CASIA OpenIR  > 智能制造技术与系统研究中心  > 先进制造与自动化
Pedestrian Detection Using Boosted HOG Features
Zhen-rui Wang; Yulan Jia; Hua Huang; Shuming Tang
Conference NameThe Proceedings of the 11th IEEE International Conference on Intelligent Transportation Systems
Conference DateOctober 12-15, 2008
Conference PlaceBeijing, China
AbstractThis paper presents a novel approach in pedestrian detection in static images. The state-of-art feature named Histograms of Oriented Gradients (HOG) [1] is adopted as the basic feature which we modify and create a new feature using boosting algorithm. The detection is achieved by training a linear SVM with the boosted HOG feature. We experimentally demonstrate that our solution achieve comparable performance as the HOG algorithm on the INRIA pedestrian dataset yet considerably reduce storage requirement and simplify the computation in terms of elementary operations.
KeywordSupport Vector Machines Intelligent Transportation Systems Support Vector Machine Classification Automation Humans Computer Vision Histograms Shape Infrared Detectors Computational Efficiency
Document Type会议论文
Corresponding AuthorZhen-rui Wang
Recommended Citation
GB/T 7714
Zhen-rui Wang,Yulan Jia,Hua Huang,et al. Pedestrian Detection Using Boosted HOG Features[C],2008.
Files in This Item: Download All
File Name/Size DocType Version Access License
Pedestrian Detection(292KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhen-rui Wang]'s Articles
[Yulan Jia]'s Articles
[Hua Huang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhen-rui Wang]'s Articles
[Yulan Jia]'s Articles
[Hua Huang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhen-rui Wang]'s Articles
[Yulan Jia]'s Articles
[Hua Huang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Pedestrian Detection Using Boosted HOG Features.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.