LIDAR and vision based pedestrian detection and tracking system

Abstract

Pedestrian detection is a key technology in autonomous driving perception system. Although the current vision-based pedestrian detection has obtained very good detection performance, the camera is sensitive to light and shadow. In addition, it is unable to provide precise location information, which is difficult to address autonomous driving problem. To tackle these issues, a LIDAR subsystem is applied here in order to extract object structure features and train an SVM classifier. Additionally, the association of object detections can be solved in the 3D world coordinates by the LIDAR system. In the proposed fusion framework, LIDAR-based pedestrian segmentation is regarded as weak classifier, vision-based pedestrian classifier as strong classifier, and the final detection is given by fusing multiple sensor information in multiple frames together with a voting strategy. Experimental results highlight the performance of the proposed pedestrian detection and tracking system as well as the related sensor data combination strategies.