{"title":"An Efficient Obstacle Detection Algorithm Using Colour and Texture","authors":"Chau Nguyen Viet, Ian Marshall","volume":36,"journal":"International Journal of Computer and Information Engineering","pagesStart":2756,"pagesEnd":2762,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/1945","abstract":"
This paper presents a new classification algorithm using colour and texture for obstacle detection. Colour information is computationally cheap to learn and process. However in many cases, colour alone does not provide enough information for classification. Texture information can improve classification performance but usually comes at an expensive cost. Our algorithm uses both colour and texture features but texture is only needed when colour is unreliable. During the training stage, texture features are learned specifically to improve the performance of a colour classifier. The algorithm learns a set of simple texture features and only the most effective features are used in the classification stage. Therefore our algorithm has a very good classification rate while is still fast enough to run on a limited computer platform. The proposed algorithm was tested with a challenging outdoor image set. Test result shows the algorithm achieves a much better trade-off between classification performance and efficiency than a typical colour classifier.<\/p>\r\n","references":"[1] P. E. Richard O.Duda and D. G.Stork, Pattern Classification. Inter-\r\nScience, 2001.\r\n[2] I. Ulrich and I. R. NourbakhshLo, \"Appearance-based obstacle detection\r\nwith monocular color vision,\" in AAAI\/IAAI, 2000, pp. 866-871.\r\n[3] M. Sridharan and P. Stone, \"Color learning and illumination invariance\r\non mobile robots: A survey,\" Robotics and Autonomous Systems, vol. 57,\r\nno. 6-7, pp. 629 - 644, 2009.\r\n[4] L. Lorigo, R. Brooks, and W. Grimsou, \"Visually-guided obstacle avoidance\r\nin unstructured environments,\" in Intelligent Robots and Systems,\r\n1997. IROS -97., Proceedings of the 1997 IEEE\/RSJ International\r\nConference on, vol. 1, Grenoble, France, Sep. 1997, pp. 373-379.\r\n[5] T. S. team, \"Stanley : The robot that won the darpa grand challenge,\"\r\nStanford University, Tech. Rep., 2005.\r\n[6] S. Belongie, C. Carson, H. Greenspan, and J. Malik, \"Color- and texturebased\r\nimage segmentation using em and its application to content-based\r\nimage retrieval,\" iccv, vol. 00, p. 675, 1998.\r\n[7] Y.-C. Cheng and S.-Y. Chen, \"Image classification using color, texture\r\nand regions,\" Image and Vision Computing, vol. 21, no. 9, pp. 759-776,\r\nSep. 2003.\r\n[8] D. Cremers, M. Rousson, and R. Deriche, \"A review of statistical\r\napproaches to level set segmentation: Integrating color, texture, motion\r\nand shape,\" International Journal of Computer Vision, vol. 72, no. 2,\r\npp. 195-215, Apr. 2007.\r\n[9] M. Shneier, T. Chang, T. Hong, W. Shackleford, R. Bostelman, and J. Albus,\r\n\"Learning traversability models for autonomous mobile vehicles,\"\r\nAutonomous Robots, vol. 24, no. 1, pp. 69-86, Jan. 2008.\r\n[10] J. Michels, A. Saxena, and A. Y. Ng, \"High speed obstacle avoidance\r\nusing monocular vision and reinforcement learning,\" in ICML -05:\r\nProceedings of the 22nd international conference on Machine learning.\r\nNew York, NY, USA: ACM Press, 2005, pp. 593-600.\r\n[11] R. Haralick, \"Statistical and structural approaches to texture,\" Proceedings\r\nof the IEEE, vol. 67, no. 5, pp. 786-804, May 1979.\r\n[12] T. P. Weldon, W. E. Higgins, and D. F. Dunn, \"Efficient gabor filter\r\ndesign for texture segmentation,\" Pattern Recognition, vol. 29, no. 12,\r\npp. 2005-2015, Dec. 1996.\r\n[13] M. Unser, \"Texture classification and segmentation using wavelet\r\nframes,\" Image Processing, IEEE Transactions on, vol. 4, no. 11, pp.\r\n1549-1560, Nov 1995.\r\n[14] T. Ojala, M. Pietikinen, and D. Harwood, \"A comparative study of\r\ntexture measures with classification based on featured distributions,\"\r\nPattern Recognition, vol. 29, no. 1, pp. 51-59, Jan. 1996.\r\n[15] S. Grigorescu, N. Petkov, and P. Kruizinga, \"Comparison of texture\r\nfeatures based on gabor filters,\" Image Processing, IEEE Transactions\r\non, vol. 11, no. 10, pp. 1160-1167, Oct 2002.\r\n[16] T. Randen and J. Husoy, \"Filtering for texture classification: a comparative\r\nstudy,\" Pattern Analysis and Machine Intelligence, IEEE Transactions\r\non, vol. 21, no. 4, pp. 291-310, Apr 1999.\r\n[17] T. Leung and J. Malik, \"Representing and recognizing the visual\r\nappearance of materials using three-dimensional textons,\" Int. J. Comput.\r\nVision, vol. 43, no. 1, pp. 29-44, 2001.\r\n[18] \"http:\/\/www.gumstix.org.\"","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 36, 2009"}