Applying Fuzzy Method to Vision-Based Lane Detection and Departure Warning System

• Main Authors: Jyun-Guo Wang, 王峻國
• Other Authors: Cheng-Jian Lin
• Format: Others
• Language: en_US
• Published: 2008
• Online Access: http://ndltd.ncl.edu.tw/handle/07366583064491094661

碩士 === 朝陽科技大學 === 資訊工程系碩士班 === 96 === As the high growth of population of vehicles, the traffic accidents are becoming more and more serious in recent years. In Taiwan, according to the statistics from the Ministry of Transportation and Communications (MOTC, R.O.C.), in the past four yours, there were more than two thousand and five hundred people hurt and died in traffic accidents every year. Most occurrences of the car accidents results from the distraction, inattention for the adjacent cars, and driving fatigue of the driver. As a result, to avoid the driver being in danger as much as possible, an intelligent vision-based system focused on image contents of front camera setting under the rear-view mirror on vehicle is developed about lane detection and lane departure warning in this study. In the thesis of lane detection, in order to enhance lane boundary information and to suitable for various light conditions all day, we combine the self-clustering algorithm (SCA), fuzzy c-mean and fuzzy rule model methods to process the spatial information and Canny algorithms to get good edge detection, so that the lane boundary keeps distinct whether people have seen in the day or night environment. In the thesis of lane departure warning, the system uses instantaneous information from the lane detection to calculate angle relations of the boundaries. The system sends a suitable warning signal to drivers, according to degree different of the departure. The lane detection and departure warning system proposed in this paper have been successfully evaluated on the PC platform of 3.2-GHz CPU with an average frame-rate is up to 14fps. Moreover, this algorithm can maintain stable results in day or night environment of the realistic driving on highway.