Performance enhancement techniques for traffic sign recognition using a deep neural network

An advanced traffic sign recognition (ATSR) system using novel pre-processing techniques and optimization techniques has been proposed. During the pre-processing of input road images, color contrasts are enhanced and edges are made clearer, for easier detection of small-sized traffic signs. YOLOv3 has been modified to build our traffic sign detector, since it is an efficient and effective deep neural network. In this YOLOv3 modifications, grid optimization and anchor box optimization were done to optimize the detection performance on small-sized traffic signs. We trained the system on our traffic sign dataset and tested the recognition performance using the Mean Average Precision (MAP) on the Korean Traffic Sign Dataset (KTSD) and German Traffic Sign Detection Benchmark (GTSDB). We used the bisection method for selecting the optimum threshold of confidence score to reduce false predictions. Our ATSR system is capable of recognizing Prohibitory, Mandatory, and Danger class traffic signs from road images. ATSR can detect small-sized traffic signs accurately along with big-sized traffic signs. It shows the best recognition performance of 98.15% on the challenging KTSD (the previously reported best performance was 90.07%) and 100% on the GTSDB. Result comparisons show that ATSR significantly outperforms ITSR, TS detector, YOLOv3, and D-patches, on KTSD.