Person Detection in Video Surveillance

This paper presents a method for motion detection and person recognition from a video stream generated by a surveillance system. The goal of this work is to implement an algorithm that differentiates a person form other types of forms. Motion detection is realized based on the comparison of two frames extracted at a specific time interval from the real-time video stream. Based on the resulted comparison, a binarization algorithm and a region growing algorithm are used to extract all independent moving objects in the motion case. For each extracted region, a series of geometric features are computed to differentiate the form of a person from other detected forms.