pose-DRL, a fully trainable deep reinforcement learning-based active pose estimation architecture which learns to select appropriate views, in space and time, to feed an underlying monocular pose estimator. We evaluate our model using single- and multi-target estimators with strong result in both settings. Our system further learns automatic stopping conditions in time and transition functions to the next temporal processing step in videos. In extensive experiments with the Panoptic multi-view setup, and for complex scenes containing multiple people, we show that our model learns to select viewpoints that yield significantly more accurate pose estimates compared to strong multi-view baselines.
引用
收藏
页码:10835 / 10844
页数:10
相关论文
共 36 条
[1]  
Ammirato Phil, 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA), P1378, DOI 10.1109/ICRA.2017.7989164
[2]  
[Anonymous], 2018, NIPS
[3]  
[Anonymous], 2018, CVPR, DOI DOI 10.1109/CVPR.2018.00945
[4]  
[Anonymous], 2016, CVPR, DOI DOI 10.1109/CVPR.2016.414
[5]  
[Anonymous], 2018, NEURIPS
[6]  
[Anonymous], 2017, PROC IEEE C COMPUT V
[7]   Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image [J].
Bogo, Federica ;
Kanazawa, Angjoo ;
Lassner, Christoph ;
Gehler, Peter ;
Romero, Javier ;
Black, Michael J. .
COMPUTER VISION - ECCV 2016, PT V, 2016, 9909 :561-578
[8]   Active Object Localization with Deep Reinforcement Learning [J].
Caicedo, Juan C. ;
Lazebnik, Svetlana .
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, :2488-2496
[9]  
Cheng A., 2018, Conference on Robot Learning, P422
[10]  
Das A., 2018, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, P2054