Lightweight Neural Network for Real-Time Crack Detection on Concrete Surface in Fog

被引:1
|
作者
Yao, Gang [1 ]
Sun, Yujia [1 ]
Yang, Yang [1 ]
Liao, Gang [1 ]
机构
[1] Chongqing Univ, Sch Civil Engn, Chongqing, Peoples R China
来源
FRONTIERS IN MATERIALS | 2021年 / 8卷
基金
中国国家自然科学基金;
关键词
crack detection; deep learning; concrete surface; improved YOLOv4; ghostnet; dark channel prior; DAMAGE DETECTION; DEEP; ALGORITHMS;
D O I
10.3389/fmats.2021.798786
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Cracks are one of the most common factors that affect the quality of concrete surfaces, so it is necessary to detect concrete surface cracks. However, the current method of manual crack detection is labor-intensive and time-consuming. This study implements a novel lightweight neural network based on the YOLOv4 algorithm to detect cracks on a concrete surface in fog. Using the computer vision algorithm and the GhostNet Module concept for reference, the backbone network architecture of YOLOv4 is improved. The feature redundancy between networks is reduced and the entire network is compressed. The multi-scale fusion method is adopted to effectively detect cracks on concrete surfaces. In addition, the detection of concrete surface cracks is seriously affected by the frequent occurrence of fog. In view of a series of degradation phenomena in image acquisition in fog and the low accuracy of crack detection, the network model is integrated with the dark channel prior concept and the Inception module. The image crack features are extracted at multiple scales, and BReLU bilateral constraints are adopted to maintain local linearity. The improved model for crack detection in fog achieved an mAP of 96.50% with 132 M and 2.24 GMacs. The experimental results show that the detection performance of the proposed model has been improved in both subjective vision and objective evaluation metrics. This performs better in terms of detecting concrete surface cracks in fog.
引用
收藏
页数:16
相关论文
共 50 条
  • [41] LightMOT: a lightweight convolution neural network for real-time multi-object tracking
    Guo, Lie
    Ge, Pingshu
    Zhao, Yibing
    Wang, Dongxing
    Huang, Liang
    [J]. INTERNATIONAL JOURNAL OF BIO-INSPIRED COMPUTATION, 2023, 22 (03) : 152 - 161
  • [42] A Real-time Driver Fatigue Monitoring System Based on Lightweight Convolutional Neural Network
    Zhou, Chunyu
    Li, Jun
    [J]. PROCEEDINGS OF THE 33RD CHINESE CONTROL AND DECISION CONFERENCE (CCDC 2021), 2021, : 1548 - 1553
  • [43] A Lightweight Object Detection Network for Real-Time Detection of Driver Handheld Call on Embedded Devices
    Zhao, Zuopeng
    Zhang, Zhongxin
    Xu, Xinzheng
    Xu, Yi
    Yan, Hualin
    Zhang, Lan
    [J]. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2020, 2020
  • [44] A Deep Lightweight Convolutional Neural Network Method for Real-Time Small Object Detection in Optical Remote Sensing Images
    Yanyong Han
    Yandong Han
    [J]. Sensing and Imaging, 2021, 22
  • [45] A Deep Lightweight Convolutional Neural Network Method for Real-Time Small Object Detection in Optical Remote Sensing Images
    Han, Yanyong
    Han, Yandong
    [J]. SENSING AND IMAGING, 2021, 22 (01):
  • [46] Real-Time Crack Detection in Aerospace Structures
    不详
    [J]. WELDING JOURNAL, 2009, 88 (02) : 46 - 47
  • [47] LACTNet: A Lightweight Real-Time Semantic Segmentation Network Based on an Aggregated Convolutional Neural Network and Transformer
    Zhang, Xiangyue
    Li, Hexiao
    Ru, Jingyu
    Ji, Peng
    Wu, Chengdong
    [J]. ELECTRONICS, 2024, 13 (12)
  • [48] Real-time crack detection in aerospace structures
    [J]. Welding Journal (Miami, Fla), 2009, 88 (02): : 46 - 47
  • [49] Lightweight Network Architecture for Real-Time Action Recognition
    Kozlov, Alexander
    Andronov, Vadim
    Gritsenko, Yana
    [J]. PROCEEDINGS OF THE 35TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING (SAC'20), 2020, : 2074 - 2080
  • [50] Lightweight mobile network for real-time violence recognition
    Zhang, Youshan
    Li, Yong
    Guo, Shaozhe
    [J]. PLOS ONE, 2022, 17 (10):