Traffic Sign Detection via Improved Sparse R-CNN for Autonomous Vehicles

• Published in: Journal of advanced transportation Vol. 2022; pp. 1 - 16
• Main Authors: Liang, Tianjiao, Bao, Hong, Pan, Weiguo, Pan, Feng
• Format: Journal Article
• Language: English
• Published: London Hindawi 01.03.2022; John Wiley & Sons, Inc; Wiley
• Subjects: Accuracy; Algorithms; Augmentation; Autonomous vehicles; Candidates; Computer vision; Data acquisition; Data collection; Datasets; Deep learning; Design; Driverless cars; Feature extraction; Methods; Proposals; Semantics; Signs; Traffic control; Traffic signs; Transportation; Vehicles; China
• ISSN: 0197-6729; 2042-3195
• DOI: 10.1155/2022/3825532

Traffic sign detection is an important component of autonomous vehicles. There is still a mismatch problem between the existing detection algorithm and its practical application in real traffic scenes, which is mainly due to the detection accuracy and data acquisition. To tackle this problem, this study proposed an improved sparse R-CNN that integrates coordinate attention block with ResNeSt and builds a feature pyramid to modify the backbone, which enables the extracted features to focus on important information, and improves the detection accuracy. In order to obtain more diverse data, the augmentation method used is specifically designed for complex traffic scenarios, and we also present a traffic sign dataset in this study. For on-road autonomous vehicles, we designed two modules, self-adaption augmentation (SAA) and detection time augmentation (DTA), to improve the robustness of the detection algorithm. The evaluations on traffic sign datasets and on-road testing demonstrate the accuracy and effectiveness of the proposed method.