Detecting Irregularities by Image Contour Based on Fuzzy Neural Network

Visual analysis of human motion in video sequences has attached more and more attention to computer visions in recent years. In order to indicate pedestrian movement in Intelligent Monitoring System, a Euclidean distance based on centroid method is proposed. And then according to the movement of body a set of standard images contour are made. All matrixes which represent human silhouette are normalized using affine transformation, which cuts computational cost. The difference between two matrixes is regard as fuzzy function. Fuzzy neural network is proposed to infer abnormal behavior of the walker. First of all, a four layer fuzzy neural network is presented. And then Fuzzy C-means clustering algorithm is used to calculate the number of hidden layer nodes. Finally the degree of the anomaly is resulted from the fuzzy membership of the two matrixes difference. Fuzzy discriminant can detect irregularities and implements initiative analysis to body behavior. The results show that the new algorithm has better performance.