关键词: 缺陷检测, 双重细化, 门控自适应融合, RT-DETR, 可变形卷积

Abstract: The road crack detection task presents various defect types and complex anomaly regions. The current object detection algorithms suffer from redundant feature processing in channel and spatial dimensions, blind fusion of stage information, and other issues, leading to low network efficiency and loss of crucial information. This paper introduces a dual-refinement gate-controlled adaptive fusion network (DR-DETR) that achieves dual refinement processing of features in channel and spatial dimensions in latent space, addressing previous issues and enhancing road crack detection accuracy. Constructing a dual-refinement information distillation mechanism in channel and spatial dimensions, distilling redundant features separately in channel and spatial dimensions, reducing redundant processing of features by the network, and achieving efficient representation of crucial features. Aiming at the coarse-grained fusion of stage features, a Feature-Gated Fine-grained Adaptive Fusion module (FGAF-Fusion) is proposed, which utilizes enhanced stripe-wise dilated convolutions to capture global information, then employs contrastive perceptual attention for inter-channel interaction and fusion, while utilizing a gate-adaptive fusion mechanism to select critical semantic information of small targets. Designing the Res-DCNv3 module, utilizing the flexibility of DCNv3 deformable convolutions to accurately extract diverse features of road cracks with varying morphologies. Experimental results on the RDD2022 public dataset demonstrate that the proposed DR-DETR achieves mAP50 and mAP50:95 of 51.7% and 24.9%, respectively, representing improvements of 4.2 and 3.3 percentage points over RT-DETR. In road crack object detection tasks, the proposed DR-DETR can effectively detect various types of road defects, demonstrating highly competitive detection results and good robustness.

Key words: defect detection, dual refinement, gate controlled adaptive fusion, RT-DETR, deformable , convolution