Kernel Based Automatic Traffic Sign Detection and Recognition Using SVM
Traffic sign detection and recognition is an important issue of research recently. Road and traffic signs have been designed according to stringent regulations using special shapes and colors, very different from the natural environment, which makes them easily recognizable by drivers. The human visual perception abilities depend on the individual’s physical and mental conditions. In certain conditions, these abilities can be affected by many factors such as fatigue, and observatory skills. Detection of regulatory road signs in outdoor images from moving vehicles will help the driver to take the right decision in good time, which means fewer accidents, less pollution, and better safety. In automatic traffic-sign maintenance and in a visual driver-assistance system, road-sign detection and recognition are two of the most important functions. This paper presents automatic regulatory road-sign detection with the help of distance to borders (DtBs) and distance from centers (DfCs) feature vectors. Our system is able to detect and recognize regulatory road signs. The proposed recognition system is based on the generalization properties of SVMs. The system consists of following processes: segmentation according to the color of the pixel, traffic-sign detection by shape classification using linear SVM and content recognition based on Gaussian-kernel SVM. A result shows a high success rate and a very low amount of false positives in the final recognition stage.
KeywordsDistance to Borders Distance from Centers Gaussian-kernel Regulatory Support Vector Machines (SVMs) Traffic Sign Recognition
Unable to display preview. Download preview PDF.
- 1.Fang, C.-Y., Chen, S.-W., Fuh, C.-S.: Road-sign detection and tracking. IEEE Transactions on Vehicular Technology, 52–57 (September 2003)Google Scholar
- 2.Loy, G., Barnes, N.: Fast shape-based road sign detection for a driver assistance system. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2004, September 2- October, vol. 1, pp. 70–75 (2004)Google Scholar
- 3.Fleyeh, H.: Road and traffic sign color detection and segmentation-a fuzzy approach (2005)Google Scholar
- 4.Miura, J., Kanda, T., Shirai, Y.: An active vision system for real-time traffic sign recognition. In: Intelligent Transportation Systems, pp. 52–57. IEEE (2000)Google Scholar
- 7.Cristianini, N., Shame-Taylor, J.: Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge Univ. Press, Cambridge (2000)Google Scholar
- 8.Chang, C., Lin, C.: LIBSVM: A Library for Support Vector Machines (2001) (Online) http://www.csie.ntu.edu.tw/~cjlin/libsvm
- 10.Bascon, S.M., et al.: Road Sign Detection and Recognition Based on Support Vector Machines. IEEE Transactions on Intelligent Transportation Systems 8(2) (June 2007)Google Scholar
- 11.Image Database, http://roadanalysis.uah.es/Documentos
- 12.Lafuente Arroyo, S., Gil Jimenez, P., Maldonado Bascon, R., Lopez Ferreras, F., Maldonado Bascon, S.: Traffic Sign Shape Classification Evaluation I: SVM using Distance to Borders. In: Proceedings of IEEE Intelligent Vehicles Symposium, Las Vegas, pp. 557–562 (June 2005)Google Scholar