A Fast Pedestrian Detection via Modified HOG Feature

被引：0

作者：

Li Weixing ^{[1
]}

Su Haijun ^{[1
]}

Pan Feng ^{[1
]}

Gao Qi ^{[1
]}

Quan Bin ^{[1
]}

机构：

[1] Beijing Inst Technol, Sch Automat, Beijing 100081, Peoples R China

来源：

2015 34TH CHINESE CONTROL CONFERENCE (CCC) | 2015年

关键词：

Pedestrian Detection; Combination of HOG Channels; SVM;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The Histogram of Oriented Gradient (HOG) feature for pedestrian detection has achieved good results, but it is time-consuming. For resolving this problem, a modified method for HOG is proposed to reduce the dimension of the features. On the base of analyzing the process of HOG, nine independent HOG channels (HOG-C) are extracted according to the gradient orientation interval. Through evaluating the effectiveness of HOG-C for pedestrian detection individually, a combination of HOG channels (CHOG-C) feature is presented based on statistical regularities. Comprehensive experiments on INRIA database demonstrated the promising performance of the CHOG-C feature, and the experimental results shown that the dimension is reduced meanwhile without losing the accuracy.

引用

页码：3870 / 3873

页数：4

共 13 条

[1] [Anonymous], 2009, P BRIT MACH VIS C
[2] Cherkassky V, 1999, IEEE T NEURAL NETWOR, V10, P985
[3] Cui XY, 2007, 2007 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, VOLS 1-5, P1263
[4] Histograms of oriented gradients for human detection
Dalal, N
Triggs, B
[J]. 2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, : 886 - 893
[5] Dollar P., INTEGRAL CHANNEL FEA
[6] Pedestrian Detection: An Evaluation of the State of the Art
Dollar, Piotr
Wojek, Christian
Schiele, Bernt
Perona, Pietro
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (04) : 743 - 761
[7] Li Bo, 2010, NETWORKING SENSING C, P393
[8] Distinctive image features from scale-invariant keypoints
Lowe, DG
[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2004, 60 (02) : 91 - 110
[9] Efficient HOG human detection
Pang, Yanwei
Yuan, Yuan
Li, Xuelong
Pan, Jing
[J]. SIGNAL PROCESSING, 2011, 91 (04) : 773 - 781
[10] Prisacariu V., 2009, fastHOG-a real-time GPU implementation of HOG

← 1 2 →