Discriminant Splitting of Regions in Traffic Sign Recognition
- 1.3k Downloads
Mining discriminative spatial patterns in image data is a subject of interest in traffic sign recognition. In this paper, we use an approach for detecting spatial regions that are highly discriminative. The main idea is to search the normalized size blobs for discriminative regions by adaptively partitioning the space into progressively smaller sub-regions. Thus, each cluster of signs is characterized by an unique region pattern which consists of homogeneous and discriminant 2-D regions. The mean intensities of these regions are used as features. To evaluate the discriminative power of the attributes corresponding to detected regions, we performed classification experiments using a classifier based on Support Vector Machines. The proposed method has been tested in a real traffic sign database. Results demonstrate that the method can achieve a considerable reduction of features with respect to extraction from raw images while maintaining accurate.
Keywordsfeature extraction adaptive partitioning traffic sign classification
Unable to display preview. Download preview PDF.
- 2.Hsien, J.C., Liou, Y.S., Chen, S.Y.: Road sign detection and recognition using hidden Markov model. Asian Journal of Health and Information Sciences 1, 85–100 (2006)Google Scholar
- 4.Liu, Y., Ikenaga, T., Goto, S.: Geometrical, physical and text/symbol analysis based approach of traffic sign detection system. In: Proceedings of the IEEE Intelligent Vehicle Symposium, pp. 238–243 (2006)Google Scholar
- 8.Nguwi, Y.Y., Cho, S.Y.: Two-tier self-organizing visual model for road sign recognition. In: Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN), pp. 794–799 (2008)Google Scholar
- 10.Shaposhnikov, W.D., Shaposhnikov, D.G., Lubov, N., Golovan, E.V., Shevtsova, A.: Road sign recognition by single positioning of space-variant sensor window. In: Proceedings of the 15th International Conference on Vision Interface (2002)Google Scholar
- 11.Stallkamp, J., Schlipsing, M., Salmen, J., Igel, C.: The german traffic sign recognition benchmark: a multi-class classification competition. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN), pp. 1453–1460 (2011)Google Scholar
- 12.Timofte, R., Zimmermann, K., Van Gool, L.: Multi-view traffic sign detection, recognition and 3D localisation. Journal of Machine Vision and Applications, 1–15 (2011)Google Scholar