基于角点动能模型的电梯轿厢内异常行为检测

Abnormal behavior detection in elevator car based on corner kinetic energy model

针对电梯轿厢内安全,为避免发生打架、抢劫、施暴等行为,通过视频信息分析,提出了一种基于角点动能的异常行为检测模型,以达到实时安全监控的目的。提出一种采用Hausdorff距离匹配背景边缘模型的前景目标提取方法,通过检测目标边缘的角点并计算角点的光流,根据角点光流包含的速度矢量信息建立目标的动能模型,用于异常行为判断。实验结果表明,该方法能有效地检测出电梯轿厢内的异常行为,且实现简单、算法复杂度低、能够实时报警。

To avoid fighting,robbery and violence occurred in the elevator car,this paper proposed an abnormal behavior detection model based on corner kinetic energy by analyzing the input video to achieve real-time safety monitoring.Firstly,proposed a method of extracting foreground object by matching the background edge model using Hausdorff distance.Then,detected the corner of object edge to calculate its optical flow,and established the kinetic energy model of the overall object accor-ding to the optical flow velocity vector of the edge corner to detect abnormal behavior.Experimental results show that the method can detect abnormal behavior in the elevator car effectively,and the algorithm is of low computation complexity thus it can alarm real-time.