基于运动矢量的异常拥挤行为检测算法

【摘要】 面向人群场景中异常拥挤行为检测,本文提出基于运动矢量的检测方法。该方法首先采用运动矢量场提取人群运动特征;然后基于社会力模型计算运动矢量微粒之间的相互作用力;最后对相互作用力采用词袋法实现行为判别。仿真实验表明,本算法可以区分人群场景中异常区域内相互作用力的大小,对异常拥挤行为进行判别和定位。更多还原

【Abstract】 In this paper,the detection method based on motion vector is proposed to detect the abnormal crowded behabior in a crowd scene.In this method,the motion characteristics of the crowd are extracted by using the motion vector field;Then the interaction force between the particales is calculated based on the social force model;Finally,the interaction force is used to realize the behavior by the bag of words method.The simulation results show that the algorithm can distinguish the size of the interaction force between the abnormal regions in the crowd scene,identify and locate the abnormal congestion.更多还原