DTBSVMs: A New Approach for Road Sign Recognition

Abstract

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.