2D Human Pose Estimation: New Benchmark and State of the Art Analysis

被引:1796
作者
Andriluka, Mykhaylo [1 ,3 ]
Pishchulin, Leonid [1 ]
Gehler, Peter [2 ]
Schiele, Bernt [1 ]
机构
[1] Max Planck Inst Informat, Munich, Germany
[2] Max Planck Inst Intelligent Syst, Munich, Germany
[3] Stanford Univ, Stanford, CA 94305 USA
来源
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2014年
关键词
D O I
10.1109/CVPR.2014.471
中图分类号
TP18 [人工智能理论];
学科分类号
140502 [人工智能];
摘要
Human pose estimation has made significant progress during the last years. However current datasets are limited in their coverage of the overall pose estimation challenges. Still these serve as the common sources to evaluate, train and compare different models on. In this paper we introduce a novel benchmark "MPII Human Pose" 1 that makes a significant advance in terms of diversity and difficulty, a contribution that we feel is required for future developments in human body models. This comprehensive dataset was collected using an established taxonomy of over 800 human activities [1]. The collected images cover a wider variety of human activities than previous datasets including various recreational, occupational and householding activities, and capture people from a wider range of viewpoints. We provide a rich set of labels including positions of body joints, full 3D torso and head orientation, occlusion labels for joints and body parts, and activity labels. For each image we provide adjacent video frames to facilitate the use of motion information. Given these rich annotations we perform a detailed analysis of leading human pose estimation approaches and gaining insights for the success and failures of these methods.
引用
收藏
页码:3686 / 3693
页数:8
相关论文
共 23 条
[1]
Ainsworth B., 2011, MSSE 11
[2]
[Anonymous], 2010, P CVPR
[3]
[Anonymous], 2010, INT J COMPUTER VISIO
[4]
Dantone M., CVPR 13
[5]
Eichner M., BMVC 09
[6]
Eichner M., ECCV 10
[7]
Eichner M., PAMI'12
[8]
Everingham M., IJCV 10
[9]
Felzenszwalb P. F., IJCV 05
[10]
Ferrari V., CVPR'08