中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Rotative maximal pattern: A local coloring descriptor for object classification and recognition

文献类型：期刊论文

作者Pang, Junbiao3; Huang, Jing3; Qin, Lei2; Zhang, Weigang4; Qing, Laiyun1; Huang, Qingming1,2; Yin, Baocai3
刊名INFORMATION SCIENCES
出版日期2017-09-01
卷号405页码:190-206
关键词Object detection Object recognition Max pooling Translation invariance Self similarity Photometric invariance
ISSN号0020-0255
DOI10.1016/j.ins.2017.04.011
英文摘要Inspired by the photometric invariance of color space, this paper proposes a simple yet powerful descriptor for object detection and recognition, called Rotative Maximal Pattern (RMP). The effectiveness of RMP comes from the two components: Rotatable Couple Templates (RCTs) with max pooling, and Normalized Histogram Intersection (NHI) with the theoretical guarantee. More concretely, RCTs are the combination of two templates to code the possible rotations. NHI serves as the similarity between two color histograms. We have conducted extensive experiments on INRIA pedestrian and Pascal VOC2007 data sets for object detection tasks; we also show that our approach leads to a promising performance on Caltech 101, Scene 15, UIUCsport and Stanford 40 action data sets. (C) 2017 Published by Elsevier Inc.
资助项目Natural Science Foundation of China[61672069] ; Natural Science Foundation of China[61332016] ; Natural Science Foundation of China[61620106009] ; Natural Science Foundation of China[61472387] ; Natural Science Foundation of China[U1636214] ; Natural Science Foundation of China[61650202] ; Key Research Program of Frontier Sciences[CAS: QYZDJ-SSW-SYS013] ; China Postdoctoral Science Foundation ; Beijing Post-Doctoral Research Foundation ; Beijing Municipal Commission of Education[KM201610005034] ; Funding Project for Academic Human Resources Development in Institutions of Higher Learning Under the Jurisdiction of Beijing Municipality (PHR)
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000401688100012
出版者ELSEVIER SCIENCE INC
源URL[http://119.78.100.204/handle/2XEOYT63/7244]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Qing, Laiyun
作者单位1.Univ Chinese Acad Sci, Sch Comp & Control Engn, 19 Yuquan Rd, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, 6 Kexueyuan South Rd, Beijing 100190, Peoples R China
3.Beijing Univ Technol, Fac Informat Technol, Beijing Key Lab Multimedia & Intelligent Software, 100 Pingleyuan Rd, Chaoyang Dist 100124, Peoples R China
4.Harbin Inst Technol Weihai, Sch Comp Sci & Technol, 2 West Wenhua Rd, Weihai 26209, Peoples R China
推荐引用方式
GB/T 7714		 Pang, Junbiao,Huang, Jing,Qin, Lei,et al. Rotative maximal pattern: A local coloring descriptor for object classification and recognition[J]. INFORMATION SCIENCES,2017,405:190-206.
APA Pang, Junbiao.,Huang, Jing.,Qin, Lei.,Zhang, Weigang.,Qing, Laiyun.,...&Yin, Baocai.(2017).Rotative maximal pattern: A local coloring descriptor for object classification and recognition.INFORMATION SCIENCES,405,190-206.
MLA Pang, Junbiao,et al."Rotative maximal pattern: A local coloring descriptor for object classification and recognition".INFORMATION SCIENCES 405(2017):190-206.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

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。