红外视频图像中的人体目标检测方法

被引：13

作者：

梁英宏

机构：

[1] 广东商学院广东省电子商务市场应用技术重点实验室

来源：

红外与激光工程 | 2009年 / 05期

基金：

广东省科技计划;

关键词：

人体目标检测; 红外视频图像; 目标检测; 直方图特征;

D O I：

暂无

中图分类号：

TP391.41 [];

学科分类号：

080203 ;

摘要：

人体目标检测是很多机器视觉应用的难点,如智能视频监控和车辆辅助驾驶,基于可见光图像的方法很难解决复杂背景和目标区域的分离问题,因此,越来越多的研究转向利用红外图像进行检测。提出了一种红外视频图像中的人体目标检测方法,该方法首先利用红外图像中像素值近似呈现单模态分布的特点,对高亮像素进行检测,然后采用灰度直方图和投影直方图相结合的2D直方图特征对目标进行检测。实验结果表明:该方法具有较高的检测率,但误报率也较高,其原因在于负样本的数量和代表性不足,因此,改进空间很大。

引用

页码：931 / 935

页数：5

共 10 条

[1]

Probabilistic Template Based Pedestrian Detection in Infrared Videos. H Nanda,,L Davis. Procs. IEEE Intelligent Vehicles Symposium . 2002

[2]

Pedestrian detection and tracking with night vision. Fengliang Xu,Xia Liu,Fujimura K. IEEE Transactions on Intelligent Transportation Systems . 2005

[3]

A two-stage approach to person detection in thermal imagery. DAVIS J,KECK M. Proc of the Seventh IEEE Workshops on Application of Computer Vision . 2005

[4]

Robust background-subtraction for person detection in thermal imagery. DAVIS J W,SHARMA V. Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshop . 2004

[5]

A pedestrian detector using histograms of oriented gradients and a support vector machine classifier. BERTOZZI M,BROGGI A,DEL ROSE M,et al. Proc of the IEEE Intelligent Transportation Systems Conference . 2007

[6]

Multiple detector approach to low-resolution FIR pedestrian recognition. MAHLISCH M,,OBERLANDER M,LOHLEIN O,et al. IEEE Intelligent Vehicles Symposium . 2005

[7]

IR pedestrian detection for advanced driver assistance systems. M.Bertozzi,A.Broggi,M.Carletti,A.Fascioli,T.Graf,P.Grisleri,and M.Meinecke. Lecture Notes Computer Science . 2003

[8]

Pedestrian Detection by Means of Far-Infrared Stereo Vision. M Bertozzi,A Broggi,C Caraffi, et al. Computer Vision and Image Understanding . 2007

[9]

Pedestrian detection in infrared images based on local shape features. ZHANG L,WU B,NEVATIA R. Proc of the IEEE Conference on Computer Vision and Pattern Reco-gnition . 2007

[10]

A Shape-Independent Method for Pedestrian Detection with Far-Infrared Images. Fang Y,K Yamada,Y Ninomiya,et al. IEEE Transactions on Vehicular Technology . 2004

← 1 →