Learning Sampling Distributions for Efficient Object Detection | |
Pang, Yanwei1; Cao, Jiale1; Li, Xuelong2 | |
作者部门 | 光学影像学习与分析中心 |
2017 | |
发表期刊 | IEEE TRANSACTIONS ON CYBERNETICS |
ISSN | 2168-2267 |
卷号 | 47期号:1页码:117-129 |
产权排序 | 2 |
摘要 | Object detection is an important task in computer vision and machine intelligence systems. Multistage particle windows (MPW), proposed by Gualdi et al., is an algorithm of fast and accurate object detection. By sampling particle windows (PWs) from a proposal distribution (PD), MPW avoids exhaustively scanning the image. Despite its success, it is unknown how to determine the number of stages and the number of PWs in each stage. Moreover, it has to generate too many PWs in the initialization step and it unnecessarily regenerates too many PWs around object-like regions. In this paper, we attempt to solve the problems of MPW. An important fact we used is that there is a large probability for a randomly generated PW not to contain the object because the object is a sparse event relative to the huge number of candidate windows. Therefore, we design a PD so as to efficiently reject the huge number of nonobject windows. Specifically, we propose the concepts of rejection, acceptance, and ambiguity windows and regions. Then, the concepts are used to form and update a dented uniform distribution and a dented Gaussian distribution. This contrasts to MPW which utilizes only on region of support. The PD of MPW is acceptance-oriented whereas the PD of our method (called iPW) is rejection-oriented. Experimental results on human and face detection demonstrate the efficiency and the effectiveness of the iPW algorithm. The source code is publicly accessible. |
文章类型 | Article |
关键词 | Feature Extraction Object Detection Particle Windows (Pws) Random Sampling |
WOS标题词 | Science & Technology ; Technology |
DOI | 10.1109/TCYB.2015.2508603 |
收录类别 | SCI ; EI |
关键词[WOS] | FACE DETECTION ; CLASSIFICATION |
语种 | 英语 |
WOS研究方向 | Computer Science |
项目资助者 | National Basic Research Program of China (973 Program)(2014CB340400) ; National Natural Science Foundation of China(61172121 ; 61271412 ; 61503274 ; 61222109) |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Cybernetics |
WOS记录号 | WOS:000391481400010 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/28634 |
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, Ctr Opt Imagery Anal & Learning, State Key Lab Transient Opt & Photon, Xian Inst Opt & Precis Mech, Xian 710119, Peoples R China |
推荐引用方式 GB/T 7714 | Pang, Yanwei,Cao, Jiale,Li, Xuelong. Learning Sampling Distributions for Efficient Object Detection[J]. IEEE TRANSACTIONS ON CYBERNETICS,2017,47(1):117-129. |
APA | Pang, Yanwei,Cao, Jiale,&Li, Xuelong.(2017).Learning Sampling Distributions for Efficient Object Detection.IEEE TRANSACTIONS ON CYBERNETICS,47(1),117-129. |
MLA | Pang, Yanwei,et al."Learning Sampling Distributions for Efficient Object Detection".IEEE TRANSACTIONS ON CYBERNETICS 47.1(2017):117-129. |
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 | ||
Learning Sampling Di(1981KB) | 期刊论文 | 作者接受稿 | 限制开放 | CC BY-NC-SA | 请求全文 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论