Research on Steel Surface Defect Detection Algorithm Based on Improved RT-DETR

For the problem of low detection accuracy of every type of defect on the surface of steel, proposes an algorithm based on the improvement of RT-DETR on the surface of steel. To solve the defect feature extraction difficulties, the P6 feature fusion layer is added and introduced into the feature fusion stage, which effectively expands the sensory field area in the defect image, and fuse defective features more effectively in the feature fusion stage. To address the problem of lack of effective interaction between features at various scales, the CAT module is creatively introduced in the neck, and the multihead cross-attention mechanism in the CAT module is used to perform cross-scale feature interactions on the feature maps extracted at different layers to optimize the feature representation capability. The PPN replace the CCFM structure to selectively aggregate boundary features and semantic information. To verify the effect of the improved RT-DETR, the NEU-DET dataset and the GC10-DET dataset are selected. The experimental results show that the mean average accuracy of the algorithm proposed in this paper on the two datasets is improved by 2.5% and 4.5% over the original RT-DETR algorithm to 85.7% and 76.0%, respectively, which verifies the improved algorithm is feasible.