Detecting Pedestrian Abnormal Behavior Based on Fuzzy Neural Network
Recently visual analysis of human motion in video sequences has attracted more and more attention to computer visions.In order to indicate the pedestrian movement in Intelligent Security Monitoring System,an articulated model of human is presented.According to the contour angle movement of body’s major organs,a fuzzy function is designed.Fuzzy neural network is proposed to infer abnormal behaviour of the walker.First of all,a four layer fuzzy neural network is presented.And then FCM (Fuzzy C-means) clustering algorithm is used to calculate the number of hidden layer nodes.Finally the overall degree of the anomaly is resulted from the fuzzy membership of the pedestrian’s organ.In the realization of the system a combined method of centroid and fuzzy discriminant is presented.Fuzzy discriminant can detect irregularities and implements initiative analysis of body’s behaviours in visual surveillance.Therefore,we can recognize some abnormal behaviors and then alarm,so that it becomes intelligible in nature.The results show that the new algorithm has better performance.
Intelligent Monitor Fuzzy Neural Network Articulated Model Silhouette Fuzzy C-Means Centroid
Jun Zhang Zhijing Liu Hong Zhou
School of Computer Science and Technology,Xidian University,Xi an,710071,China
国际会议
International Conference on Modelling,Identification and Control(模拟、鉴定、控制国际会议)
上海
英文
2008-06-29（万方平台首次上网日期，不代表论文的发表时间）