This paper proposes a robust driving recorder based on-road pedestrian tracking system, which effectively integrates Visual Simultaneous Localization And Mapping (V-SLAM), pedestrian detection, ground plane estimation, and kernel-based tracking techniques. The proposed system systematically detects the pedestrians from recorded video frames and tracks the pedestrians in the V-SLAM inferred 3-D space via a tracking-by-detection scheme. In order to efficiently associate the detected pedestrian frame-by-frame, we propose a novel tracking framework, combining the Constrained Multiple-Kernel (CMK) tracking and the estimated 3-D (depth) information, to globally optimize the data association between consecutive frames. By taking advantage of the appearance model and 3-D information, the proposed system not only achieves high effectiveness but also well handles occlusion in the tracking. Experimental results show the favorable performance of the proposed system which efficiently tracks on-road pedestrian in a moving camera equipped on a driving vehicle.
Driving recorder based on-road pedestrian tracking using visual SLAM and Constrained Multiple-Kernel
01.10.2014
892912 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Ground-Moving-Platform-Based Human Tracking Using Visual SLAM and Constrained Multiple Kernels
Online Contents | 2016
|Pedestrian Collaborative Inertial-Only SLAM
British Library Conference Proceedings | 2021
|