Rail Surface Defect Detection Based on Dual-Path Feature Fusion

被引:1
作者
Zhong, Yinfeng [1 ]
Chen, Guorong [1 ]
机构
[1] Chongqing Univ Sci & Technol, Dept Intelligent Technol & Engn, Chongqing 401331, Peoples R China
关键词
defect detection; dual path; attention mechanism; CLASSIFICATION;
D O I
10.3390/electronics13132564
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
With the rapid development of rail transit, the workload of track maintenance has increased, making the intelligent identification of rail surface defects crucial for improving detection efficiency. To address issues such as low defect detection accuracy, the loss of feature information due to single-path architecture backbones, and insufficient information interaction in existing rail defect detection methods, we propose a rail surface defect detection method based on dual-path feature fusion (DPF). This method initially employs a dual-path structure to separately extract low-level and high-level features. It then utilizes a combination of attention mechanisms and feature fusion techniques to integrate these features. By doing so, it preserves richer information and enhances detection accuracy and robustness. The experimental results demonstrate that the comprehensive performance of the proposed model is superior to mainstream algorithms.
引用
收藏
页数:16
相关论文
共 43 条
[1]   Automatic detection of photovoltaic module defects in infrared images with isolated and develop-model transfer deep learning [J].
Akram, M. Waqar ;
Li, Guiqiang ;
Jin, Yi ;
Chen, Xiao ;
Zhu, Changan ;
Ahmad, Ashfaq .
SOLAR ENERGY, 2020, 198 :175-186
[2]   Condition monitoring approaches for the detection of railway wheel defects [J].
Alemi, Alireza ;
Corman, Francesco ;
Lodewijks, Gabriel .
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART F-JOURNAL OF RAIL AND RAPID TRANSIT, 2017, 231 (08) :961-981
[3]   Railroad accident rates for use in transportation risk analysis [J].
Anderson, RT ;
Barkan, CPL .
RAILROADS: HIGH-SPEED PASSENGER RAIL, RAILWAY BRIDGES, AND TRACK DESIGN AND MAINTENANCE, 2004, (1863) :88-98
[4]   CUFuse: Camera and Ultrasound Data Fusion for Rail Defect Detection [J].
Chen, Zhengxing ;
Wang, Qihang ;
He, Qing ;
Yu, Tianle ;
Zhang, Min ;
Wang, Ping .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 23 (11) :21971-21983
[5]   RetinaNet With Difference Channel Attention and Adaptively Spatial Feature Fusion for Steel Surface Defect Detection [J].
Cheng, Xun ;
Yu, Jianbo .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2021, 70 (70)
[6]   PGA-Net: Pyramid Feature Fusion and Global Context Attention Network for Automated Surface Defect Detection [J].
Dong, Hongwen ;
Song, Kechen ;
He, Yu ;
Xu, Jing ;
Yan, Yunhui ;
Meng, Qinggang .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2020, 16 (12) :7448-7458
[7]  
Dong J.Y., 2021, J Zhejiang Sci-Tech Univ, V45, P379
[8]   Automatic Fastener Classification and Defect Detection in Vision-Based Railway Inspection Systems [J].
Feng, Hao ;
Jiang, Zhiguo ;
Xie, Fengying ;
Yang, Ping ;
Shi, Jun ;
Chen, Long .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2014, 63 (04) :877-888
[9]   Research on deep learning method for rail surface defect detection [J].
Feng, Jiang Hua ;
Yuan, Hao ;
Hu, Yun Qing ;
Lin, Jun ;
Liu, Shi Wang ;
Luo, Xiao .
IET ELECTRICAL SYSTEMS IN TRANSPORTATION, 2020, 10 (04) :436-442
[10]   Anomaly Detection, Localization and Classification for Railway Inspection [J].
Gasparini, Riccardo ;
D'Eusanio, Andrea ;
Borghi, Guido ;
Pini, Stefano ;
Scaglione, Giuseppe ;
Calderara, Simone ;
Fedeli, Eugenio ;
Cucchiara, Rita .
2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, :3419-3426