Automatic Signboard Recognition in Low Quality Night Images

TL;DR

This paper presents a two-step approach combining image enhancement with a modified MIRNet and traffic sign recognition with Yolov4, significantly improving detection accuracy in low-quality night images for autonomous driving.

Contribution

It introduces a novel pipeline that enhances low-quality traffic sign images before recognition, achieving state-of-the-art accuracy in challenging conditions.

Findings

Achieved 96.75% mAP@0.5 on GTSRB dataset.

Improved detection accuracy by 5.40% in low-quality images.

Attained 100% mAP@0.5 on GTSDB dataset.

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 addressed the challenges of recognizing traffic signs from images captured in low light, noise, and blurriness. To achieve this goal, a two-step methodology has been employed. The first step involves enhancing traffic sign images by applying a modified MIRNet model and producing enhanced images. In the second step, the Yolov4 model recognizes the traffic signs in an unconstrained environment. The proposed method has achieved 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.