Learning to Detect Roads in High-Resolution Aerial Images
Reliably extracting information from aerial imagery is a difficult problem with many practical applications. One specific case of this problem is the task of automatically detecting roads. This task is a difficult vision problem because of occlusions, shadows, and a wide variety of non-road objects. Despite 30 years of work on automatic road detection, no automatic or semi-automatic road detection system is currently on the market and no published method has been shown to work reliably on large datasets of urban imagery. We propose detecting roads using a neural network with millions of trainable weights which looks at a much larger context than was used in previous attempts at learning the task. The network is trained on massive amounts of data using a consumer GPU. We demonstrate that predictive performance can be substantially improved by initializing the feature detectors using recently developed unsupervised learning methods as well as by taking advantage of the local spatial coherence of the output labels. We show that our method works reliably on two challenging urban datasets that are an order of magnitude larger than what was used to evaluate previous approaches.
KeywordsRoad Network Hide Unit Aerial Image Stochastic Gradient Descent Aerial Imagery
Unable to display preview. Download preview PDF.
- 7.Boggess, J.E.: Identification of roads in satellite imagery using artificial neural networks: A contextual approach. Technical report, Mississippi State University (1993)Google Scholar
- 10.Dollar, P., Tu, Z., Belongie, S.: Supervised learning of edges and object boundaries. In: CVPR 2006: Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1964–1971 (2006)Google Scholar
- 12.Larochelle, H., Bengio, Y., Louradour, J., Lamblin, P.: Exploring strategies for training deep neural networks. Journal of Machine Learning Research 10, 1–40 (2009)Google Scholar
- 14.Norouzi, M., Ranjbar, M., Mori, G.: Stacks of convolutional restricted boltzmann machines for shift-invariant feature learning. In: CVPR (2009)Google Scholar
- 15.Jain, V., Seung, S.: Natural image denoising with convolutional networks. In: Koller, D., Schuurmans, D., Bengio, Y., Bottou, L. (eds.) Advances in Neural Information Processing Systems, vol. 21, pp. 769–776 (2009)Google Scholar
- 16.Mnih, V.: Cudamat: a CUDA-based matrix class for python. Technical Report UTML TR 2009-004, Department of Computer Science, University of Toronto (2009)Google Scholar
- 17.Wiedemann, C., Heipke, C., Mayer, H., Jamet, O.: Empirical evaluation of automatically extracted road axes. In: Empirical Evaluation Techniques in Computer Vision, pp. 172–187 (1998)Google Scholar
- 20.He, X., Zemel, R.S., Carreira-Perpiñán, M.Á.: Multiscale conditional random fields for image labeling. In: CVPR 2004: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 695–702 (2004)Google Scholar
- 21.Peng, T., Jermyn, I., Prinet, V., Zerubia, J.: An extended phase field higher-order active contour model for networks and its application to road network extraction from vhr satellite images. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 509–520. Springer, Heidelberg (2008)CrossRefGoogle Scholar
- 22.Porway, J., Wang, K., Yao, B., Zhu, S.C.: A hierarchical and contextual model for aerial image understanding. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2008)Google Scholar