Publication in refereed journal
香港中文大学研究人员 ( 现职)
| 颜庆义教授 (电子工程学系) |
全文
| 数位物件识别号 (DOI) ○○@http://aims.cuhk.edu.hk/converis/portal/Publication/2$@○○ |
引用次数
Web of Sciencehttp://aims.cuhk.edu.hk/converis/portal/Publication/2WOS source URL
其它资讯
摘要In this paper, we present a hybrid human recognition system for surveillance. A Cascade Head-Shoulder Detector (CHSD) with human body model is proposed to find the face region in a surveillance video frame image. The CHSD is a chain of rejecters which combines the advantages of Haar-like feature and HoG feature to make the detector more efficient and effective. For human recognition, we introduce an Overlapping Local Phase Feature (OLPF) to describe the face region, which can improve the robustness to pose change and blurring. To well model the variations of faces, an Adaptive Gaussian Mixture Model (AGMM) is presented to describe the distributions of the face images. Since AGMM does not need the facial topology, the proposed method is resistant to face detection error caused by imperfect localization or misalignment. Experimental results demonstrate the effectiveness of the proposed method in public dataset as well as real surveillance video. (C) http://aims.cuhk.edu.hk/converis/portal/Publication/2016 Elsevier B.V. All rights reserved.
着者Liu Q, Zhang W, Li HL, Ngan KN
期刊名称Neurocomputing
出版年份http://aims.cuhk.edu.hk/converis/portal/Publication/2016
月份6
日期19
卷号194
出版社ELSEVIER SCIENCE BV
页次10 - http://aims.cuhk.edu.hk/converis/portal/Publication/23
国际标準期刊号09http://aims.cuhk.edu.hk/converis/portal/Publication/25-http://aims.cuhk.edu.hk/converis/portal/Publication/231http://aims.cuhk.edu.hk/converis/portal/Publication/2
电子国际标準期刊号187http://aims.cuhk.edu.hk/converis/portal/Publication/2-8http://aims.cuhk.edu.hk/converis/portal/Publication/286
语言英式英语
关键词AdaBoost; Gaussian Mixture Model; Head-Shoulder Detector; Human recognition; Overlapping Local Phase Feature; Surveillance
Web of Science 学科类别Computer Science; Computer Science, Artificial Intelligence
