DTBSVMs: A New Approach for Road Sign Recognition

The tasks of traffic signs are to notify drivers about the current state of the road and give them other important information for navigation. In this paper, a new approach for detection, tracking and recognition such objects is presented. Road signs are detected using color thresholding, then candidate blobs that have specific criteria are classified based on their geometrical shape and are tracked trough successive frames based on a new similarity measure. Candidate blobs that successfully tracked processed for pictogram classification using Decision-tree-based support vector multi-class classifiers (DTBSVMs). Results show high accuracy with a low false hit rate of this method and its robustness to illumination changes and road sign occlusion or scale changes. Also results indicate that structure of DTB-balanced branches is more efficient in comparison to other SVM classifier structures such as one-against-all and one-against one both in accuracy and speed for pictogram classification.

[1]  Xiaorun Li,et al.  Novel Design of Decision-Tree-Based Support Vector Machines Multi-class Classifier , 2007, ICIC.

[2]  Min Shi,et al.  Support vector machines for traffic signs recognition , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[3]  Koichi Yamada,et al.  Improving the performance of traffic sign detection using blob tracking , 2007, IEICE Electron. Express.

[4]  Syed Hassan Gilani.  Road Sign Recognition based onInvariant Features using SupportVector Machine , 2007 .

[5]  Luis Moreno,et al.  Road traffic sign detection and classification , 1997, IEEE Trans. Ind. Electron..

[6]  John C. Platt,et al.  Fast training of support vector machines using sequential minimal optimization, advances in kernel methods , 1999 .

[8]  A. Zelinsky,et al.  Real-time radial symmetry for speed sign detection , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[9]  Alastair R. Allen,et al.  Using self-organising maps in the detection and recognition of road signs , 2009, Image Vis. Comput..

[10]  Marco Campani,et al.  Robust method for road sign detection and recognition , 1996, Image Vis. Comput..

[11]  Chung-Lin Huang,et al.  Road sign detection and recognition using matching pursuit method , 2001, Image Vis. Comput..

[12]  S. Lafuente-Arroyo,et al.  Traffic sign shape classification evaluation I: SVM using distance to borders , 2005, IEEE Proceedings. Intelligent Vehicles Symposium, 2005..

[13]  Euijin Kim,et al.  Fast and Robust Ellipse Extraction from Complicated Images , 2002 .

[14]  Francisco López-Ferreras,et al.  Road-Sign Detection and Recognition Based on Support Vector Machines , 2007, IEEE Transactions on Intelligent Transportation Systems.

[15]  Visvanathan Ramesh,et al.  A system for traffic sign detection, tracking, and recognition using color, shape, and motion information , 2005, IEEE Proceedings. Intelligent Vehicles Symposium, 2005..

[16]  Arturo de la Escalera,et al.  Traffic sign recognition and analysis for intelligent vehicles , 2003, Image Vis. Comput..

[17]  G.K. Siogkas,et al.  Detection, Tracking and Classification of Road Signs in Adverse Conditions , 2006, MELECON 2006 - 2006 IEEE Mediterranean Electrotechnical Conference.

[18]  Alexandre R. J. François.  Real-Time Multi-Resolution Blob Tracking , 2004 .

[19]  Ulrich H.-G. Kreßel,et al.  Pairwise classification and support vector machines , 1999 .