Vision-based pedestrian detection -reliable pedestrian candidate detection by combining IPM and a 1D profile

This article presents the improvement of an Inverse Perspective Mapping (IPM) based obstacle detection algorithm and its utilization in a pedestrian candidate detection module of our vision based pedestrian detection system. A vertical 1D profile of the IPM detection on the region of interest termed Pedestrian Detection Strip (PDS) is created first and the candidates are chosen by applying a threshold on the profile. The usage of the vertical profile increases the robustness of the detection on low contrast images as well as distant pedestrians significantly. A low level pedestrian oriented segmentation and fast symmetry search on the leg region of pedestrians is also presented.