Efficient Single-Stage Pedestrian Detector by Asymptotic Localization Fitting and Multi-Scale Context Encoding

doi:10.1109/TIP.2019.2938877

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 视频内容安全

	Efficient Single-Stage Pedestrian Detector by Asymptotic Localization Fitting and Multi-Scale Context Encoding
	Liu, Wei1,2,3 ; Liao, Shengcai4 ; Hu, Weidong 1
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
	2020
卷号	29 页码:1413-1425
通讯作者	Liao, Shengcai(scliao@nlpr.ia.ac.cn)
摘要	Though Faster R-CNN based two-stage detectors have witnessed significant boost in pedestrian detection accuracy, they are still slow for practical applications. One solution is to simplify this working flow as a single-stage detector. However, current single-stage detectors (e.g. SSD) have not presented competitive accuracy on common pedestrian detection benchmarks. Accordingly, a structurally simple but effective module called Asymptotic Localization Fitting (ALF) is proposed, which stacks a series of predictors to directly evolve the default anchor boxes of SSD step by step to improve detection results. Additionally, combining the advantages from residual learning and multi-scale context encoding, a bottleneck block is proposed to enhance the predictors' discriminative power. On top of the above designs, an efficient single-stage detection architecture is designed, resulting in an attractive pedestrian detector in both accuracy and speed. A comprehensive set of experiments on two of the largest pedestrian detection datasets (i.e. CityPersons and Caltech) demonstrate the superiority of the proposed method, comparing to the state of the arts on both the benchmarks.
关键词	Pedestrian detection convolutional neural networks asymptotic localization fitting
DOI	10.1109/TIP.2019.2938877
收录类别	SCI
语种	英语
资助项目	Chinese National Natural Science Foundation[61672521] ; Chinese National Natural Science Foundation[61672521]
项目资助者	Chinese National Natural Science Foundation
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000497431400002
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	目标检测、跟踪与识别
引用统计	被引频次：13[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/29400
专题	多模态人工智能系统全国重点实验室_视频内容安全
通讯作者	Liao, Shengcai
作者单位	1.Natl Univ Def Technol, Coll Elect Sci, Natl Key Lab Sci & Technol ATR, Changsha 410073, Hunan, Peoples R China 2.Chinese Acad Sci, Ctr Biometr & Secur Res, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 4.Incept Inst Artificial Intelligence, Abu Dhabi, U Arab Emirates
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Liu, Wei,Liao, Shengcai,Hu, Weidong. Efficient Single-Stage Pedestrian Detector by Asymptotic Localization Fitting and Multi-Scale Context Encoding[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29:1413-1425.
APA	Liu, Wei,Liao, Shengcai,&Hu, Weidong.(2020).Efficient Single-Stage Pedestrian Detector by Asymptotic Localization Fitting and Multi-Scale Context Encoding.IEEE TRANSACTIONS ON IMAGE PROCESSING,29,1413-1425.
MLA	Liu, Wei,et al."Efficient Single-Stage Pedestrian Detector by Asymptotic Localization Fitting and Multi-Scale Context Encoding".IEEE TRANSACTIONS ON IMAGE PROCESSING 29(2020):1413-1425.