A General Framework for a Robust Human Detection in Images Sequences

We present in this paper a human detection system for the analysis of video sequences. We perform first a foreground detection with a Gaussian background model. A tracking step based on connected components analysis combined with feature points tracking allows to collect information on 2D displacements of moving objects in the image plane and so to improve the performance of our classifier. A classification based on a cascade of boosted classifiers is used for the recognition. Moreover, we present the results of two comparative studies which concern the background subtraction and the classification steps. Algorithms from the state of the art are compared in order to validate our technical choices. We finally present some experimental results showing the efficiency of the proposed algorithm.