Real-Time Pedestrian Detection Using Support Vector Machines

In this paper, we present a real-time pedestrian detection system in outdoor environments. It is necessary for pedestrian detection to implement obstacle and face detection which are major parts of a walking guidance system. It can discriminate pedestrian from obstacles, and extract candidate regions for face detection and recognition. For pedestrian detection, we have used stereo-based segmentation and SVM (Support Vector Machines), which has superior classification performance in binary classification case (e.g. object detection). We have used vertical edges, which can extracted from arms, legs, and the body of pedestrians, as features for training and detection. The experiments on a large number of street scenes demonstrate the effectiveness of the proposed for pedestrian detection system.