D-patches: effective traffic sign detection with occlusion handling

• Published in: IET computer vision Vol. 11; no. 5; pp. 368 - 377
• Main Authors: Rehman, Yawar, Riaz, Irfan, Fan, Xue, Shin, Hyunchul
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.08.2017; Wiley
• Subjects: advanced driver assistance systems; confidence-score; d-patches; discriminative patches; driver information systems; full object templates; German TSD benchmark; hypothesis generation scheme; Korean TSD dataset; KTSD dataset; object detection; occlusion handling capability; redundant-detections; Research Article; traffic sign detection framework; traffic signs; true positive candidate; TSD framework; hypothesis generation scheme; true positive candidate; advanced driver assistance systems; discriminative patches; Korean TSD dataset; object detection; German TSD benchmark; redundant-detections; d-patches; KTSD dataset; traffic sign detection framework; TSD framework; driver information systems; occlusion handling capability; confidence-score; traffic signs; full object templates
• DOI: 10.1049/iet-cvi.2016.0303
• ISSN: 1751-9632; 1751-9640

In advanced driver assistance systems, accurate detection of traffic signs plays an important role in extracting information about the road ahead. However, traffic signs are persistently occluded by vehicles, trees, and other structures on road. Performance of a detector decreases drastically when occlusions are encountered especially when it is trained using full object templates. Therefore, we propose a new method called discriminative patches (d-patches), which is a traffic sign detection (TSD) framework with occlusion handling capability. D-patches are those regions of an object that possess the most discriminative features than their surroundings. They are mined during training and are used for classification instead of the full object templates. Furthermore, we observe that the distribution of redundant-detections around a true-positive is different from that around a false-positive. Based on this observation, we propose a novel hypothesis generation scheme that uses a voting and penalisation mechanism to accurately select a true-positive candidate. We also introduce a new Korean TSD (KTSD) dataset with several evaluation settings to facilitate detector's evaluation under different conditions. The proposed method achieves 100% detection accuracy on German TSD benchmark and achieves 4.0% better detection accuracy, when compared with other well-known methods (under partially occluded settings), on KTSD dataset.