车载红外图像的行人检测与跟踪技术  

Pedestrian detection and tracking of vehicle infrared images

作　　者：苏晓倩[1] 孙韶媛[1] 戈曼[1] 谯帅[1] 谷小婧[1] 

机构地区：[1]东华大学信息科学与技术学院,上海201620

出　　处：《激光与红外》2012年第8期949-953,共5页Laser & Infrared

基　　金：国家自然基金项目(No.61072090)资助

摘　　要：针对车载红外图像的特点,采用基于区域估计的帧差法实现车载红外图像中的行人检测,再通过行人的几何特征和运动速率特征进行行人的识别,最后运用轮廓矩匹配算法进行行人的跟踪。实验结果表明所采用的方法具有较好的行人检测及跟踪效果。Based on the characteristics of vehicle infrared images we detect pedestrians by the vehicle infrared images using three-frame-difference method which is based on region estimation. Then we make pedestrian recognition based on the geometric features and motion characteristics. Finally, pedestrian tracking is implemented using contour moment matching method. The experimental results show that the proposed method can detect and track the pedestrians aeeurately.

关 键 词：行人检测 行人跟踪 车载红外 区域估计 三帧差法 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]