基于消失点和主方向估计的道路分割算法RoadSegmentation.pdfVIP

基于消失点和主方向估计的道路分割算法 1 1 1 1 2 田 峥 徐 成 米 超 李仁发 王晓栋 1 （湖南大学信息科学与工程学院 长沙 410082） 2 （厦门理工学院计算机与信息工程系 福建厦门 361024） jt.tianzheng@ （ ） Road Segmentation Based on Vanishing Point and Principal Orientation Estimation 1 1 1 1 2 Tian Zheng , Xu Cheng , Mi Chao , Li Renfa and Wang Xiaodong 1 (College of Information Science and Engineering, Hunan University, Changsha 410082) 2 (Department of Computer and Information Engineering, Xiamen University of Technology, Xiamen, Fujian, 361024) Abstract Most existing vanishing point estimation based road segmentation algorithms demand the vanishing point located inside the image, and they are always time-consuming and cannot effectively overcome the interference of noise which has strong texture features. This paper focuses on these problems, and proposed a road segmentation method based on principal orientation and vanishing point estimation. Firstly, the valid voters were selected by the restrains of road principal orientation. Then a multi-dimension voting scheme was presented, which recorded the voting information in different orientations of candidate vanishing point, and this information was later used to judge whether the vanishing point is located inside image. Finally a boundary fitting strategy based on principal orientation was proposed, which extracted the road region according to the data generated on the multi-dimension voting stage. Quantitative and qualitative experiments show that the proposed road segmentation method is more accurate and faster than the traditional algorithms, and it can still work well when the vanishing point is located outside the image. Key Words road segmentation; vanishing point estimation; principal orientation; multi-dimension voting scheme; boundary fitting 摘 要 现有基于消失点估计的道