Detection of Surface Defects on Railway Tracks Based on Deep Learning
Обнаружение поверхностных дефектов железнодорожных рельсов на основе глубокого обучения
2022-01-01
SCID: 54.1/pvfce7k6
Discuss with AI
V-CBAM attention mechanismYOLOv5s-VFadaptive spatial feature fusionobject detectionrail surface defect detection
Figures from the paper
Abstract (AI)
The detection of rail surface defects is very important in railway transportation. However, the edge defects on both sides of the rail and the multi-scale variation between different types of defects both pose challenges to the detection of rail surface defects. In order to solve the above problems, this paper proposes a novel rail surface defect detection network, YOLOv5s-VF. First, we design a sharpening functional attention mechanism (V-CBAM) that contains two key components: adaptive channel attention (F-CAM) and sharpened spatial attention (SSA). In F-CAM, we use one-dimensional convolution with adaptive convolution kernels for cross-channel connections, which reduces the number of parameters of the attention mechanism without affecting its performance. In SSA, we design a sharpening filter suitable for spatial attention, which is used to enhance the attention to the edge position defects of railway tracks and enhance the detection effect of the network on edge defects. Second, we construct a microscale adaptive spatial feature fusion (M-ASFF), which adds a high-resolution feature extraction layer to enhance the details of the underlying features of tiny defects. At the same time, in order to prevent the loss of detailed information and the excessive increase of the parameters of the model, the low-resolution feature layer is removed. Combined with adaptive spatial feature fusion, it can prevent the semantic conflict caused by the fusion of features at different scales. Finally, given the lack of labeled public rail surface defect datasets, this paper is based on the collection of real rail images and manually labels defects to train an object detection network and open source it. The experimental results show that YOLOv5s-VF outperforms the existing rail surface defect detection methods with a detection accuracy of 93.5% and a detection speed of 114.9 fps.
Key Findings
1
M-ASFF adds high-resolution feature extraction for tiny defects while removing a low-resolution layer, limiting detail loss and parameter growth during multi-scale fusion.
2
The authors collected and manually labeled real rail images, creating and open-sourcing a public rail-surface defect dataset.
3
The proposed YOLOv5s-VF network addresses railway rail-surface defects, including edge defects and multi-scale defects.
4
V-CBAM combines adaptive channel attention with sharpened spatial attention to reduce attention parameters and improve detection of edge-position defects.
5
YOLOv5s-VF outperformed existing rail-surface defect detection methods, achieving 93.5% detection accuracy and 114.9 frames per second.
Research Object
Railway track rail surfaces with surface defects, including edge and tiny defects
Research Subject
Detection accuracy and speed for identifying multi-scale rail surface defects, especially edge defects, using an object-detection network
Publication Details
Publication Date
2022-01-01
Journal
Publisher
ISSN
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest