Evaluation of Transfer Learning Techniques with Convolutional Neural Networks (CNNs) to Detect the Existence of Roads in High-Resolution Aerial Imagery

  • Calimanut-Ionut CiraEmail author
  • Ramon Alcarria
  • Miguel-Ángel Manso-Callejo
  • Francisco Serradilla
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1051)


Infrastructure detection and monitoring traditionally required manual identification of geospatial objects in aerial imagery but advances in deep learning and computer vision enabled the researchers in the field of remote sensing to successfully apply transfer learning from pretrained models on large-scale datasets for the task of geospatial object detection. However, they mostly focused on objects with clearly defined boundaries that are independent of the background (e.g. airports, airplanes, buildings, ships, etc.). What happens when we have to deal with more complicated, continuous objects like roads? In this paper we will review four of the best-known CNN architectures (VGGNet, Inception-V3, Xception, Inception-ResNet) and apply feature extraction and fine-tuning techniques to detect the existence of roads in aerial orthoimages divided in tiles of 256 × 256 pixels in size. We will evaluate each model´s performance on unseen test data using the accuracy metric and compare the results with those obtained by a CNN especially built for this purpose.


Transfer learning Convolutional neural networks Remote sensing Road detection 



This research received funding from the Cartobot project, in collaboration with Instituto Geográfico Nacional (IGN), Spain. We thank all Cartobot participants for their help in generating the dataset.


  1. 1.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 25, pp. 1097–1105. Curran Associates Inc, Red Hook (2012)Google Scholar
  2. 2.
    Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition, ArXiv14091556 Cs, (September 2014)Google Scholar
  3. 3.
    Szegedy, C., et al.: Going Deeper with Convolutions, ArXiv14094842 Cs, September (2014)Google Scholar
  4. 4.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep Residual Learning for Image Recognition, ArXiv151203385 Cs, December (2015)Google Scholar
  5. 5.
    Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.: Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning, ArXiv160207261 Cs, February (2016)Google Scholar
  6. 6.
    Pritt, M., Chern, G.: Satellite image classification with deep learning, In: 2017 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), pp. 1–7. Washington, DC, USA (2017)Google Scholar
  7. 7.
    Zhou, W., Newsam, S., Li, C., Shao, Z.: PatternNet: a benchmark dataset for performance evaluation of remote sensing image retrieval. ISPRS J. Photogramm. Remote Sens. 145, 197–209 (2018)CrossRefGoogle Scholar
  8. 8.
    Albert, A., Kaur, J., Gonzalez, M.C.: Using convolutional networks and satellite imagery to identify patterns in urban environments at a large scale. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD 2017, pp. 1357–1366. Halifax, NS, Canada, 2017Google Scholar
  9. 9.
    Chollet, F.: Deep Learning with Python. Manning Publications Co, Shelter Island (2018)Google Scholar
  10. 10.
    Cai, B., Jiang, Z., Zhang, H., Zhao, D., Yao, Y.: Airport detection using end-to-end convolutional neural network with hard example mining. Remote Sens. 9(11), 1198 (2017)CrossRefGoogle Scholar
  11. 11.
    Yang, H.L., Yuan, J., Lunga, D., Laverdiere, M., Rose, A., Bhaduri, B.: Building extraction at scale using convolutional neural network: mapping of the United States. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 11(8), 2600–2614 (2018)CrossRefGoogle Scholar
  12. 12.
    Li, Y., Zhang, Y., Huang, X., Yuille, A.L.: Deep networks under scene-level supervision for multi-class geospatial object detection from remote sensing images. ISPRS J. Photogramm. Remote Sens. 146, 182–196 (2018)CrossRefGoogle Scholar
  13. 13.
    Hutchison, D., et al.: Learning to detect roads in high-resolution aerial images. ECCV 2010. LNCS, vol. 6316, pp. 210–223. Springer, Heidelberg (2010). Scholar
  14. 14.
    Zhang, Z., Liu, Q., Wang, Y.: Road Extraction by Deep Residual U-Net. IEEE Geosci. Remote Sens. Lett. 15(5), 749–753 (2018)CrossRefGoogle Scholar
  15. 15.
    Wang, Q., Gao, J., Yuan, Y.: Embedding Structured Contour and Location Prior in Siamesed Fully Convolutional Networks for Road Detection. IEEE Trans. Intell. Transp. Syst. 19(1), 230–241 (2018)CrossRefGoogle Scholar
  16. 16.
    Alshehhi, R., Marpu, P.R., Woon, W.L., Mura, M.D.: Simultaneous extraction of roads and buildings in remote sensing imagery with convolutional neural networks. ISPRS J. Photogramm. Remote Sens. 130, 139–149 (2017)CrossRefGoogle Scholar
  17. 17.
    Henry, C., Azimi, S.M., Merkle, N.: Road segmentation in SAR satellite images with deep fully-convolutional neural networks. IEEE Geosci. Remote Sens. Lett. 15(12), 1867–1871 (2018)CrossRefGoogle Scholar
  18. 18.
    Liu, Y., Yao, J., Lu, X., Xia, M., Wang, X., Liu, Y.: RoadNet: learning to comprehensively analyze road networks in complex urban scenes from high-resolution remotely sensed images. IEEE Trans. Geosci. Remote Sens. 57(4), 2043–2056 (2019)CrossRefGoogle Scholar
  19. 19.
    Luque, B., Morros, J.R., Ruiz-Hidalgo, J.: Spatio-temporal road detection from aerial imagery using CNNs, In: Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications,, pp. 493–500. Porto, Portugal (2017)Google Scholar
  20. 20.
    Woźniak, M., Damaševičius, R., Maskeliūnas, R., Malūkas, U.: Real time path finding for assisted living using deep learning. JUCS - J. Univers. Comput. Sci. 24(4), 475–487 (2018)Google Scholar
  21. 21.
    Xu, Y., Goodacre, R.: On splitting training and validation set: a comparative study of cross-validation, bootstrap and systematic sampling for estimating the generalization performance of supervised learning. J. Anal. Test. 2(3), 249–262 (2018)CrossRefGoogle Scholar
  22. 22.
    May, R.J., Maier, H.R., Dandy, G.C.: Data splitting for artificial neural networks using SOM-based stratified sampling. Neural Netw. 23(2), 283–294 (2010)CrossRefGoogle Scholar
  23. 23.
    Cira, C.I., Alcarria, R., Manso-Callejo, M.A., Serradilla, F.: A deep convolutional neural network to detect the existence of geospatial elements in high-resolution aerial imagery. Proceedings, 19(1), 17 (2019)CrossRefGoogle Scholar
  24. 24.
    Kingma, D.P., Ba, J.: Adam: A Method for Stochastic Optimization, ArXiv14126980 Cs, (December 2014)Google Scholar
  25. 25.
    Chen, X., Liu, S., Sun, R., Hong, M.: On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization, ArXiv180802941 Cs Math Stat, (August 2018)Google Scholar
  26. 26.
    Chollet, F., Xception: Deep Learning with Depthwise Separable Convolutions, ArXiv161002357 Cs, (October 2016)Google Scholar
  27. 27.
    Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks?, ArXiv14111792 Cs, (November 2014)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Universidad Politécnica de MadridMadridSpain

Personalised recommendations