Efficient complete intelligent video surveillance system has become the urgent needs in today′s so ciety.For crowd gathering and running behavior detection in public places,a method based on distributive entr opy and average speed of crowd movement is proposed.On the one hand,according to the spatial distribution of th e foreground pixels,the distribution entropy is defined and used to measure the concentration of the crowd and implement the det ection of the gathered crowd.On the other hand,the motion vector of the feature points between two consecutive frames in the video sequence is gained by tracking the feature points on the image using the optical flow method,which is used to estimate the crowd′s speed and detect the crowd running behavior.This method does not need to a single pede strian segmentation as well as the training sample.To test the performance of this algorithm,videos with different scenes an d different crowed densities are used in the experiments.Experimental results show that our method can quickly and accur ately detect crowd abnormal behaviors.