A NEW EDGE FEATURE FOR HEAD-SHOULDER DETECTION

被引:0
作者
Wang, Shu [1 ,2 ]
Zhang, Jian [1 ]
Miao, Zhenjiang [2 ]
机构
[1] Univ Technol Sydney, Adv Analyt Inst, Sydney, NSW 2007, Australia
[2] Beijing Jiaotong Univ, Inst Informat Sci, Beijing, Peoples R China
来源
2013 20TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP 2013) | 2013年
关键词
Head-shoulder detection; Edge pattern; Contour enhance;
D O I
暂无
中图分类号
TB8 [摄影技术];
学科分类号
0804 ;
摘要
In this work, we introduce a new edge feature to improve the head-shoulder detection performance. Since Head-shoulder detection is much vulnerable to vague contour, our new edge feature is designed to extract and enhance the head-shoulder contour and suppress the other contours. The basic idea is that head-shoulder contour can be predicted by filtering edge image with edge patterns, which are generated from edge fragments through a learning process. This edge feature can significantly enhance the object contour such as human head and shoulder known as En-Contour. To evaluate the performance of the new En-Contour, we combine it with HOG+LBP [1] as HOG+LBP+En-Contour. The HOG+LBP is the state-of-the-art feature in pedestrian detection. Because the human head-shoulder detection is a special case of pedestrian detection, we also use it as our baseline. Our experiments have indicated that this new feature significantly improve the HOG+LBP.
引用
收藏
页码:2822 / 2826
页数:5
相关论文
共 10 条
[1]  
Arbeláez P, 2009, PROC CVPR IEEE, P2294, DOI 10.1109/CVPRW.2009.5206707
[2]   Efficient, High-Quality Image Contour Detection [J].
Catanzaro, Bryan ;
Su, Bor-Yiing ;
Sundaram, Narayanan ;
Lee, Yunsup ;
Murphy, Mark ;
Keutzer, Kurt .
2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2009, :2381-2388
[3]  
Chengbin Zeng, 2010, Proceedings of the 2010 20th International Conference on Pattern Recognition (ICPR 2010), P2069, DOI 10.1109/ICPR.2010.509
[4]   Pedestrian Detection: An Evaluation of the State of the Art [J].
Dollar, Piotr ;
Wojek, Christian ;
Schiele, Bernt ;
Perona, Pietro .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (04) :743-761
[5]  
Li M., 2008, 2008 19 INT C PATTER, P1, DOI DOI 10.1109/ICPR.2008.4761705
[6]   RAPID AND ROBUST HUMAN DETECTION AND TRACKING BASED ON OMEGA-SHAPE FEATURES [J].
Li, Min ;
Zhang, Zhaoxiang ;
Huang, Kaiqi ;
Tan, Tieniu .
2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-6, 2009, :2545-2548
[7]  
Lin Z, 2007, IEEE I CONF COMP VIS, P2301
[8]  
Sabzmeydani P., 2007, Computer Vision and Pattern Recog- nition, P1
[9]   An HOG-LBP Human Detector with Partial Occlusion Handling [J].
Wang, Xiaoyu ;
Han, Tony X. ;
Yan, Shuicheng .
2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2009, :32-39
[10]  
Wu B, 2005, IEEE I CONF COMP VIS, P90