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
  • [21] Intracranial Aneurysm Segmentation with a Dual-Path Fusion Network
    Wang, Ke
    Zhang, Yong
    Fang, Bin
    BIOENGINEERING-BASEL, 2025, 12 (02):
  • [22] Steel strip surface defect detection based on multiscale feature sensing and adaptive feature fusion
    Mi, Zengzhen
    Gao, Yan
    Xu, Xingyuan
    Tang, Jing
    AIP ADVANCES, 2024, 14 (04)
  • [23] Dual-path parallel hierarchical diagnostic model of glioma based on pathomorphological feature
    Fang, Lingling
    Jiang, Yumeng
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2024, 87
  • [24] Attention-Based Multiscale Feature Fusion for Efficient Surface Defect Detection
    Zhao, Yuhao
    Liu, Qing
    Su, Hu
    Zhang, Jiabin
    Ma, Hongxuan
    Zou, Wei
    Liu, Song
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2024, 73 : 1 - 10
  • [25] A Method for Surface Defect Detection Based on Multiscale Feature Fusion and Pyramid Attention
    Tang, Ying
    Wang, Hongyuan
    Zhou, Qunying
    Sun, Boyan
    IEEE ACCESS, 2024, 12 : 36457 - 36465
  • [26] Surface Defect Detection Based on Adaptive Multi-Scale Feature Fusion
    Wen, Guochen
    Cheng, Li
    Yuan, Haiwen
    Li, Xuan
    SENSORS, 2025, 25 (06)
  • [27] Damage Detection Method for Rail Surface Based on Multi-Level Feature Fusion
    Han Q.
    Liu J.
    Feng Q.
    Wang S.
    Dai P.
    Zhongguo Tiedao Kexue/China Railway Science, 2021, 42 (05): : 41 - 49
  • [28] Vehicle Detection in Congested Traffic Based on Simplified Weighted Dual-Path Feature Pyramid Network With Guided Anchoring
    Luo, Jingqing
    Fang, Husheng
    Shao, Faming
    Hu, Cong
    Meng, Fanjie
    IEEE ACCESS, 2021, 9 : 53219 - 53231
  • [29] Filter-based feature selection for rail defect detection
    C. Mandriota
    M. Nitti
    N. Ancona
    E. Stella
    A. Distante
    Machine Vision and Applications, 2004, 15 : 179 - 185
  • [30] Filter-based feature selection for rail defect detection
    Mandriota, C
    Nitti, M
    Ancona, N
    Stella, E
    Distante, A
    MACHINE VISION AND APPLICATIONS, 2004, 15 (04) : 179 - 185