摘要
提出了一种基于行走轨迹的异常行为识别方法,运用背景减除法与时间差分法加权平均的目标检测法对运动人体进行检测,通过对人的行走轨迹的跟踪与记录来判断某人是否可疑,轨迹出现闭合曲线和螺旋线说明有徘徊行为,即可疑予以报警。实验表明,该方法具有一定的可靠性和鲁棒性,实时性较强。
An abnormal behavior recognition method with walking trajectory is proposed,the detection is carried out for moving body by using an object detection method averaged by background subtraction method and time difference method,whether someone is suspicious or not is determined by tracking and record of walking trajectory,if the trajectory is a close curve,then the police will receive the signal.The experimental results show that this method has a certain reliability and robustness,and strong real time performance.
出处
《辽宁科技大学学报》
CAS
2010年第5期453-455,共3页
Journal of University of Science and Technology Liaoning
关键词
行走轨迹
智能监控
异常行为
视频分析
walking trajectory
intelligent monitoring
abnormal behavior
video analysis