A DSP-Based Lane Departure Warning System

A DSP-Based adaptive lane departure warning system (ALDWS) is presented in this paper. The system can be applied in highways, tunnels and urban roadways, and works well in sunny, cloudy, and rainy conditions in day or night. Different types of lane markings can be detected, such as solid, dashed, double, etc., by the proposed vision-based detection algorithm. The DSP image processor on ALDWS works with operating frequency of 600MHz and the lane marking detection speed can be more than 35 frames per second with QVGA size. The presented fast adaptive lane detection algorithm is efficient and robust at both day and night. A modified lane model is proposed to increase the accuracy of detection. Moreover, an automatic calibration between the lane width and the road inclination is considered and adjusted on-line. ALDWS is equipped on the smart car, TAIWAN iTS-1, and has been successfully verified for hundreds of kilometers on Highway No.3 and Expressway No.68 in Taiwan. Key-Words: Lane departure warning, vision-based detection