Rail Surface Defect Detection Based on Dual-Path Feature Fusion

被引:0
|
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 50 条
  • [31] A Rail Surface Defect Detection Method Based on Pyramid Feature and Lightweight Convolutional Neural Network
    Liu, Yu
    Xiao, Huaxi
    Xu, Jiaming
    Zhao, Jingyi
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 71
  • [32] Dual-Path GAN: A Method for Enhancing Small-scale Defect Detection on Metal Images
    Ye, Zhuoxun
    Liu, Meiqin
    Zhang, Senlin
    Wei, Ping
    2022 41ST CHINESE CONTROL CONFERENCE (CCC), 2022, : 6292 - 6297
  • [33] YOLOv3-DPFIN: A Dual-Path Feature Fusion Neural Network for Robust Real-Time Sonar Target Detection
    Kong, Wanzeng
    Hong, Jichen
    Jia, Mingyang
    Yao, Jinliang
    Gong, Weihua
    Hu, Hua
    Zhang, Haigang
    IEEE SENSORS JOURNAL, 2020, 20 (07) : 3745 - 3756
  • [34] Generating generalized zero-shot learning based on dual-path feature enhancement
    Chang, Xinyi
    Wang, Zhen
    Liu, Wenhao
    Gao, Limeng
    Yan, Bingshuai
    MULTIMEDIA SYSTEMS, 2024, 30 (05)
  • [35] Remaining Useful Life Prediction Method Based on Dual-Path Interaction Network with Multiscale Feature Fusion and Dynamic Weight Adaptation
    Lu, Zhe
    Li, Bing
    Fu, Changyu
    Wu, Junbao
    Xu, Liang
    Jia, Siye
    Zhang, Hao
    ACTUATORS, 2024, 13 (10)
  • [36] A Dual-Path Multihead Feature Enhancement Detector for Oriented Object Detection in Remote Sensing Images
    Li, Yibing
    Li, Zifan
    Ye, Fang
    Li, Yingsong
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [37] Rail Surface Defect Detection Based on Deep Learning
    Li, Xiaoqing
    Zhou, Ying
    Chen, Hu
    ELEVENTH INTERNATIONAL CONFERENCE ON GRAPHICS AND IMAGE PROCESSING (ICGIP 2019), 2020, 11373
  • [38] Defect detection of PCB based on Bayes feature fusion
    Lu, Zhisheng
    He, Qinqin
    Xiang, Xinguang
    Liu, Hong
    JOURNAL OF ENGINEERING-JOE, 2018, (16): : 1741 - 1745
  • [39] Surface Tiny Defect Detection Based on Gaussian Distribution Modeling and Adaptive Feature Fusion
    Wang, Weijia
    Hao, Liang
    Wang, Jinghua
    Hu, Yu
    Xu, Yong
    2024 INTERNATIONAL CONFERENCE ON ELECTRONIC ENGINEERING AND INFORMATION SYSTEMS, EEISS 2024, 2024, : 30 - 35
  • [40] Lightweight and efficient dual-path fusion network for iris segmentation
    Lei, Songze
    Shan, Aokui
    Liu, Bo
    Zhao, Yanxiao
    Xiang, Wei
    SCIENTIFIC REPORTS, 2023, 13 (01)