Alexander Ioffe

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.

A REAL-TIME DETECTION ALGORITHM FOR VISION-BASED PEDESTRIAN PROTECTION

This paper discusses the robust, real-time detection of stationary and moving pedestrians utilizing a single car-mounted monochrome camera. First, the system detects potential pedestrians above the ground plane by combining conventional Inverse Perspective Mapping (IPM)-based obstacle detection with the vertical 1D profile evaluation of the IPM detection result. Usage of the vertical profile increases the robustness of detection in low-contrast images as well as the detection of distant pedestrians significantly. A fast digital image stabilization algorithm is used to compensate for erroneous detections whenever the flat ground plane assumption is an inaccurate model of the road surface. Finally, a low-level pedestrian-oriented segmentation and fast symmetry search on the leg region of pedestrians is also presented. A novel approach termed Pedestrian Detection Strip (PDS) is used to improve the calculation time by a factor of six compared to conventional approaches.