A Novel Multi-Feature Descriptor for Human Detection Using Cascaded Classifiers in Static Images

doi:10.1007/s11265-014-0960-6

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	A Novel Multi-Feature Descriptor for Human Detection Using Cascaded Classifiers in Static Images
	Liu, Hong 2; Xu, Tao 1; Wang, Xiangdong 2; Qian, Yueliang 2
刊名	JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY
	2015-12-01
卷号	81 期号:3 页码:377-388
关键词	Human detection Feature extraction HOG Multi-feature Cascaded classifiers
ISSN号	1939-8018
DOI	10.1007/s11265-014-0960-6
英文摘要	Combining multiple kinds of features is useful to achieve the state of the art performance for human detection. But combining more features will result in high dimensional feature descriptors, which is time-consuming for feature extraction and detection. How to exploit different kinds of features and reduce the dimension of feature descriptor are challenging problems. A novel multi-feature descriptor (MFD) combining Optimal Histograms of Oriented Gradients (OHOG), Local Binary Patterns (LBP) and Color Self-Similarity in Neighbor (NCSS) is proposed. Firstly, a discriminative feature selection and combination strategy is introduced to obtain distinctive local HOGs and construct OHOG feature. OHOG combines local discriminative and correlated information, which improves the classification performance compared with HOG. Besides, LBP describes texture feature of human appearance. Finally, a compact and lower dimensional feature NCSS is proposed to encode the self-similarity of color histograms in limited neighbor sub-regions instead of global regions. The proposed MFD describes human appearance from gradient, texture and color features, which can complement each other and improve the robustness of human description. To further improve detection speed without decreasing accuracy, we cascade early stages of Adaboost based on selected local HOGs and SVM classifier based on MFD. The former part can reject most non-human detection windows quickly and the final SVM classifier can guarantee a high accuracy. Experimental results on public dataset show that the proposed MFD and cascaded classifiers framework can achieve promising results both in accuracy and detection speed.
资助项目	National Nature Science Foundation of China[61,202,209] ; Beijing Natural Science Foundation[4,142,051] ; Beijing Natural Science Foundation[4,122,079]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000362575300005
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/9287]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Liu, Hong
作者单位	1.Lehigh Univ, Dept Comp Sci & Engn, Bethlehem, PA 18015 USA 2.Chinese Acad Sci, Beijing Key Lab Mobile Comp & Pervas Device, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Liu, Hong,Xu, Tao,Wang, Xiangdong,et al. A Novel Multi-Feature Descriptor for Human Detection Using Cascaded Classifiers in Static Images[J]. JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY,2015,81(3):377-388.
APA	Liu, Hong,Xu, Tao,Wang, Xiangdong,&Qian, Yueliang.(2015).A Novel Multi-Feature Descriptor for Human Detection Using Cascaded Classifiers in Static Images.JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY,81(3),377-388.
MLA	Liu, Hong,et al."A Novel Multi-Feature Descriptor for Human Detection Using Cascaded Classifiers in Static Images".JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY 81.3(2015):377-388.