Skip to main content
Book cover

International Conference on Neuroinformatics

NEUROINFORMATICS 2020: Advances in Neural Computation, Machine Learning, and Cognitive Research IV pp 175–183Cite as

Roof Defect Segmentation on Aerial Images Using Neural Networks

Part of the Studies in Computational Intelligence book series (SCI,volume 925)

Abstract

The paper describes usage of deep neural networks for flat roof defect segmentation on aerial images. Such architectures as U-Net, DeepLabV3+ and HRNet+ OCR are studied for recognition five categories of roof defects: “hollows”, “swelling”, “folds”, “patches” and “breaks”. Paper introduces RoofD dataset containing 6400 image pairs: aerial photos and corresponding ground truth masks. Based on this dataset different approaches to neural networks training are analyzed. New SDice coefficient with categorical cross-entropy is studied for precise training of U-Net and proposed light U-NetMCT architecture. Weighted categorical cross-entropy is studied for DeepLabV3+ and HRNet+ OCR training. It is shown that these training methods allow correctly recognize rare categories of defects. The state-of-the-art model multi-scale HRNet+ OCR achieves the best quality metric of 0.44 mean IoU. In sense of inference time the fastest model is U-NetMCT and DeeplabV3+ with worse quality of 0.33–0.37 mean IoU. The most difficult category for segmentation is “patches” because of small amount of images with this category in the dataset. Paper also demonstrates the possibility of implementation of the obtained models in the special software for automation of the roof state examination in industry, housing and communal services.

Keywords

  • Image segmentation
  • Roof defect
  • Aerial image
  • Neural network
  • Deep learning

This is a preview of subscription content, access via your institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-60577-3_20
  • Chapter length: 9 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   219.00
Price excludes VAT (USA)
  • ISBN: 978-3-030-60577-3
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   279.99
Price excludes VAT (USA)
Hardcover Book
USD   279.99
Price excludes VAT (USA)
Learn about institutional subscriptions
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.

References

  1. Kofler, C., Spöck, G., Muhr, R.: Classifying defects in topography images of silicon wafers. In: Winter Simulation Conference (WSC), pp. 3646–3657 (2017)

    Google Scholar 

  2. Soukup, D., Huber-Mörk, R.: Convolutional neural networks for steel surface defect detection from photometric stereo images. Lect. Notes Comput. Sci., vol. 8887, pp. 668 –677 (2014)

    Google Scholar 

  3. Faghih-Roohi, S., et al.: Deep convolutional neural networks for detection of rail surface defects. In: International Joint Conference Neural Networks (IJCNN), pp. 2584–2589 (2016)

    Google Scholar 

  4. Maestro-Watson, D., Balzategui, J., Eciolaza, L., Arana-Arexolaleiba, N.: Deflectometric data segmentation for surface inspection: a fully convolutional neural network approach. J. Electron. Imaging 29(4), 041007 (2020)

    CrossRef  Google Scholar 

  5. Li, S., Zhao, X., Zhou G.: Automatic pixel-level multiple damage detection of concrete structure using fully convolutional network. Comput. Aided Civil Infrastruct. Eng., 34(7), 616–634 (2019)

    Google Scholar 

  6. Yudin, D., Naumov, A., Dolzhenko, A., Patrakova, E.: Software for roof defects recognition on aerial photographs. J. Phys: Conf. Ser. 1015(3), 032152 (2018)

    Google Scholar 

  7. Computer Vision Annotation Tool (CVAT). https://github.com/opencv/cvat. Accessed 10 May 2020

  8. Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28

    CrossRef  Google Scholar 

  9. Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., Jorge Cardoso, M.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Cardoso, M.J., Arbel, T., Carneiro, G., Syeda-Mahmood, T., Tavares, J.M.R.S., Moradi, M., Bradley, A., Greenspan, H., Papa, J.P., Madabhushi, A., Nascimento, J.C., Cardoso, J.S., Belagiannis, V., Lu, Z. (eds.) DLMIA/ML-CDS -2017. LNCS, vol. 10553, pp. 240–248. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-67558-9_28

    CrossRef  Google Scholar 

  10. Yudin, D.A., Skrynnik, A., Krishtopik, A., Belkin, I., Panov, A.I.: Object detection with deep neural networks for reinforcement learning in the task of autonomous vehicles path planning at the intersection. Opt. Memory Neural Networks 28(4), 283–295 (2019). https://doi.org/10.3103/S1060992X19040118

    CrossRef  Google Scholar 

  11. Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833–851. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_49

    CrossRef  Google Scholar 

  12. Yuan, Y., Chen, X., Wang, J.: Object-contextual representations for semantic segmentation. ArXiv, abs/1909.11065 (2019)

    Google Scholar 

  13. Chollet, F.: Xception: deep learning with depthwise separable convolutions. CVPR 2017, arXiv:1610.02357 (2017)

  14. Wang, J., Sun, K., Cheng, T., Jiang, B., Deng, C., Zhao, Y., Liu, D., Mu, Y., Tan, M., Wang, X., Liu, W., Xiao, B.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2020)

    Google Scholar 

Download references

Acknowledgment

Task formulation, RoofD dataset and training approaches of deep neural networks (with modified Dice coefficient and weighted cross-entropy) were developed during the project of Russian Fund of Basic Research No 18-47-310009. Experimental results were obtained during works supported by the Government of the Russian Federation (Agreement No. 075-02-2019-967).

Author information

Authors and Affiliations

  1. Moscow Institute of Physics and Technology, Moscow Region, Institutsky Per. 9, Dolgoprudny, 141700, Russia

    Dmitry A. Yudin & Vasily Adeshkin

  2. Belgorod State Technological University named after V.G. Shukhov, Kostukova Str. 46, Belgorod, 308012, Russia

    Alexandr V. Dolzhenko, Alexandr Polyakov & Andrey E. Naumov

Authors
  1. Dmitry A. Yudin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Vasily Adeshkin
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Alexandr V. Dolzhenko
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Alexandr Polyakov
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Andrey E. Naumov
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dmitry A. Yudin .

Editor information

Editors and Affiliations

  1. Scientific Research Institute for System Analysis, Russian Academy of Sciences, Moscow, Russia

    Prof. Boris Kryzhanovsky

  2. Scientific Research Institute for System Analysis, Russian Academy of Sciences, Moscow, Russia

    Prof. Witali Dunin-Barkowski

  3. Scientific Research Institute for System Analysis, Russian Academy of Sciences, Moscow, Russia

    Prof. Vladimir Redko

  4. Moscow Aviation Institute (National Research University), Moscow, Russia

    Prof. Yury Tiumentsev

Rights and permissions

Reprints and Permissions

Copyright information

© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Yudin, D.A., Adeshkin, V., Dolzhenko, A.V., Polyakov, A., Naumov, A.E. (2021). Roof Defect Segmentation on Aerial Images Using Neural Networks. In: Kryzhanovsky, B., Dunin-Barkowski, W., Redko, V., Tiumentsev, Y. (eds) Advances in Neural Computation, Machine Learning, and Cognitive Research IV. NEUROINFORMATICS 2020. Studies in Computational Intelligence, vol 925. Springer, Cham. https://doi.org/10.1007/978-3-030-60577-3_20

Download citation