Automated Pixel-Level Detection of Expansion Joints on Asphalt Pavement Using a Deep-Learning-Based Approach

被引:10
作者
He, Anzheng [1 ]
Dong, Zishuo [1 ]
Zhang, Hang [1 ]
Zhang, Allen A. A. [1 ]
Qiu, Shi [2 ]
Liu, Yang [3 ]
Wang, Kelvin C. P. [3 ]
Lin, Zhihao [4 ]
机构
[1] Southwest Jiaotong Univ, Sch Civil Engn, Chengdu 610031, Peoples R China
[2] Cent South Univ, Sch Civil Engn, Changsha 410075, Peoples R China
[3] Oklahoma State Univ, Sch Civil & Environm Engn, Stillwater, OK 74078 USA
[4] Sichuan Shudao New Energy Technol Dev Co Ltd, Chengdu 610041, Peoples R China
基金
中国国家自然科学基金;
关键词
CRACK DETECTION; SURFACES;
D O I
10.1155/2023/7552337
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Pixel-level detection of expansion joints on complex pavements is significant for traffic safety and the structural integrity of highway bridges. This paper proposed an improved HRNet-OCR, named as expansion joints segmentation network (EJSNet), for automated pixel-level detection of the expansion joints on asphalt pavement. Different from the high-resolution network (HRNet), the proposed EJSNet modifies the residual structure of the first stage by conducting a Conv. + BN + ReLU (convolution + batch normalization + rectified linear unit) operation for each shortcut connection, which can avoid the network degradation. The feature selection module (FSM) and receptive field block (RFB) module are incorporated into the proposed EJSNet model to learn and extract the contexts at different resolution levels for enhanced latent representations. The convolutional block attention module (CBAM) is introduced to enhance the adaptive feature refinement of the network. Moreover, the shared multilayer perceptron (MLP) architecture of the channel attention module (CAM) is also modified in this paper. Experimental results demonstrate that the F-measure and intersection-over-union (IOU) attained by the proposed EJSNet model on 500 testing image sets are 95.14% and 0.9036, respectively. Compared with four state-of-the-art models for semantic segmentation (i.e., SegNet, DeepLabv3+, dual attention network (DANet), and HRNet-OCR), the proposed EJSNet model can yield higher detection accuracy on both private and public datasets.
引用
收藏
页数:15
相关论文
共 34 条
  • [21] Ronneberger O, 2015, Arxiv, DOI arXiv:1505.04597
  • [22] Residual Attention Network for Image Classification
    Wang, Fei
    Jiang, Mengqing
    Qian, Chen
    Yang, Shuo
    Li, Cheng
    Zhang, Honggang
    Wang, Xiaogang
    Tang, Xiaoou
    [J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 6450 - 6458
  • [23] Deep High-Resolution Representation Learning for Visual Recognition
    Wang, Jingdong
    Sun, Ke
    Cheng, Tianheng
    Jiang, Borui
    Deng, Chaorui
    Zhao, Yang
    Liu, Dong
    Mu, Yadong
    Tan, Mingkui
    Wang, Xinggang
    Liu, Wenyu
    Xiao, Bin
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (10) : 3349 - 3364
  • [24] Bilirubin ameliorates murine atherosclerosis through inhibiting cholesterol synthesis and reshaping the immune system
    Wen, Guanmei
    Yao, Leyi
    Hao, Yali
    Wang, Jinheng
    Liu, Jinbao
    [J]. JOURNAL OF TRANSLATIONAL MEDICINE, 2022, 20 (01)
  • [25] Woo S, 2018, Arxiv, DOI [arXiv:1807.06521, DOI 10.48550/ARXIV.1807.06521, 10.48550/arXiv.1807.06521, 10.48550/ARXIV.1807.06521]
  • [26] HRCNet: High-Resolution Context Extraction Network for Semantic Segmentation of Remote Sensing Images
    Xu, Zhiyong
    Zhang, Weicun
    Zhang, Tianxiang
    Li, Jiangyun
    [J]. REMOTE SENSING, 2021, 13 (01) : 1 - 23
  • [27] Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection
    Yang, Fan
    Zhang, Lei
    Yu, Sijia
    Prokhorov, Danil
    Mei, Xue
    Ling, Haibin
    [J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2020, 21 (04) : 1525 - 1535
  • [28] Yuan YH, 2021, Arxiv, DOI arXiv:1909.11065
  • [29] Automated Pixel-Level Pavement Crack Detection on 3D Asphalt Surfaces with a Recurrent Neural Network
    Zhang, Allen
    Wang, Kelvin C. P.
    Fei, Yue
    Liu, Yang
    Chen, Cheng
    Yang, Guangwei
    Li, Joshua Q.
    Yang, Enhui
    Qiu, Shi
    [J]. COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, 2019, 34 (03) : 213 - 229
  • [30] Deep Learning-Based Fully Automated Pavement Crack Detection on 3D Asphalt Surfaces with an Improved CrackNet
    Zhang, Allen
    Wang, Kelvin C. P.
    Fei, Yue
    Liu, Yang
    Tao, Siyu
    Chen, Cheng
    Li, Joshua Q.
    Li, Baoxian
    [J]. JOURNAL OF COMPUTING IN CIVIL ENGINEERING, 2018, 32 (05)