The recognition and prediction of people's activities from videos are major concerns in the field of computer vision. The main objective of this article is to propose an adaptive global algorithm that analyzes human behavior from video. This problem is also called video content analysis or VCA. This analysis is performed in outdoor or indoor environments. The video scene can be depending on the number of people present, is characterized by the presence of only one person at a time in the video. We are interested in scenes containing a large number of people. This is called crowd scenes where we will address the problems of motion pattern extraction in crowd event detection. To achieve our goals, we propose an approach based on scheme analysis of a new adaptive architecture and hybrid technique detection movement. The first stage consists of acquiring the image from camera recordings. After several successive stages are applied, the active detection of movement by a hybrid technique, until classification by fuzzy logic is preformed, which is the last phase intervening in the process of detection of anomalies based on the increase in the speed of the reaction of safety services in order to carry out a precise analysis and detect events in real time. In order to provide the users with concrete results on the analysis of human behavior, result experimentation on datasets have validated our approaches, with very satisfying results compared to the other state-of-the-art approaches.