Skip to main content
SpringerLink
Log in

Satellite imagery analysis for road segmentation using U-Net architecture

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Road network plays a significant role in today’s urban development. These are a vital part of applications such as automatic road navigation, traffic management, route optimization, etc. In this paper, we aim to explore the potential and performance of convolution neural network architecture, U-Net, performing semantic segmentation to detect roads. The model has been evaluated on Massachusetts Roads Dataset with the estimation of numerous parameters such as filter stride, learning rate, training epochs, data size, and various augmentation techniques. The employment of the proposed technique and hyperparameters to the U-Net architecture gives a boost to test accuracy and improves the dice coefficient by a value of 0.007. Experimental results thereby demonstrate that our model is computationally efficient and achieves comparable segmentation results.

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

Access this article

Log in via an institution

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

Similar content being viewed by others

References

  1. Abderrahim NYQ, Abderrahim S, Rida A (2020) Road segmentation using u-net architecture. Proc 200 IEEE Int Conf Moroccan Geomatics. https://doi.org/10.1109/Morgeo49228.2020.9121887

  2. Wei Y, Wang Z, Xu M (2017) Road structure refined CNN for road extraction in aerial image. IEEE Geosci Remote Sens Lett 14(5):709–713. https://doi.org/10.1109/LGRS.2017.2672734

    Article  Google Scholar 

  3. Hormese J, Saravanan C (2016) Automated road extraction from high resolution satellite images. Procedia Technol 24:1460–1467. https://doi.org/10.1016/j.protcy.2016.05.180

    Article  Google Scholar 

  4. Ahmadi FF, Zoej MJV, Ebadi H, Mokhtarzade M (2008) Road extraction from high resolution satellite images using image processing algorithms and CAD-Based environments facilities. J Appl Sci 8(17):2975–2982. https://doi.org/10.3923/jas.2008.2975.2982

    Article  Google Scholar 

  5. Panboonyuen T, Jitkajornwanich K, Lawawirojwong S, Srestasathiern P, Vateekul P (2017) Road segmentation of remotely-sensed images using deep convolutional neural networks with landscape metrics and conditional random fields. Remote Sens 9(7):1–19. https://doi.org/10.3390/rs9070680

    Article  Google Scholar 

  6. Hou Y, Liu Z, Zhang T, Li Y (2021) C-UNet: complement UNet for remote sensing road extraction. Sensors 21(6):1–21. https://doi.org/10.3390/s21062153

    Article  Google Scholar 

  7. Chen LC, Zhu Y, Papandreou G, Schroff F, Adam H (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. Lect Notes Comput Sci (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics 11211 LNCS(1): 833–851. https://doi.org/10.1007/978-3-030-01234-2_49

  8. Liu B, Wu H, Wang Y, Liu W (2015) Main road extraction from ZY-3 grayscale imagery based on directional mathematical morphology and VGI prior knowledge in Urban areas. PLoS ONE 10(9):1–16. https://doi.org/10.1371/journal.pone.0138071

    Article  Google Scholar 

  9. Wang W, Yang N, Zhang Y, Wang F, Cao T, Eklund P (2016) A review of road extraction from remote sensing images. J Traffic Transp Eng (English Ed., vol. 3, no. 3, pp. 271–282, 2016. https://doi.org/10.1016/j.jtte.2016.05.005

  10. Song M, Civco D (2004) Road extraction using SVM and image segmentation. Photogramm Eng Remote Sensing 70(12):1365–1371. https://doi.org/10.14358/PERS.70.12.1365

    Article  Google Scholar 

  11. Wegner JD, Montoya-Zegarra JA, Schindler K (2013) A higher-order CRF model for road network extraction. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit: 1698–1705. https://doi.org/10.1109/CVPR.2013.222

  12. Maurya R, Gupta PR, Shukla AS (2011) Road extraction using K-means clustering and morphological operations. ICIIP 2011 - Proc. 2011 Int. Conf. Image Inf. Process. no. Iciip. https://doi.org/10.1109/ICIIP.2011.6108839

  13. Mattyus G, Wang S, Fidler S, Urtasun R (2015) Enhancing road maps by parsing aerial images around the world. Proc IEEE Int Conf Comput Vis 2015 (Inter): 1689–1697. https://doi.org/10.1109/ICCV.2015.197

  14. Mnih V, Hinton GE (2010) Learning to detect roads in high-resolution aerial images. Lect Notes Comput Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics) 6316 LNCS(PART 6): 210–223. https://doi.org/10.1007/978-3-642-15567-3_16

  15. Saito S, Yamashita T, Aoki Y (2016) Multiple object extraction from aerial imagery with convolutional neural networks. J Imaging Sci Technol 60(1):1–9. https://doi.org/10.2352/J.ImagingSci.Technol.2016.60.1.010402

    Article  Google Scholar 

  16. Zhou L, Zhang C, Wu M (2018) D-linknet: linknet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction. IEEE Comput Soc Conf Comput Vis Pattern Recognit Work 2018(June): 192–196. https://doi.org/10.1109/CVPRW.2018.00034

  17. Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. Proc - 30th IEEE Conf Comput Vis Pattern Recognition, CVPR 2017 2017: 6230–6239. https://doi.org/10.1109/CVPR.2017.660

  18. Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 40(4):834–848. https://doi.org/10.1109/TPAMI.2017.2699184

    Article  Google Scholar 

  19. Badrinarayanan V, Kendall A, Cipolla R (2017) https://arxiv.org/pdf/1511.00561.pdf. Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39(12): 2481–2495

  20. Shelhamer E, Long J, Darrell T (2017) Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 39(4):640–651. https://doi.org/10.1109/TPAMI.2016.2572683

    Article  Google Scholar 

  21. Zhong Z, Li J, Cui W, Jiang H (2016) Fully convolutional networks for building and road extraction: Preliminary results. Int Geosci Remote Sens Symp 2016-Novem(July): 1591–1594. https://doi.org/10.1109/IGARSS.2016.7729406

  22. Campos A, Aboshehwa F, Li L, Zhang W (2020) Deep convolutional neural networks for road extraction. 2020 IEEE Green Energy Smart Syst. Conf. IGESSC 2020. https://doi.org/10.1109/IGESSC50231.2020.9285011

  23. Ronneberger O, Fischer P, Brox T (2015) UNet: convolutional networks for biomedical image segmentation. IEEE Access. https://doi.org/10.1109/ACCESS.2021.3053408

    Article  Google Scholar 

  24. Singh P, Dash R (2019) A two-step deep convolution neural network for road extraction from aerial images. 2019 6th Int Conf Signal Process Integr Networks, SPIN 2019: 660–664. https://doi.org/10.1109/SPIN.2019.8711639

  25. Zhang Z, Liu Q, Wang Y (2018) Road extraction by deep residual U-Net. IEEE Geosci Remote Sens Lett 15(5):749–753. https://doi.org/10.1109/LGRS.2018.2802944

    Article  Google Scholar 

  26. Yuan M, Liu Z, Wang F (2019) Using the wide-range attention u-net for road segmentation. Remote Sens Lett 10(5):506–515. https://doi.org/10.1080/2150704X.2019.1574990

    Article  Google Scholar 

  27. Demir I et al. (2018) DeepGlobe 2018: a challenge to parse the earth through satellite images. IEEE Comput Soc Conf Comput Vis Pattern Recognit. Work 2018 (June): 172–181. https://doi.org/10.1109/CVPRW.2018.00031.

  28. Iglovikov V, Shvets A (2018) TernausNet: U-Net with VGG11 encoder pre-trained on ImageNet for image segmentation, [Online]. Available: http://arxiv.org/abs/1801.05746

  29. Van Etten A, Lindenbaum D, Bacastow TM (2018) SpaceNet: a remote sensing dataset and challenge series, [Online]. Available: http://arxiv.org/abs/1807.01232

  30. Fay DL (1967) UNet: Implementation Study. Angewandte Chemie International Edition 6(11): 951–952. https://amaarora.github.io/2020/09/13/unet.html.

  31. Lamba H (2019) Understanding semantic segmentation with UNET. by Harshall Lamba. Towards Data Science. Towards Data Science. https://towardsdatascience.com/understanding-semantic-segmentation-with-unet-6be4f42d4b47

  32. Balraj Ashwath (2020) Aerial images of Massachusetts to aid machine learning for aerial image labeling. https://www.kaggle.com/balraj98/massachusetts-roads-dataset. Accessed June 2021

  33. Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. 3rd Int Conf Learn Represent. ICLR 2015—Conf. Track Proc: 1–15

  34. Oktay O et al. (2018) Attention U-Net: learning where to look for the pancreas. no. Midl, [Online]. Available: http://arxiv.org/abs/1804.03999

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science and Engineering, Sant Longowal Institute of Engineering and Technology, Longowal, Sangrur, Punjab, India

    Vidhi Chaudhary, Preetpal Kaur Buttar & Manoj Kumar Sachan

Authors
  1. Vidhi Chaudhary
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Preetpal Kaur Buttar
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Manoj Kumar Sachan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Preetpal Kaur Buttar.

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

Chaudhary, V., Buttar, P.K. & Sachan, M.K. Satellite imagery analysis for road segmentation using U-Net architecture. J Supercomput 78, 12710–12725 (2022). https://doi.org/10.1007/s11227-022-04379-6

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11227-022-04379-6

Keywords

Search

Navigation