Abstract:
Low visibility is more likely to cause accidents on the highway. An accurate visibility measurement system can greatly reduce these accidents and improve driving safety. However, some existing visibility measurement systems are very expensive and cannot send the visibility information to drivers in real time. Hence, this paper proposes a real-time low visibility auxiliary driving system based on dark channel prior. This proposed system will run on the on-board camera, which may reduce the cost of the measurement system and can make drivers obtain the visibility information in real time. Firstly, the transmission that is obtained through dark channel prior is utilized to judge the visibility condition. Secondly, a region growing algorithm is given to determine the measurement bandwidth in the transmission image. And then, the measurement line in this bandwidth is obtained via the gradient variation of transmission. Thirdly, according to the highway lane line in the transmission image, an improved real time automatic calibration method is proposed to estimate the visibility distance that will be sent to the driver. Finally, experimental results show that the proposed highway visibility measurement system can effectively estimate the real-time highway visibility distance in the low visibility weather.