A Novel Vehicle Reversing Speed Control Based on Obstacle Detection and Sparse Representation

In this paper we present a vehicle safety method for reversing speed control based on obstacle detection and sparse representation. The proposed system consists of three main steps, namely, binocular camera obstacle detection and segmentation, obstacle tracking and recognition, and vehicle reversing speed control algorithm. First of all, a binocular camera system is used to detect obstacles as a vehicle is reversing. Using disparity computation and triangulation, we can get all objects´ distance information in the rear of a vehicle. Second, the framework of particle filter and sparse representation are used to track and identify the main obstacles such as human or animal bodies, vehicles, or any other objects. Finally, the vehicle reversing speed control algorithm, which controls the electronic throttle opening and automatic braking prior to collisions, makes the reversing control safer and more reliable. This system has been field tested on a Dodge sport utility vehicle by which the final performance evaluation demonstrates the validity of the proposed vehicle reversing speed control.