Robust vehicle detection and tracking method for Blind Spot Detection System by using vision sensors

摘要

This paper presents a method to detect the present vehicles from side and rear for BSDS(Blind Spot Detection System) with vision system. Because the real image acquired during car driving has a lot of information to exam the target vehicle, background image, and the noises such as lighting and shading, it is hard to extract only the target vehicle for the background image with satisfied robustness. In this paper, the target vehicle is detected by repetitive image processing such as sobel and morphological operations and a Kalman filter is also designed to cancel the background image and prevent the misreading of the target image. Compared to previous researches, the proposed method can get an image processing with much improved speed and robustness. Various experiments were performed on the highway driving situations to evaluate the performance of the proposed algorithm.