A Study on Real-Time Detection Method of Lane and Vehicle for Lane Change Assistant System Using Vision System on Highway

In this work, we introduce an approach to detect information about lane and vehicle for the driver assistance system, or the lane change assistant system. Most previous research works could only detect the lanes or vehicles separately. However, the combination of lane information and vehicle information is able to support the driver assistance system, or the lane change assistant system, and to improve the reliability of results. For the lane change assistant system (LCAS), it must detect the frontal lanes and discover the vehicles around a test vehicle. Therefore, in this study, a vision system is utilized including three cameras, two of them are under the right and left wing mirrors, the left one is equipped on the windscreen of the test vehicle. The images from the cameras are used to detect three lanes, and detect vehicles. In the lane detection, the line detection is used. For the vehicle detection, we combine the horizontal edge filter,the Otsu's thresholding, and the vertical edge. The horizontal edge filter and the Otsu's thresholding are used to detect the vehicle candidates, then the vertical edge is used to verify the vehicle candidates.Moreover, Kalman filter is used to track the detected vehicle. Finally, the relative speed between the detected vehicle and the test is computed in this work. The proposed algorithm works in an average of 43 ms for each frame with resolution on a 3.30 GHz Intel CPU. The system was tested on the highway in Korea.