Research on traffic sign detection algorithm based on deep learning

Due to the respective interests among the main bodies of the supply chain, it is necessary to introduce some mechanisms to coordinate the problem of decrease of detection rate caused by the interconnection of closed-loop traffic signs. This paper proposes a traffic sign detection algorithm based on deep learning. It uses the red, green, and blue (RGB) normalization-based color detection algorithm and regional feature decision criteria to automatically identify the multi-sign interconnection candidate regions and perform edge smoothing and contour tracking for the extracted target regions. It uses deep learner based on global and local curvature characteristics to make traffic sign detection on the extracted contours, and, according to judgment criteria of convexity and concavity of corners as well as matching conditions of detection point pairs, extracts the detection point pairs between the signs from the corners. It seeks the detection lines between detection point pairs and realizes the final detection of signs. The experimental results verify the effectiveness of the proposed algorithm. Compared with the existing sign detection algorithm based on watershed transformation and the improved adaptive detection algorithm, it overcomes the sign over-detection problem and improves the overall performances of the sign detection.