Multiple thresholding and subspace based approach for detection and recognition of traffic sign

• Published in: Multimedia tools and applications Vol. 76; no. 5; pp. 6973 - 6991
• Main Authors: Gudigar, Anjan, Chokkadi, Shreesha, Raghavendra, U, Acharya, U Rajendra
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.03.2017; Springer Nature B.V
• Subjects: Algorithms; Ambiguity; Automation; Autonomous vehicles; Cameras; Classification; Computer Communication Networks; Computer Science; Correlation; Data Structures and Information Theory; Discriminant analysis; Drivers; Engineering; Fourier transforms; Machine learning; Multimedia Information Systems; Navigation systems; Neural networks; Pictographs; Position tracking; Principal components analysis; Recognition; Segmentation; Signs; Special Purpose and Application-Based Systems; Street signs; Studies; Support vector machines; Traffic control; Traffic signs; Vision systems; United States > US; Advanced driver assistance system; Computer vision; Multiple thresholds; Support vector machine; Traffic sign recognition
• ISSN: 1380-7501; 1573-7721
• DOI: 10.1007/s11042-016-3321-6

Automatic detection and recognition of traffic sign has been a topic of great interest in advanced driver assistance system. It enhances vehicle and driver safety by providing the condition and state of the road to the drivers. However, visual occlusion and ambiguities in the real-world scenario make the traffic sign recognition a challenging task. This paper presents an Automatic Traffic Sign Detection and Recognition (ATSDR) system, involving three modules: segmentation, detection, and recognition. Region of Interest (ROI) is extracted using multiple thresholding schemes with a novel environmental selection strategy. Then, the traffic sign detection is carried out using correlation computation between log-polar mapped inner regions and the reference template. Finally, recognition is performed using Support Vector Machine (SVM) classifier. Our proposed system achieved a recognition accuracy of 98.3 % and the experimental results demonstrates the robustness of traffic sign detection and recognition in real-world scenario.