面向视频监控的自动行人检测  

Automatic Pedestrian Detection Based on Video Surveillance

作　　者：李新江[1] 龚勋[1] 李天瑞[1] 赵涛[1] 熊伟[1] 

机构地区：[1]西南交通大学信息科学与技术学院,成都610031

出　　处：《计算机科学》2014年第12期264-268,共5页Computer Science

基　　金：国家自然科学基金(61202191);中央高校基本科研业务费专项资金(SWJTU12CX095)资助

摘　　要：为了解决目前行人检测技术的检测速度和准确性之间的平衡问题,对基于视频的行人检测技术进行了研究,提出了利用LUV颜色空间信息与C4行人检测算法相结合的视频自动行人检测方法(LUVC4)。首先利用C4行人检测算法快速遍历视频的每帧图像,当得到的窗口置信度在可疑区间时,再进一步对该窗口做LUV颜色空间检测。如果两次检测的加权和分数满足阈值,则判别为行人。通过大量实验表明,该方法在检测速度几乎能达到C4速度的同时,还能在FPPI为0.1时降低约9%的漏检率。To address the problem that the technologies of pedestrian detection can＇t achieve the balance between detecting speed and accuracy,this paper aimed to research on pedestrian detection under video surveillance An automatic video pedestrian detection method （denoted as LUVC4） was proposed by combining LUV color space information and C4 pedestrian detection algorithm.Firstly the C4 algorithm is used to rapidly traversal each frame of the video image.The LUV color space is taken to detect this window further when the confidence score of detect window is in the suspicious interval.If the weighted sum of scores of the two detections satisfies the threshold,it is discriminated as a pedestrian.A large number of experiments show that the detection speed of the proposed method nearly reaches that of C4 and it can greatly decrease the missrate about 9 ％ when false positive per image equals to 0.1.

关 键 词：行人检测 LUV C4 置信度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]