(44-4) 18 * << * >> * Russian * English * Content * All Issues

Semantic segmentation of satellite images of airports using convolutional neural networks
V.A. Gorbachev 1, I.A. Krivorotov 1,2, A.O. Markelov 1,2, E.V. Kotlyarova 2

State Research Institute of Aviation Systems (SSC of RF), Moscow, Russia,
Moscow Institute of Physics and Technology (State University), Moscow, Russia

 PDF, 2671 kB

DOI: 10.18287/2412-6179-CO-636

Pages: 636-645.

Full text of article: Russian language.

The paper is devoted to the development of an effective semantic segmentation algorithm for automation of airport infrastructure labelling in RGB satellite images. This task is addressed using algorithms based on deep convolutional artificial neural networks, as they have proven themselves in a wide range of tasks, including the terrestrial imagery segmentation, where they show consistently high results. A new dataset was labelled for this particular task and a comparative analysis of different architectures and backbones was carried out. A conditional random field model (CRF) was used for postprocessing and accounting of contextual information and neighborhood of objects of different classes in order to eliminate outliers. Features of the solutions applied at all preparatory stages of the algorithm were described, including data preparation, neural network training and post-processing of the training results.

semantic segmentation, artificial neural networks, deep learning, image processing.

Gorbachev VA, Krivorotov IA, Markelov AO, Kotlyarova EV. Semantic segmentation of satellite images of airports using convolutional neural networks. Computer Optics 2020; 44(4): 636-645. DOI: 10.18287/2412-6179-CO-636.

The work was supported by the Russian Foundation of Basic Research under grant No. 17-08-00191.


  1. ISPRS 2D semantic labeling contest. Source: <http://www2.isprs.org/commissions/comm3/wg4/semantic-labeling.html>.
  2. Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 2017; 39(4): 640-651.
  3. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. Source: <https://arxiv.org/pdf/1409.1556.pdf>.
  4. Kaiming H, Xiangyu Z, Shaoqing R, Jian S. Deep residual learning for image recognition. IEEE Conf Comp Vis Pattern Recogn (CVPR) 2016: 770-778.
  5. Badrinarayanan V, Kendall A, Cipolla R. SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 2017; 39(12): 2481-2495.
  6. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. Med Image Comput Comput Assist Interv 2015; 1(3): 234-241.
  7. Chaurasia A, Culurciello E. LinkNet: Exploiting encoder representations for efficient semantic segmentation. IEEE VCIP 2017: 1-4.
  8. Chen L-Ch, Papandreou G, Kokkinos I, Murphy K, Yuille AL. Deep Lab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 2018; 40(4): 834-848.
  9. Zhang H, Zhang H, Wang C, Xie J. Co-occurrent features in semantic segmentation. IEEE CVPR 2019: 548-557.
  10. Hengshuang Z, Jianping S, Xiaojuan Q, Xiaogang W, Jiaya J. Pyramid scene parsing network. IEEE CVPR 2017: 2881-2890.
  11. Lin G, Milan A, Shen Ch, Reid I. RefineNet: Multi-path refinement networks for high-resolution semantic segmentation. IEEE CVPR 2019: 5168-5177.
  12. Fu J, Liu H, Tian H, Fang Z, Lu H. Dual attention network for scene segmentation. IEEE CVPR 2019: 3146-3154.
  13. Kaiming H, Gkioxari G, Dollar P, Girshick R. Mask R-CNN. IEEE ICCV 2017: 2980-2988.
  14. Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y. Generative adversarial nets. Proc NIPS'14 2014: 2672-2680.
  15. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. IEEE CVPR 2015: 2818-2826.
  16. Sandler M, Howard AG, Zhu M, Zhmoginov A, Chen L-C. MobileNetV2: Inverted residuals and linear bottlenecks. IEEE CVPR 2018: 4510-4520.
  17. Tan M, Le QV. EfficientNet: Rethinking model scaling for convolutional neural networks. ICML 2019: 6105-6114.
  18. Carole HS, Wenqi L, Vercauteren T, Ourselin S, Cardoso MJ. Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations. Deep Learn Med Image Anal Multimodal Learn Clin Decis Support 2017: 240-248.
  19. Lin T, Goyal P, Girshick R, Kaiming H, Dollar P. Focal loss for dense object detection. IEEE ICCV 2017: 2999-3007.
  20. Blokhinov YB, Gorbachev VA, Rakutin YO, Nikitin AD. A real-time semantic segmentation algorithm for aerial imagery. Computer Optics 2018; 42(1): 141-148. DOI: 10.18287/2412-6179-2018-42-1-141-148.
  21. ImageNet large scale visual recognition competition 2014. Source: <http://image-net.org/challenges/ LSVRC/2014/>.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: ko@smr.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20