CAJ | 학술논문

对拥挤地区人群行为的检测对于多种安全任务都至关重要.这个问题包括2个部分:对拥挤程度的估计和对异常的检测.本文定义了一个运动特征来进行群体建模和实时检测.在此基础上,通过分析大量的运动信息.提出了一种通过自定义的能量函数来评估观测区域内的拥挤程度和异常事件检测的新方法.此方法被用于地铁的视频监控系统中,具有良好的效果.
대옹제지구인군행위적검측대우다충안전임무도지관중요.저개문제포괄2개부분:대옹제정도적고계화대이상적검측.본문정의료일개운동특정래진행군체건모화실시검측.재차기출상,통과분석대량적운동신식.제출료일충통과자정의적능량함수래평고관측구역내적옹제정도화이상사건검측적신방법.차방법피용우지철적시빈감공계통중,구유량호적효과.
Surveillance on pedestrian flows in crowded areas is of significance for various security tasks. This problem involves two parts: evaluation of crowdedness and detection of abnormality. This paper defines a motion feature to deal with crowd modeling and processing in the real-time surveillance. Based on it, a new approach is presented to evaluate the level of crowdedness and monitor abnormal events of the scene according to an analysis on the amount of motion information. The result of a metro subway video surveillance system demonstrated the effectiveness of this method.