|Table of Contents|

Unsupervised Road Scene Segmentation Method


Research Field:
Publishing date:


Unsupervised Road Scene Segmentation Method
ZHANG Hao-fengYE Qiao-linZHAO Chun-xiaYANG Jing-yu
School of Computer Science and Technology,NUST,Nanjing 210094,China
road scene segmentation XYZ color space Gabor texture K-means clustering graph cut
To solve the problems that lots of training samples are needed in the road scene segmentation and the changes of different roads cause the segmentation error easily,this paper proposes an unsupervised road scene segmentation method.First,K-means clustering method is applied to the first image for its initial segmentation;Second,graph cut optimization algorithm is used to minimize the total image energy to get the optimal segmentation.With the computed class centers of the segmented image,the next image is also optimized by graph cut.Experimental results show that this method can segment the road scene quickly without quantities of training samples,and can keep efficient in changing of different road types.


[1] Sparbert J,Dietmayer K,Streller D. Lane detection and street type classification using laser range images[A]. IEEE Proceedings on Intelligent Transportation Systems[C]. Oakland,USA: IEEE, 2001: 454-459.
[2] Ma Bing,Lakshmanan S,Hero A O. Simultaneous detection of lane and pavement boundaries using modelbased multi-sensor fusion[J]. IEEE Transactions on Intelligent Transportation Systems,2000,1 ( 3 ) : 135 -147.
[3] Bertozzi M,Broggi A. Gold: A parallel real-time stereo vision system for generic obstacle and lane detection [J]. IEEE Transactions on Image Processing,1998,7 ( 1) : 62-81.
[4] Southhall J,Taylor C. Stochastic road shape estimation [A]. International Conference on Computer Vision [C]. Vancouver,B C,Canada: IEEE, 2001: 205-212.
[5] Yu Bin,Jain A K. Lane boundary detection using amultiresolution hough transform[A]. International Conference on Image Processing[C]. Santa Barbara,CA, USA: IEEE, 1997: 748-751.
[6] Freeman W,Adelson E. The design and use of steerable filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13( 9) : 891-906.[7] Wang Yue,Teoh E K,Shen Dinggang. Lane detection and tracking using b-snake [J]. Image and Vision Computing, 2004, 22( 4) : 269-280.
[8] 石磊,赵春霞,杨静宇. 一种基于粒子群的道路检测新算法[J]. 数据采集与处理, 2010, 45( 3) : 384-388.
[9] 张莉,谭新莲,周文晖,等. 一种改进的均值偏移算法及其应用[J]. 南京理工大学学报,2007,32( 1) : 86-90.
[10] Alon Y,Ferencz A,Shashua A. Off-road path following using region classification and geometric projection constraints[A]. IEEE Proceedings on Computer Vision and Pattern Recognition[C]. Jerusalem, Israel: IEEE, 2006: 689-696.
[11] Lookingbill A,Rogers J,Lieb D,et al. Reverse optical flow for self-supervised adaptive autonomous robot navigation [J]. International Journal of Computer Vision, 2007, 74( 3) : 287-302.
[12] Broggi A,Caraffi C,Fedriga R I,et al. Obstacle detection with stereo vision for off-road vehicle navigation [A]. Proceedings of IEEE International Workshop on Machine Vision for Intelligent Vehicles[C]. San Diego,CA,USA: IEEE, 2005: 65-65.
[13] Manduchi R,Castano A,Talukder A, et al. Obstacle detection and terrain classification for autonomous off-road navigation[J]. Autonomous Robots,2005,18 ( 1) : 81 -102.
[14] 周文晖,林莉莉,武二勇. 融合图切割和聚类算法的鲁棒自适应道路跟踪[J]. 仪器仪表学报, 2009, 30( 11) : 2366-2371.
[15] 韩守东,赵勇,陶文兵,等. 基于高斯超像素的快速 Graph Cuts 图像分割方法[J]. 自动化学报, 2011, 37( 1) : 11-20.
[16] Colantoni P. ColorSpace 1. 11[OL]. http: / /colantoni. nerim. net /download /ColorSpace-1. 1. 1. exe, 2010.
[17] Zhang Jianguo,Tan Tieniu,Ma Li. Invariant texture segmentation via circular gabor filter[A]. Proceedings of the 16th IAPR International Conference on Pattern Recognition[C]. Quebec,Canada: IEEE, 2002: 901-904.
[18] Boykov Y,Kolmogorov V. An experimental comparison of min-cut /max-flow algorithms for energy minimization in vision[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26( 9) : 1124-1137.


Last Update: 2012-10-12