Roof Defect Segmentation on Aerial Images Using Neural Networks

Dmitry A. Yudin, Vasily Adeshkin, Alexandr V. Dolzhenko, Alexandr Polyakov, Andrey E. Naumov

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish
Title of host publicationAdvances in Neural Computation, Machine Learning, and Cognitive Research IV - Selected Papers from the 22nd International Conference on Neuroinformatics, 2020
EditorsBoris Kryzhanovsky, Witali Dunin-Barkowski, Vladimir Redko, Yury Tiumentsev
PublisherSpringer Science and Business Media Deutschland GmbH
Pages175-183
Number of pages9
ISBN (Print)9783030605766
DOIs
Publication statusPublished - 2021
Externally publishedYes
Event22nd International Conference on Neuroinformatics, 2020 - Moscow, Russian Federation
Duration: 12 Oct 202016 Oct 2020

Publication series

NameStudies in Computational Intelligence
Volume925 SCI
ISSN (Print)1860-949X
ISSN (Electronic)1860-9503

Conference

Conference22nd International Conference on Neuroinformatics, 2020
Country/TerritoryRussian Federation
CityMoscow
Period12/10/2016/10/20

Keywords

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

Fingerprint

Dive into the research topics of 'Roof Defect Segmentation on Aerial Images Using Neural Networks'. Together they form a unique fingerprint.

Cite this