Message Board

Respected readers, authors and reviewers, you can add comments to this page on any questions about the contribution, review,        editing and publication of this journal. We will give you an answer as soon as possible. Thank you for your support!

Name
E-mail
Phone
Title
Content
Verification Code
Turn off MathJax
Article Contents

XIAO Liyang, LI Wei, YUAN Bo, CUI Yiqun, GAO Rong, WANG Wenqing. Pavement Crack Automatic Identification Method Based on Improved Mask R-CNN Model[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20210279
Citation: XIAO Liyang, LI Wei, YUAN Bo, CUI Yiqun, GAO Rong, WANG Wenqing. Pavement Crack Automatic Identification Method Based on Improved Mask R-CNN Model[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20210279

Pavement Crack Automatic Identification Method Based on Improved Mask R-CNN Model

doi: 10.13203/j.whugis20210279
Funds:

Supported by the National Key Research and Development Program “Comprehensive Transportation and Intelligent Transportation” Special Project (2018YFB1600202),the National Natural Science Foundation of China (51978071) and the Youth Fund of the National Natural Science Foundation of China (51908059).

  • Received Date: 2021-06-25
  • Objectives: In order to solve problems of low accuracy and single task in the existing crack identification algorithm, this paper proposes a pavement crack identification method via improved Mask R-CNN model. Methods: Firstly, the crack dataset is collected and labeled.Through the training and optimization of the Mask R-CNN model, the crack pixels in the generated detection box are segmented while the crack is located. Secondly, to solve the problems of inaccurate detection of crack edge and low accuracy of Mask R-CNN model, an improved C-Mask RCNN is designed, which improves the quality of crack region proposal generation by cascading multi threshold detectors and achieves accurate positioning under high threshold. Finally,a series of optimization parameters and experimental comparison are carried out for the improved model, and the effectiveness of the proposed model is verified. Results: The experimental results show that the mean average precision of C-Mask RCNN model detection part is 95.4%, which is 9.7% higher than that of the conventional model, and the mean average precision of the segmentation part is 93.5%, which is 13.0% higher than that of the conventional model. Conclusions: In summary, the C-Mask RCNN model proposed in this paper can locate and extract cracks with high identification accuracy.
  • [1] Premachandra C, Waruna H, Premachandra H, et al.Image Based Automatic Road Surface Crack Detection for Achieving Smooth Driving on Deformed Roads[J].2013 IEEE International Conference on Systems, Man, and Cybernetics, 2013:4018-4023
    [2] Oliveira H, Correia P L.CrackIT-An image processing toolbox for crack detection and characterization[C]//2014 IEEE International Conference on Image Processing.Paris, France.2014:798-802
    [3] Yoo H S, Kim Y S.Development of a Crack Recognition Algorithm from Non-Routed Pavement Images Using Artificial Neural Network and Binary Logistic Regression[J].KSCE Journal of Civil Engineering, 2016, 20(4):1151-1162
    [4] Zou Q, Zhang Z, Li Q Q, et al.DeepCrack:Learning Hierarchical Convolutional Features for Crack Detection[J].IEEE Transactions on Image Processing, 2019, 28(3):1498-1512
    [5] Badrinarayanan V, Kendall A, Cipolla R.SegNet:A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12):2481-2495
    [6] Maeda H, Sekimoto Y, Seto T, et al.Road Damage Detection and Classification Using Deep Neural Networks with Smartphone Images[J].Computer-Aided Civil and Infrastructure Engineering, 2018, 33(12):1127-1141
    [7] Alipour M, Harris D K, Miller G R.Robust Pixel-Level Crack Detection Using Deep Fully Convolutional Neural Networks[J].Journal of Computing in Civil Engineering, 2019, 33(6):4019040
    [8] Nguyen H T, Yu G H, Na S Y, et al.Pavement Crack Detection and Segmentation Based on Deep Neural Network[J].The Journal of Korean Institute of Information Technology, 2019, 17(9):99-112
    [9] Ren S Q, He K M, Girshick R, et al.Faster R-CNN:Towards real-time object detection with region proposal networks[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence.:1137-1149
    [10] Girshick R.Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision.Santiago, Chile.2015:1440-1448
    [11] Girshick R, Donahue J, Darrell T, et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus, OH, USA.2014:580-587
    [12] He K M, Gkioxari G, Dollár P, et al.Mask R-CNN[C]//2017 IEEE International Conference on Computer Vision.Venice, Italy.2017:2980-2988
    [13] Cai Z W, Vasconcelos N.Cascade R-CNN:Delving into High Quality Object Detection[J].2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018:6154-6162
  • 加载中
通讯作者: 陈斌, bchen63@163.com
  • 1. 

    沈阳化工大学材料科学与工程学院 沈阳 110142

  1. 本站搜索
  2. 百度学术搜索
  3. 万方数据库搜索
  4. CNKI搜索

Article Metrics

Article views(104) PDF downloads(4) Cited by()

Related
Proportional views

Pavement Crack Automatic Identification Method Based on Improved Mask R-CNN Model

doi: 10.13203/j.whugis20210279
Funds:

Supported by the National Key Research and Development Program “Comprehensive Transportation and Intelligent Transportation” Special Project (2018YFB1600202),the National Natural Science Foundation of China (51978071) and the Youth Fund of the National Natural Science Foundation of China (51908059).

Abstract: Objectives: In order to solve problems of low accuracy and single task in the existing crack identification algorithm, this paper proposes a pavement crack identification method via improved Mask R-CNN model. Methods: Firstly, the crack dataset is collected and labeled.Through the training and optimization of the Mask R-CNN model, the crack pixels in the generated detection box are segmented while the crack is located. Secondly, to solve the problems of inaccurate detection of crack edge and low accuracy of Mask R-CNN model, an improved C-Mask RCNN is designed, which improves the quality of crack region proposal generation by cascading multi threshold detectors and achieves accurate positioning under high threshold. Finally,a series of optimization parameters and experimental comparison are carried out for the improved model, and the effectiveness of the proposed model is verified. Results: The experimental results show that the mean average precision of C-Mask RCNN model detection part is 95.4%, which is 9.7% higher than that of the conventional model, and the mean average precision of the segmentation part is 93.5%, which is 13.0% higher than that of the conventional model. Conclusions: In summary, the C-Mask RCNN model proposed in this paper can locate and extract cracks with high identification accuracy.

XIAO Liyang, LI Wei, YUAN Bo, CUI Yiqun, GAO Rong, WANG Wenqing. Pavement Crack Automatic Identification Method Based on Improved Mask R-CNN Model[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20210279
Citation: XIAO Liyang, LI Wei, YUAN Bo, CUI Yiqun, GAO Rong, WANG Wenqing. Pavement Crack Automatic Identification Method Based on Improved Mask R-CNN Model[J]. Geomatics and Information Science of Wuhan University. doi: 10.13203/j.whugis20210279
Reference (13)

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return