摘要: 为了解决复杂光照下的缩微道路车道线检测问题,提出了一种适用于复杂光照下的缩微道路车道线检测方法。首先运用朴素贝叶斯对不同光照下的车道图像进行分类,然后对分类后的车道图像采取相应的图像处理方法,最后运用改进的大津法和改进概率霍夫变换来检测车道线。对多段不同光照模式下的车道图像进行的仿真实验表明,该方法对缩微道路车道线检测的成功率达到95.5%,具有很强的鲁棒性和抗干扰能力。
[1] Wang Guo-yin,Chen Qiao-song,Wang Jin.Discussion on the Intelligent Vehicle Technologies[J].Computer Science,2012,39(5):1-8 [2] Lakhoyia A,Golconda S,Maida A,et al.CajunBot:Architecture and Algorithms[M].Springer Tracts in Advanced Robotics,2007,36:245-280 [3] Bruce J,Balch T,Veloso M.Fast and Inexpensive Color ImageSegmentation for Interactive Robots[J].IEEE/RSJ InternationalConference on Intelligent Robots and Systems,2000(10):2061-2066 [4] Ji Xue-jiao.Vision-based Autonomous Driving in Miniature Traf-fic Environment[D].Beijing:Tsinghua University,2011 [5] Ma Yu-lin,Yan Xin-ping,Wu qing.Research on Intelligent Vehicle Platoon Driving Simulation Experiment System under the Coordination between Vehicle and Highway[J].Joural of Computers,2010,5(11):1767-1768 [6] Chu Wei-dong,Wang Guo-yi,Wang Jin.Lane Detection in Micro-Traffic Environment[J].Journal of Frontiers of Computer Science and Technology,2012,6(10):921-926 [7] Zhao Jia-jia.The Design of Illumination Classifier for Lanes[D].Jilin:Jilin University,2007 [8] Huang Zhi-kai,Liu De-hui.Segmentation of Color Image Using EM algorithm in HSV Color Space[C]∥Proceedings of the 2007International Conference on Information Acquisition,2007.Jeju,Korea,2007:316-319 [9] Bradski G,Kaebler A.Learning OpenCV Computer Vision with the OpenCV Library[M].O’Reilly Media,2008 [10] 贾永红.计算机图像处理与分析[M].武汉:武汉大学出版社,2001 [11] Otsu N.A threshold selection method from gray-level histo-gram.IEEE Transactions on Systems[J].Man and Cybernetics,1979,9(1):62-66 [12] Wang Zhi,He Sai-xian.An Adaptive Edge-detection MethodBased on Canny Algorithm[J].Journal of Image and Graphics,2004,9(8):957-961 [13] Galamhos C,Matas J,Kittler J.Progressive Probablistic Hough Transform for line detection[C]∥Proceedings of Computer Vision and Pattern Recognition.1999:23-25 [14] http://cs.cqupt.edu.cn/MemberReadNews.asp?NewsID=113-99&SpecialID=0 |
No related articles found! |
|