DFR-TSD: A Deep Learning Based Framework for Robust Traffic Sign Detection Under Challenging Weather Conditions

TL;DR

This paper introduces a CNN-based framework for traffic sign detection that remains robust under challenging weather conditions by using targeted image enhancement and challenge classification.

Contribution

It proposes a novel modular CNN framework with a challenge classifier and an enhancement network focused on traffic sign regions, improving detection accuracy in adverse conditions.

Findings

Achieved 91.1% precision and 70.71% recall, outperforming benchmarks.

Outperformed state-of-the-art detectors like Faster-RCNN and R-FCN.

Demonstrated robustness of the approach on the CURE-TSD dataset.

Abstract

Robust traffic sign detection and recognition (TSDR) is of paramount importance for the successful realization of autonomous vehicle technology. The importance of this task has led to a vast amount of research efforts and many promising methods have been proposed in the existing literature. However, the SOTA (SOTA) methods have been evaluated on clean and challenge-free datasets and overlooked the performance deterioration associated with different challenging conditions (CCs) that obscure the traffic images captured in the wild. In this paper, we look at the TSDR problem under CCs and focus on the performance degradation associated with them. To overcome this, we propose a Convolutional Neural Network (CNN) based TSDR framework with prior enhancement. Our modular approach consists of a CNN-based challenge classifier, Enhance-Net, an encoder-decoder CNN architecture for image enhancement, and two separate CNN architectures for sign-detection and classification. We propose a novel training pipeline for Enhance-Net that focuses on the enhancement of the traffic sign regions (instead of the whole image) in the challenging images subject to their accurate detection. We used CURE-TSD dataset consisting of traffic videos captured under different CCs to evaluate the efficacy of our approach. We experimentally show that our method obtains an overall precision and recall of 91.1% and 70.71% that is 7.58% and 35.90% improvement in precision and recall, respectively, compared to the current benchmark. Furthermore, we compare our approach with SOTA object detection networks, Faster-RCNN and R-FCN, and show that our approach outperforms them by a large margin.