Biased Boosting Using Weighted Template Matching for Pedestrian Detection

被引：0

作者：

Huang, Shih-Shinh ^{[1
]}

Ku, Shih-Han ^{[1
]}

机构：

[1] Natl Kaohsiung First Univ Sci & Technol, Dept Comp & Commun Engn, Kaohsiung, Taiwan

来源：

2014 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS - TAIWAN (ICCE-TW) | 2014年

关键词：

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

The main objective of this work is to alleviate this problem by imposing the matching results from a classifier based on a set of constructed weighted templates to the boosting framework. The integration of global contour templates and local HOGs is through the adjustment of the hyperplane from the support vector machine. The concept behind is to bias the hyperplane and make it consistent with the template-based classifier at each round of boosting stage.

引用

页数：2

共 6 条

[1]

[Anonymous], 2005, P 22 INT C MACHINE L

[2] Histograms of oriented gradients for human detection [J].

Dalal, N ;

Triggs, B .

2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, :886-893

[3] Monocular Pedestrian Detection: Survey and Experiments [J].

Enzweiler, Markus ;

Gavrila, Dariu M. .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2009, 31 (12) :2179-2195

[4]

Huang SS, 2012, IEEE SYS MAN CYBERN, P565, DOI 10.1109/ICSMC.2012.6377785

[5]

THANH ND, 2009, IEEE INT C IM PROC, P2549

[6]

Zhu Q., 2006, IEEE COMP SOC C COMP, V2, P1491, DOI [10.1109/CVPR.2006.119, DOI 10.1109/CVPR.2006.119]

← 1 →