Joint Pedestrian and Body Part Detection via Semantic Relationship Learning

doi:10.3390/app9040752

	Joint Pedestrian and Body Part Detection via Semantic Relationship Learning
	Gu, Junhua 1,2; Lan, Chuanxin 1,3; Chen, Wenbai 4; Han, Hu 3
	2019-02-02
发表期刊	APPLIED SCIENCES-BASEL
ISSN	2076-3417
卷号	9 期号:4 页码:14
摘要	While remarkable progress has been made to pedestrian detection in recent years, robust pedestrian detection in the wild e.g., under surveillance scenarios with occlusions, remains a challenging problem. In this paper, we present a novel approach for joint pedestrian and body part detection via semantic relationship learning under unconstrained scenarios. Specifically, we propose a Body Part Indexed Feature (BPIF) representation to encode the semantic relationship between individual body parts (i.e., head, head-shoulder, upper body, and whole body) and highlight per body part features, providing robustness against partial occlusions to the whole body. We also propose an Adaptive Joint Non-Maximum Suppression (AJ-NMS) to replace the original NMS algorithm widely used in object detection, leading to higher precision and recall for detecting overlapped pedestrians. Experimental results on the public-domain CUHK-SYSU Person Search Dataset show that the proposed approach outperforms the state-of-the-art methods for joint pedestrian and body part detection in the wild.
关键词	joint pedestrian and body part detection adaptive joint non-maximum suppression semantic relationship learning
DOI	10.3390/app9040752
收录类别	SCI
语种	英语
资助项目	NSF of Hebei Province through the Key Program[F2016202144]
WOS研究方向	Chemistry ; Materials Science ; Physics
WOS类目	Chemistry, Multidisciplinary ; Materials Science, Multidisciplinary ; Physics, Applied
WOS记录号	WOS:000460696500138
出版者	MDPI
引用统计	被引频次：8[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/4116
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Han, Hu
作者单位	1.Hebei Univ Technol, Sch Artificial Intelligence, Tianjin 300401, Peoples R China 2.Hebei Prov Key Lab Big Data Comp, Tianjin 300401, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 4.Beijing Informat Sci & Technol Univ, Sch Automat, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	Gu, Junhua,Lan, Chuanxin,Chen, Wenbai,et al. Joint Pedestrian and Body Part Detection via Semantic Relationship Learning[J]. APPLIED SCIENCES-BASEL,2019,9(4):14.
APA	Gu, Junhua,Lan, Chuanxin,Chen, Wenbai,&Han, Hu.(2019).Joint Pedestrian and Body Part Detection via Semantic Relationship Learning.APPLIED SCIENCES-BASEL,9(4),14.
MLA	Gu, Junhua,et al."Joint Pedestrian and Body Part Detection via Semantic Relationship Learning".APPLIED SCIENCES-BASEL 9.4(2019):14.