Skip to main content

Advertisement

Springer Nature Link
Log in

Semantic segmentation and detection of satellite objects using U-Net model of deep learning

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Deep learning methods are used to analyze satellite images. These satellite images contain many constructed and natural objects, but these are not entirely visible and detectable with naked eyes. Because human eyes can only see and detect the light that falls in the visible range. These satellite images fall beyond the visual scope, thus rendering it impossible for a human. However, after the application of pre-processing techniques and methods of image processing, it can be seen. So, we apply deep learning methods to classify and detect different objects in satellite images and segment them according to their classes. These methods also count class-wise objects using segmentation techniques. Here, only ten predefined classes are considered and classify all objects of a satellite image into these classes. For this, we use the U-Net model of deep learning of image segmentation. The Kaggle dataset of the DSTL competition is used to segment them according to their classes and count their numbers. We measured the performance of models in terms of the Jaccard index, dice coefficient, accuracy, and loss at the time of training and testing. To prove the model’s superiority, we compared it with others’ scores in terms of the Jaccard index. The motivation behind this work is to apply deep learning techniques in satellite imaging analysis for well-being. Because with the help of satellite images, we can know changes in flora and fauna of an area in a particular range of time. This technique also helps monitor disaster management efficiently in flood, fire, and natural calamities where physical presence is impossible. The satellite can monitor all-region effectively. Based on satellite image analysis, accurate and fast decisions can be made economically and efficiently. Thus this research will be beneficial for humankind.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21

Similar content being viewed by others

Notes

  1. https://www.kaggle.com/c/dstl-satellite-imagery-feature-detection/data

References

  1. Aharon M, Elad M, Bruckstein A (2006) K-svd: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Transactions on Signal processing 54(11):4311–4322

    Article  MATH  Google Scholar 

  2. Ahonen T, Hadid A, Pietikäinen M (2004) Face recognition with local binary patterns. In: European conference on computer vision. Springer, pp 469–481

  3. Ahonen T, Hadid A, Pietikainen M (2006) Face description with local binary patterns: application to face recognition. IEEE Transactions on Pattern Analysis & Machine Intelligence 28(12):2037–2041

  4. Ashraf S, Brabyn L, Hicks BJ (2012) Image data fusion for the remote sensing of freshwater environments. Appl Geogr 32(2):619–628

    Article  Google Scholar 

  5. Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE transactions on pattern analysis and machine intelligence 39(12):2481–2495

    Article  Google Scholar 

  6. Benarchid O, Raissouni N (2013) Support vector machines for object based building extraction in suburban area using very high resolution satellite images, a case study: Tetuan, Morocco. IAES International Journal of Artificial Intelligence 2(1)

  7. Bischke B, Helber P, Folz J, Borth D, Dengel A (2019) Multi-task learning for segmentation of building footprints with deep neural networks. In: 2019 IEEE International Conference on Image Processing (ICIP), pp 1480–1484

  8. Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection

  9. Huang B, Lu K, Audeberr N, Khalel A, Tarabalka Y, Malof J, Boulch A, Le Saux B, Collins L, Bradbury K et al (2018) Large-scale semantic classification: outcome of the first year of inria aerial image labeling benchmark. In: IGARSS 2018-2018 IEEE International geoscience and remote sensing symposium. IEEE, pp 6947–6950

  10. Iglovikov V, Mushinskiy S, Osin V (2017) Satellite imagery feature detection using deep convolutional neural network: A kaggle competition. arXiv:1706.06169

  11. Iglovikov V, Shvets A (2018) Ternausnet: U-net with vgg11 encoder pre-trained on imagenet for image segmentation. arXiv:1801.05746

  12. Joachims T (1998) Text categorization with support vector machines: Learning with many relevant features. In: European conference on machine learning. Springer, pp 137–142

  13. Kwarteng P, Chavez A (1989) Extracting spectral contrast in landsat thematic mapper image data using selective principal component analysis, Photogramm. Eng. Remote Sens 55(339-348):1

    Google Scholar 

  14. LeCun Y, Bengio Y , Hinton G (2015) Deep learning. Nature 521(7553):436

    Article  Google Scholar 

  15. Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431–3440

  16. Padwick C, Deskevich M, Pacifici F, Smallwood S (2010) Worlview-2 pan-sharpening, asprs annual convention san diego

  17. Patravali J, Jain S, Chilamkurthy S (2017) 2d-3d fully convolutional neural networks for cardiac mr segmentation. In: International Workshop on Statistical Atlases and Computational Models of the Heart. Springer, pp 130–139

  18. Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention. Springer, pp 234–241

  19. Vakalopoulou M, Karantzalos K, Komodakis N, Paragios N (2015) Building detection in very high resolution multispectral data with deep learning features. In: 2015 IEEE International geoscience and remote sensing symposium (IGARSS). IEEE, pp 1873–1876

  20. Zhang S, Tian Q, Hua G, Huang Q, Li S (2009) Descriptive visual words and visual phrases for image applications. In: Proceedings of the 17th ACM International conference on multimedia. ACM, pp 75–84

Download references

Acknowledgements

Thanks to CSIR for giving me a senior research fellowship (SRF) File No. 09/263(1098)/2016-EMR-I by the grace of which I can do research and write this paper. I also thank all friends, teachers, and relatives who helped me to write this paper and provided such an environment. Without their motivation and help, it was impossible. I also thank Kaggle and DSTL for providing a data set for this research.

Author information

Authors and Affiliations

  1. School of Computer and Systems Sciences, Jawaharlal Nehru University, New Delhi, 110067, India

    Yadavendra & Satish Chand

Authors
  1. Yadavendra
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Satish Chand
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Yadavendra.

Ethics declarations

Conflict of Interests

Yadavendra is a PhD student under the supervision of professor Satish Chand, both belong to Jawaharlal Nehru University, New Delhi, India and have not got any financial benefit from any organisation for this work. Both have not any conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yadavendra, Chand, S. Semantic segmentation and detection of satellite objects using U-Net model of deep learning. Multimed Tools Appl 81, 44291–44310 (2022). https://doi.org/10.1007/s11042-022-12892-2

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-12892-2

Keywords