RGB-D Rail Surface Defect Inspection Driven by Conditional Diffusion Architecture and Frequency Knowledge

Authors:
Publisher website
Google Scholar
Abstract
RGB-D Rail Surface Defect Inspection (RSDI) is a critical measure for ensuring transportation safety. It improves inspection accuracy by using depth maps, but the issue of poor-quality depth maps in rail defect datasets is often overlooked. Additionally, the similarity between the foreground and background has always been a persistent challenge in RGB-D RSDI. In this article, we propose a novel network, termed DiffRSDI to overcome these challenges in RGB-D RSDI, which treats RGB-D RSDI as a mask generation task using a conditional diffusion architecture. Specifically, DiffRSDI consists of two key components: Cross-modal Cyclic Enhancement (CCE) module and Frequency-aware Alternate Fusion (FAF) module. CCE module is based on the cyclic enhancement approach, and aims to eliminate interference from poor-quality depth maps and aggregate cross-modal features. FAF module overcomes the similarity between the foreground and background in the frequency-domain, and achieves cross-scale fusion in the fused features. Comprehensive experiments conducted on the NEU RSDDS-AUG dataset confirm that our method achieves superior performance in comparison to 14 related methods. The DiffRSDI code and results are available at https://github.com/zeroyi37/DiffRSDI.
Funding Information
  • National Natural Science Foundation of China (62401350, 62471285)
  • Shanghai Sailing Program (24YF2713000)
  • Open Research Fund of Anhui Province Key Laboratory of Machine Vision Detection and Perception (KLMVI-2024-HIT-04)

This publication has 62 references indexed in Scilit: