부산대학교 도서관

In this paper, a multi-sensor road detection system in unmanned driving is designed. The system is divided into two parts which are road marking detection and obstacle detection. The road detection part is mainly completed by a Charge-Coupled Device (CCD) vision sensor in the front of the car. After segmentation and binarization of the pictures taken by the camera, the near-field and far-field are respectively fitted to the curve equations of the lane markings. Eight ultrasonic sensors and two CCD sensors are used in obstacle detection. The CCD sensor can obtain the angle between the obstacle and the unmanned vehicle, and the ultrasonic sensor can obtain the distance between the obstacle and the unmanned vehicle, so the position of the obstacle can be determined. This kind of road detection system proposed in this paper can accurately detect road markings and the location of obstacles, which greatly improves the safety of unmanned driving.