Deep Learning Architecture U-Net Based Road Network Detection from Remote Sensing Images


Miral Patel
Hasmukh P Koringa


Roads are the foundation of human civilisation and one of the most important routes of transportation. For the city planning, vehicle traffic control, road network monitoring, map updating and GPS navigation, the study of road extraction is extremely important. Due to similar spectral characteristics, occlusion of buildings and trees present in remote sensing images makes to extract the road surface is challenging task. This paper address the road network detection based on deep learning sementic segmentation architecture such as U-Net and SegNet from Remote Sensing Images (RSI). Publically available dataset is used to train the U-Net and SegNet. These methods are tuned with various hyper parameters such as learning rate, batch size and epochs. The performance of the methods is also observed under various optimization algorithm like SGD and ADAM. The suggested method performance is measured by training and testing accuracy, total training time, inference time, average iou score and average dice score.


How to Cite
Patel, M., & Hasmukh P Koringa. (2023). Deep Learning Architecture U-Net Based Road Network Detection from Remote Sensing Images. International Journal of Next-Generation Computing, 14(3).


  1. Alshehhi, R., Marpu, P. R., Woon, W. L., and Dalla Mura, M. 2017. Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks. ISPRS Journal of Photogrammetry and Remote Sensing 130, 139–149. DOI:
  2. Anil, P. and Natarajan, S. 2010. A novel approach using active contour model for semiautomatic road extraction from high resolution satellite imagery. In 2010 Second International Conference on Machine Learning and Computing. IEEE, 263–266. DOI:
  3. Badrinarayanan, V., Kendall, A., and Cipolla, R. 2017. ” segnet: A deep convolutional encoder-decoder architecture for image segmentation,” in ieee transactions on pattern analysis and machine intelligence, vol. 39, no. 12, pp. 2481-2495, dec. 1. DOI:
  4. Bakhtiari, H. R. R., Abdollahi, A., and Rezaeian, H. 2017. Semi automatic road extraction from digital images. The Egyptian Journal of Remote Sensing and Space Science 20, 1, 117–123. DOI:
  5. Chen, Z. and Chen, Z. 2017. Rbnet: A deep neural network for unified road and road boundary detection. In Neural Information Processing: 24th International Conference, ICONIP 2017, Guangzhou, China, November 14-18, 2017, Proceedings, Part I 24. Springer, 677–687. DOI:
  6. Cheng, G., Wang, Y., Xu, S., Wang, H., Xiang, S., and Pan, C. 2017. Automatic road detection and centerline extraction via cascaded end-to-end convolutional neural network. IEEE Transactions on Geoscience and Remote Sensing 55, 6, 3322–3337. DOI:
  7. Ghasemloo, N., Mobasheri, M. R., Zare, A. M., and Eftekhari, M. M. 2013. Road and tunnel extraction from spot satellite images using neural networks. DOI:
  8. Hormese, J. and Saravanan, C. 2016. Automated road extraction from high resolution satellite images. Procedia Technology 24, 1460–1467. DOI:
  9. Liu, R., Miao, Q., Song, J., Quan, Y., Li, Y., Xu, P., and Dai, J. 2019. Multiscale road centerlines extraction from high-resolution aerial imagery. Neurocomputing 329, 384–396. DOI:
  10. Liu, Y., Yao, J., Lu, X., Xia, M., Wang, X., and Liu, Y. 2018. Roadnet: Learning to comprehensively analyze road networks in complex urban scenes from high-resolution remotely sensed images. IEEE Transactions on Geoscience and Remote Sensing 57, 4, 2043–2056. DOI:
  11. Patel, M. J. and KotharI, A. 2022. Road network extraction methods from remote sensing images: A review paper. International Journal of Next-Generation Computing 13, 2. DOI:
  12. Patel, M. J. and Kothari, A. M. 2022. Deep learning-enabled road segmentation and edgecenterline extraction from high-resolution remote sensing images. International Journal of Image and Graphics, 2350058. DOI:
  13. Ronneberger, O., Fischer, P., and Brox, T. 2015. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention. Springer, 234–241. DOI:
  14. Senchuri, R., Kuras, A., and Burud, I. 2021. Machine learning methods for road edge detection on fused airborne hyperspectral and lidar data. In 2021 11th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS). IEEE, 1–5. DOI:
  15. Shamsolmoali, P., Zareapoor, M., Zhou, H., Wang, R., and Yang, J. 2020. Road segmentation for remote sensing images using adversarial spatial pyramid networks. IEEE Transactions on Geoscience and Remote Sensing 59, 6, 4673–4688. DOI:
  16. Shen, J., Lin, X., Shi, Y., and Wong, C. 2008. Knowledge-based road extraction from high resolution remotely sensed imagery. In 2008 Congress on Image and Signal Processing. Vol. 4. IEEE, 608–612. DOI:
  17. Ting, K. M. 2010. Confusion matrix, pages 209–209. springer us, boston. Vincent, L. and Soille, P. 1991. Watersheds in digital spaces: an efficient algorithm based on immersion simulations. IEEE Transactions on Pattern Analysis & Machine Intelligence 13, 06, 583–598. DOI:
  18. Wang, D. 1997. A multiscale gradient algorithm for image segmentation using watershelds. Pattern recognition 30, 12, 2043–2052. DOI:
  19. Wang, W., Yang, N., Zhang, Y., Wang, F., Cao, T., and Eklund, P. 2016. A review of road extraction from remote sensing images. Journal of traffic and transportation engineering (english edition) 3, 3, 271–282. DOI:
  20. Wei, Y. and Ji, S. 2021. Scribble-based weakly supervised deep learning for road surface extraction from remote sensing images. IEEE Transactions on Geoscience and Remote Sensing 60, 1–12. DOI:
  21. Wei, Y., Zhang, K., and Ji, S. 2020. Simultaneous road surface and centerline extraction from large-scale remote sensing images using cnn-based segmentation and tracing. IEEE Transactions on Geoscience and Remote Sensing 58, 12, 8919–8931. DOI:
  22. Xin, J., Zhang, X., Zhang, Z., and Fang, W. 2019. Road extraction of high-resolution remote sensing images derived from denseunet. Remote Sensing 11, 21, 2499. DOI:
  23. Xu, G., Zhang, D., and Liu, X. 2009. Road extraction in high resolution images from google earth. In 2009 7th International Conference on Information, Communications and Signal Processing (ICICS). IEEE, 1–5. DOI:
  24. Zhang, Z., Liu, Q., and Wang, Y. 2018. Road extraction by deep residual u-net. IEEE Geoscience and Remote Sensing Letters 15, 5, 749–753. DOI: