CCSPNet-Joint: Efficient Joint Training Method for Traffic Sign Detection Under Extreme Conditions

TL;DR

This paper introduces CCSPNet-Joint, a novel joint training approach combining image denoising and traffic sign detection under extreme conditions, leading to improved accuracy and efficiency in challenging scenarios.

Contribution

The paper proposes a new feature extraction module and a joint training framework that enhances traffic sign detection performance in adverse weather and visual conditions.

Findings

CCSPNet outperforms existing methods in extreme scenarios.

Joint training improves data efficiency and generalization.

Achieves 5.32% higher precision and 18.09% higher mAP@.5.

Abstract

Traffic sign detection is an important research direction in intelligent driving. Unfortunately, existing methods often overlook extreme conditions such as fog, rain, and motion blur. Moreover, the end-to-end training strategy for image denoising and object detection models fails to utilize inter-model information effectively. To address these issues, we propose CCSPNet, an efficient feature extraction module based on Contextual Transformer and CNN, capable of effectively utilizing the static and dynamic features of images, achieving faster inference speed and providing stronger feature enhancement capabilities. Furthermore, we establish the correlation between object detection and image denoising tasks and propose a joint training model, CCSPNet-Joint, to improve data efficiency and generalization. Finally, to validate our approach, we create the CCTSDB-AUG dataset for traffic sign detection in extreme scenarios. Extensive experiments have shown that CCSPNet achieves state-of-the-art performance in traffic sign detection under extreme conditions. Compared to end-to-end methods, CCSPNet-Joint achieves a 5.32% improvement in precision and an 18.09% improvement in mAP@.5.