ROI-HOG and LBP Based Human Detection via Shape Part-Templates Matching

被引：0

作者：

Zhou, Shenghui ^{[1
]}

Liu, Qing ^{[1
]}

Guo, Jianming ^{[1
]}

Jiang, Yuanyuan ^{[1
]}

机构：

[1] Wuhan Univ Technol, Sch Automat, Wuhan 430070, Peoples R China

来源：

NEURAL INFORMATION PROCESSING, ICONIP 2012, PT V | 2012年 / 7667卷

关键词：

Pedestrian detection; ROI-HOG descriptor; LBP feature; Shape part-template matching;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Currently, Histogram of Oriented Gradient (HOG) descriptor serves as the predominant method when it comes to human detection. To further improving its detection accuracy and decrease its large dimensions of feature vectors, we introduce an improved method in which HOG is extracted in the Region of Interest (ROI) of human body with a combined Local Binary Pattern (LBP) feature. Via establishing human shape part-templates tree, a template matching approach is employed to improve detection results and segment human edges. The experimental results on INRIA database and images from practical campus video surveillance demonstrate the effectiveness of our method.

引用

页码：109 / 115

页数：7

共 6 条

[1] [Anonymous], 2005, PROC CVPR IEEE
[2] Changyan Li, 2010, 2010 3rd International Congress on Image and Signal Processing (CISP 2010), P290, DOI 10.1109/CISP.2010.5648239
[3] Shape-Based Human Detection and Segmentation via Hierarchical Part-Template Matching
Lin, Zhe
Davis, Larry S.
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2010, 32 (04) : 604 - 618
[4] Multiresolution gray-scale and rotation invariant texture classification with local binary patterns
Ojala, T
Pietikäinen, M
Mäenpää, T
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (07) : 971 - 987
[5] Qing Liu, 2011, 2011 Seventh International Conference on Natural Computation (ICNC 2011), P584, DOI 10.1109/ICNC.2011.6022084
[6] An HOG-LBP Human Detector with Partial Occlusion Handling
Wang, Xiaoyu
Han, Tony X.
Yan, Shuicheng
[J]. 2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2009, : 32 - 39

← 1 →