PEN: Pose-Embedding Network for Pedestrian Detection

doi:10.1109/TCSVT.2020.3000223

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 多媒体计算与图形学团队

	PEN: Pose-Embedding Network for Pedestrian Detection
	Jiao, Yifan 2; Yao, Hantao 3; Xu, Changsheng 1,3
刊名	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
	2021-03-01
卷号	31 期号:3 页码:1150-1162
关键词	Visualization Proposals Detectors Feature extraction Object detection Pose estimation Fuses Pedestrian detection pedestrian recognization network pose-embedding pose information
ISSN号	1051-8215
DOI	10.1109/TCSVT.2020.3000223
通讯作者	Xu, Changsheng(csxu@nlpr.ia.ac.cn)
英文摘要	In the past years, pedestrian detection has achieved significant progress via improving the visual description. However, the visual description is not robust to discover the occluded pedestrian, which is the bottleneck of the existing pedestrian methods. Targeting to overcome the shortcoming of visual description, we employ the human pose information, which is complementary to the visual description, to address the occlusion and false positive failure problems in pedestrian detection. The advantage of using human pose information is that the pose estimation model can localize the local part of the pedestrian once the pedestrian is occluded. By embedding the human pose information with the visual description, we propose a novel Pose-Embedding Network for pedestrian detection, which consists of two components: a Region Proposal Network, and a Pedestrian Recognization Network. The Region Proposal Network targets to generate lots of candidate proposals and corresponding confidence scores. Once obtaining the candidate proposals, the Pedestrian Recognization Network is proposed to distinguish pedestrian proposals by taking the visual information and pose information into consideration to refine the confidence scores and eliminate the false positives. Given the proposal image, the visual information is extracted with the Visual Feature Module. The Human Pose Module, which is proposed based on the pose estimation model, is used to predict the pose information. Further, the Classification Module is employed to fuse the visual and pose information and generates a pose-embedding pedestrian description. Extensive experiments on three challenging datasets, i.e., Caltech, CityPersons, and COCOPersons, show that the proposed approach achieves a significant improvement upon the state-of-the-art methods.
资助项目	National Key Research and Development Program of China[2018AAA0102200] ; National Natural Science Foundation of China[61902399] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[U1705262] ; National Natural Science Foundation of China[61532009] ; National Natural Science Foundation of China[61832002] ; National Natural Science Foundation of China[61720106006] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC039] ; National Postdoctoral Programme for Innovative Talents[BX20180358]
WOS研究方向	Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000626532100025
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Key Research Program of Frontier Sciences, CAS ; National Postdoctoral Programme for Innovative Talents
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/44190]
专题	自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者	Xu, Changsheng
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Hefei Univ Technol, Sch Comp Sci & Informat Engn, Hefei 230009, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Jiao, Yifan,Yao, Hantao,Xu, Changsheng. PEN: Pose-Embedding Network for Pedestrian Detection[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2021,31(3):1150-1162.
APA	Jiao, Yifan,Yao, Hantao,&Xu, Changsheng.(2021).PEN: Pose-Embedding Network for Pedestrian Detection.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,31(3),1150-1162.
MLA	Jiao, Yifan,et al."PEN: Pose-Embedding Network for Pedestrian Detection".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 31.3(2021):1150-1162.