LPCAN：用于使用RGB-D数据进行铁路表面缺陷检测的轻量级金字塔交叉注意力网络
LPCAN: Lightweight Pyramid Cross-Attention Network for Rail Surface Defect Detection Using RGB-D Data
AI总结：
针对铁路表面缺陷检测方法局限，提出LPCANet，利用RGB-D数据，集成MobileNetv2等模块，经多模态融合与结构分析提升性能。在多数据集上评估效果显著，消融研究验证关键模块作用，为工业缺陷检测提供实用框架，未来将聚焦模型压缩。
摘要：
本文指出了当前基于视觉的铁路缺陷检测方法存在计算复杂度高、参数过多和精度欠佳等局限。我们提出了轻量级金字塔交叉注意力网络（LPCANet），利用RGB-D数据高效准确地识别缺陷。该架构将MobileNetv2作为RGB特征提取主干，结合轻量级金字塔模块处理深度信息，通过交叉注意力机制进行多模态融合，利用空间特征提取器增强结构分析。在三个无监督RGB-D铁路数据集上综合评估表明，LPCANet仅用990万个参数、2.50 G FLOPs和162.60 fps推理速度就实现了最优性能，相比18种现有方法有显著提升。消融研究证实了交叉注意力机制和空间特征提取器的关键作用，在非铁路数据集上的实验验证了其泛化能力。该框架有效衔接了传统与深度学习方法，对工业缺陷检测有重要实用价值，未来工作将聚焦进一步模型压缩以实现实时部署。
英文摘要：
This paper addresses the limitations of current vision-based rail defect detection methods, including high computational complexity, excessive parameter counts, and suboptimal accuracy. We propose a Lightweight Pyramid Cross-Attention Network (LPCANet) that leverages RGB-D data for efficient and accurate defect identification. The architecture integrates MobileNetv2 as a backbone for RGB feature extraction with a lightweight pyramid module (LPM) for depth processing, coupled with a cross-attention mechanism (CAM) for multimodal fusion and a spatial feature extractor (SFE) for enhanced structural analysis. Comprehensive evaluations on three unsupervised RGB-D rail datasets (NEU-RSDDS-AUG, RSDD-TYPE1, RSDD-TYPE2) demonstrate that LPCANet achieves state-of-the-art performance with only 9.90 million parameters, 2.50 G FLOPs, and 162.60 fps inference speed. Compared to 18 existing methods, LPCANet shows significant improvements, including +1.48\% in $S_α$, +0.86\% in IOU, and +1.77\% in MAE over the best-performing baseline. Ablation studies confirm the critical roles of CAM and SFE, while experiments on non-rail datasets (DAGM2007, MT, Kolektor-SDD2) validate its generalization capability. The proposed framework effectively bridges traditional and deep learning approaches, offering substantial practical value for industrial defect inspection. Future work will focus on further model compression for real-time deployment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
