铁路客运站视频监控系统中的行人逆行异常事件检测算法研究

由于铁路客运站的许多区域要求行人单向运动,因此检测视频中是否出现行人逆行异常事件,是保证铁路客运站拥有安全稳定乘车秩序的重要手段.鉴于此,本文提出了一种逆行异常事件的检测算法,首先基于HoG特征进行行人检测,随后利用mean-shift算法对目标进行实时跟踪,并通过判断其运动方向是否与规定方向一致,最终实现对逆行异常事件的检测.实验结果表明,该方法既能显著降低运算的复杂度,又能明显提高检测的准确率.

Research on algorithm of abnormal event detection to pedesorian opposing flow in Video Monitoring System of railway passenger station

In the railway passenger station, pedestrians were required to run in one way traffic lane in order to guarantee the order and public security in open environments. So, it was an important way to detec if there was pedestrian opposing flow abnormal event. A novel method for detecting opposing flow abnormal event was proposed. Firstly, the HoG features were utilized to detect the pedestrians in the railway passenger station. And then the mean-shift algorithm was used to track the pedestrians to finally determine if there was an abnormal event. The experimental results showed that the proposed method could dramatically reduce the complexity, and as well improve detection accuracy.