Efficient object detection by prediction in 3D space

doi:10.1016/j.sigpro.2014.08.039

OPT OpenIR > 光谱成像技术研究室

	Efficient object detection by prediction in 3D space
	Pang, Yanwei 1; Jiang, Xiaoheng 1; Li, Xuelong2 ; Pan, Jing 3
作者部门	光学影像学习与分析中心
	2015-07-01
发表期刊	SIGNAL PROCESSING
ISSN	0165-1684
卷号	112 期号:SI 页码:64-73
产权排序	2
摘要	Because the scale, horizontal and vertical coordinates of an object in an image are arbitrary, so object detection can be viewed as a process of searching the object in the 3D space spanned by the scale, horizontal, and vertical factors. Traditional sliding window based method has to exhaustively search and check the 3D space, resulting in prohibitive computation cost. To deal with this problem, in this paper, we propose to explore both the scaling capacity and translation capacity of object detector to accelerate detection speed, without loss of detection accuracy. In our paradigm, scaling capacity can relieve the use of all possible sizes of templates at the first stage, i.e., only a few number of templates that can cover a large range of target object size are used to coarsely find the targets. Similarly, translation capacity can avoid dense grid sampling at the very beginning. After initial estimation, further evaluations with templates of finer scales are carried out around the candidates to verify the existence of target objects. Moreover, different from traditional uniform grid scanning, we present an interlaced scanning method called diamond grid scanning which can reduce redundant evaluation. Experimental results on face detection demonstrate the advantage of our method. (C) 2014 Elsevier B.V. All rights reserved.
文章类型	Article
关键词	Object Detection Scaling Capacity Translation Capacity Diamond Scanning
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.sigpro.2014.08.039
收录类别	SCI ; EI
关键词[WOS]	PEDESTRIAN DETECTION ; FACE-RECOGNITION ; CASCADE ; FEATURES ; CLASSIFICATION ; PATTERNS
语种	英语
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000351976400008
引用统计	被引频次：9[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.opt.ac.cn/handle/181661/24130
专题	光谱成像技术研究室
作者单位	1.Tianjin Univ, Sch Elect Informat Engn, Tianjin 300072, Peoples R China 2.Chinese Acad Sci, Xian Inst Opt & Precis Mech, State Key Lab Transient Opt & Photon, Ctr OPT IMagery Anal & Learning OPTIMAL, Xian 710119, Shaanxi, Peoples R China 3.Tianjin Univ Technol & Educ, Sch Elect Engn, Tianjin 300222, Peoples R China
推荐引用方式 GB/T 7714	Pang, Yanwei,Jiang, Xiaoheng,Li, Xuelong,et al. Efficient object detection by prediction in 3D space[J]. SIGNAL PROCESSING,2015,112(SI):64-73.
APA	Pang, Yanwei,Jiang, Xiaoheng,Li, Xuelong,&Pan, Jing.(2015).Efficient object detection by prediction in 3D space.SIGNAL PROCESSING,112(SI),64-73.
MLA	Pang, Yanwei,et al."Efficient object detection by prediction in 3D space".SIGNAL PROCESSING 112.SI(2015):64-73.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Efficient object det（1172KB）	期刊论文	出版稿	限制开放	CC BY	请求全文