Traffic sign detection improves with better feature fusion and channel attention
Squeeze-Aware-YOLO: Early Channel Recalibration and Multi-Scale Fusion for Real-Time Traffic Sign Detection
Computer Vision and Pattern Recognition
Summary
Detecting traffic signs accurately is hard when signs are small, blurred, or affected by weather. The authors created a lightweight system called Squeeze-Aware-YOLO that uses a new way to focus on important parts of images and combine information at different sizes to improve detection. They tested it on three different traffic sign datasets and found it works better than recent similar systems while staying fast enough for real-time use. This helps vehicles detect signs more reliably under tough conditions.
What this means in practice
- •For automotive engineering teams: Enhance advanced driver assistance systems with improved traffic sign recognition that handles small and degraded signs in real time.
- •For smart city infrastructure developers: Deploy lightweight, efficient traffic sign detection models to support autonomous vehicle navigation and traffic monitoring systems.
Authors
Mizbaul Haque Maruf, Syed Samin Sadaf, Syed Tamzid Bakht, Md. Hasanul Kabir, Sabbir Ahmed
Abstract
Traffic sign detection plays a vital role in intelligent transportation systems, supporting the safe operation of advanced driver assistance systems and autonomous vehicles. Despite significant progress in real-time object detection, accurately identifying traffic signs under challenging conditions remains difficult. Variations in lighting, adverse weather, motion blur, and partial occlusion often reduce detection performance, especially for small or visually degraded signs where important spatial information can be lost. To address these challenges, we propose Squeeze-Aware-YOLO, a lightweight traffic sign detection framework that introduces a multi-branch bottleneck module combining convolutional kernels of different sizes with a Squeeze-and-Excitation mechanism to improve feature extraction and adaptive channel weighting. In addition, we integrate the Multi-Branch Auxiliary Feature Pyramid Network and Re-parameterized Heterogeneous Multi-Scale modules to strengthen multi-scale feature representation and feature fusion while preserving real-time inference efficiency for practical deployment. The proposed approach is evaluated on the Bangladeshi Traffic Sign Detection Dataset, the CSUST Chinese Traffic Sign Detection Benchmark 2021, and the German Traffic Sign Detection Benchmark, achieving mAP@0.5 scores of 74.7%, 79.4%, and 84.0%, respectively, while consistently outperforming recent state-of-the-art YOLO-based traffic sign detectors. These findings demonstrate that combining multi-scale receptive fields, channel attention, and enhanced feature fusion enables more accurate and robust traffic sign detection while maintaining the computational efficiency required for real-world deployment.