Research on Real-Time Detection System of Rail Surface Defects Based on Deep Learning
- 24 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (13) , 21157-21167
Abstract
The heavy workload of rail track inspection makes it time consuming, and thus calls out a real-time inspection algorithm to achieve precise and efficient detiction. In this study, we developed a real-time detection system for rail surface. Our system utilizes machine vision and real-time algorithms to ensure efficient and fast inspections. Edge computing device is used for real-time detection of track defect. To increase detection accuracy and speed, we optimized the YOLOv5 structure by introducing depth-separable convolution and re-parameterization methods. Through training and evaluating the model on a dataset of rail surface defects, we achieved a mean average precision (mAP) of 83.2% and a detection speed of 51 FPS on edge computing devices. The performance of model outstrips that of other one-stage algorithms and backbone network detection results, as it exhibits high accuracy and speed. This achievement lays the groundwork for realizing real-time detection of rail defects and augmenting railroad safety.Keywords
Funding Information
- Beijing Natural Science Foundation (L231021)
- Fundamental Research Funds for the Central Universities (2022JBXT005)
This publication has 45 references indexed in Scilit:
- High-speed acquisition and intelligent tunnel surface defects recognitionTunnelling and Underground Space Technology, 2023
- Image-based intelligent detection of typical defects of complex subway tunnel surfaceTunnelling and Underground Space Technology, 2023
- A novel vibration-based prognostic scheme for gear health management in surface wear progression of the intelligent manufacturing systemWear, 2023
- RAG-PaDiM: Residual Attention Guided PaDiM for Defects Segmentation in Railway TracksJournal of Electrical Engineering & Technology, 2022
- Cross-scale fusion and domain adversarial network for generalizable rail surface defect segmentation on unseen datasetsJournal of Intelligent Manufacturing, 2022
- Ultrasonic imaging of buried defects in railsNDT & E International, 2022
- Sharp U-Net: Depthwise convolutional network for biomedical image segmentationComputers in Biology and Medicine, 2021
- Real-time railroad track components inspection based on the improved YOLOv4 frameworkAutomation in Construction, 2021
- Track Surface Defect Detection Based on Image Processing2018
- Hidden defect recognition based on the improved ensemble empirical decomposition method and pulsed eddy current testingNDT & E International, 2017