Multi-Scale Feature Refinement Road Crack Detection Algorithm Based on Improved RT-DETR
Road crack detection is an important part of the operation and maintenance of intelligent transportation infrastructure. However, the traditional convolution method has the problem of geometric mismatch when dealing with the slender linear structure of cracks, and the multi-scale adaptability and anti-interference ability of the detection model under a complex road background are still insufficient. Aiming at key problems such as the difficulty of linear feature extraction, poor multi-scale adaptability, and complex background interference, this paper proposes a road crack detection algorithm based on an improved RT-DETR multi-dimensional feature fusion method. This method improves the detection performance by introducing three core innovative modules. Firstly, a lightweight directional decoupled dynamic convolution (D3Conv) is designed, which makes the convolution kernel fit the crack direction through direction prediction and adaptive sampling, so as to improve the recall rate by 0.012 (from 0.647 to 0.659) and reduce the computational burden. Secondly, a multi-scale cross-attention enhancement module (MCAA) was proposed to fuse multi-scale convolution and direction-aware strip convolution, and the dual attention mechanism was combined to enhance the perception of crack morphology and scale. Furthermore, a context-guided feature reconstruction (CGFR) module was constructed, which effectively aggregated global semantics and local details through dynamic feature selection and a multi-branch refining mechanism to improve the accuracy of boundary location. Experiments on the public dataset SVRDD2024 show that the proposed algorithm achieves an mAP@50 of 0.724, which is 2.2% higher than the baseline RT-DETR-R18 in terms of mAP@50. Especially, the detection performance is significantly improved for small cracks and in complex environments. It provides a reliable and efficient solution for the automatic inspection of intelligent transportation infrastructure.