Automatic Signboard Recognition in Low Quality Night Images

Abstract

An essential requirement for driver assistance systems and autonomous driving technology is implementing a robust system for detecting and recognizing traffic signs. This system enables the vehicle to autonomously analyze the environment and make appropriate decisions regarding its movement, even when operating at higher frame rates. However, traffic sign images captured in inadequate lighting and adverse weather conditions are poorly visible, blurred, faded, and damaged. Consequently, the recognition of traffic signs in such circumstances becomes inherently difficult. This paper addresses the challenges of recognizing traffic signs from images captured in low light, noise, and blurriness. To achieve this goal, a two-step methodology is employed. The first step involves enhancing traffic sign images by applying a modified MIRNet model. In the second step, the YOLOv4 model recognizes traffic signs from enhanced images. The proposed method has achieved a 5.40% increment in mAP@0.5 for low-quality images on YOLOv4. The overall mAP@0.5 of 96.75% has been achieved on the GTSRB dataset. It has also attained mAP@0.5 of 100% on the GTSDB dataset for the broad categories, comparable with the state-of-the-art work. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.