Preceding vehicle detection using histograms of oriented gradients

doi:10.1109/ICCCAS.2010.5581983

CQUET-IR > 质量管理中心

	Preceding vehicle detection using histograms of oriented gradients
	Mao, Ling 1; Xie, Mei 1; Huang, Yi2 ; Zhang, Yuefei 1
	2010
会议录名称	2010 International Conference on Communications, Circuits and Systems, ICCCAS 2010 - Proceedings
页码	354-358
出版者	IEEE Computer Society
摘要	This paper presents a monocular vision-based preceding vehicle detection system using Histogram of Oriented Gradient (HOG) based method and linear SVM classification. Our detection algorithm consists of three main components: HOG feature extraction, linear SVM classifier training and vehicles detection. Integral Image method is adopted to improve the HOG computational efficiency, and hard examples are generated to reduce false positives in the training phase. In detection step, the multiple overlapping detections due to multi-scale window searching are very well fused by non-maximum suppression based on mean-shift. The monocular system is tested under different traffic scenarios (e.g., simply structured highway, complex urban environments, local occlusion conditions), illustrating good performance. © 2010 IEEE.
关键词	Computational efficiency Graphic methods Image enhancement Support vector machines Vehicles Complex urban environments Detection algorithm Histogram of oriented gradients (HOG) Histograms of oriented gradients Monocular systems Non-maximum suppression Preceding vehicle detections Vehicles detection
DOI	10.1109/ICCCAS.2010.5581983
收录类别	EI
语种	英语
EI入藏号	20104613394042
原始文献类型	Conference article (CA)
文献类型	会议论文
条目标识符	https://ir.cqcet.edu.cn/handle/39TD4454/3297
专题	质量管理中心
作者单位	1.School of Electronic Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan, China; 2.Department of Communication Engineering, Chongqing College of Electronic Engineering, Shapingba, Chongqing, China
推荐引用方式 GB/T 7714	Mao, Ling,Xie, Mei,Huang, Yi,et al. Preceding vehicle detection using histograms of oriented gradients[C]:IEEE Computer Society,2010:354-358.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Mao-2010-Preceding v（1194KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载