A Novel Obstacle Detection and Tracking System Using Fisheye Vision

The large blind region behind the large body of a truck is the primary reason for reversing collisions. However, there are few truck reversing auxiliary approaches to avoid reversing accidents. In this paper, we present a novel heavy-duty truck safety approach for reversing based on pedestrian detection and obstacle tracking using fisheye stereo vision. The proposed system contains four primary steps: fisheye camera calibration and image matching, distortion correction and pedestrian identification, obstacle tracking with an improved CMT algorithm, and heavy-duty truck speed control method.