Road Extraction using Deep Learning

  • Authors

    • J. D. Dorathi Jayaseeli
    • D. Malathi
    • Gopika S
    2018-10-02
    https://doi.org/10.14419/ijet.v7i4.10.27923
  • Remote Sensing Data, Road Extraction, Roadmaps, Features, Classification Methods, Artificial Neural Network

  • Abstract

    The Road extraction from aerial image, stands as a quintessential node for the development of rudimentary layers in innumerable fields. From GIS, to Unmanned Aerial vehicles, road maps pave the foundation for data accumulation. This significant process is a result of number of mechanisms devised over the years through iterative experiments and research.  However, the glut of methods available often pose as a hurdle in the selection process. In this project we implement a novel approach to solve the extraction problem, by incorporating generative algorithm using conditional adversarial networks. We investigate conditional adversarial networks as a general-purpose solution to image-to-image translation problems. These networks not only learn the mapping from input image to output image, but also learn a loss function to train this mapping. This makes it possible to apply the same generic approach to problems that traditionally would require very different loss formulations. The U-Network incorporated essentially convolves and de-convolves over the generative model, thus producing a pixel to pixel image translation, the result of which is the vector road map of its corresponding aerial image. The entire model is trained on a 990 MS GPU for computational ease. 

     

     

  • References

    1. [1] Abraham L., Sasikumar M., “A fuzzy-based road network extraction from degraded satellite images,†International Conference on Advances in Computing, Communications and Informatics, Mysore, 2013.

      [2] Anil P.N., Natarajan S., “A novel approach using active contour model for semi-automatic road extraction from high-resolution satellite imagery,†In Second International Conference on Machine Learning and Computing, Shijiazhuang, 2010.

      [3] Barzohar, M., Cooper, D.B., “The automatic finding of main roads in aerial images by using geometric-stochastic models and estimation,â€. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 18, No.7, (1996), pp. 707-721.

      [4] Caparrini F., E. Caporali and F. Castelli, “Neural network analysis of satellite images for land cover discrimination Mediterranean Storms,†Proceedings of the EGS Plinius Conference held at Maratea, Italy, 1999.

      [5] Baumgartner A., Steger C., Mayer H., “Automatic road extraction based on multi-scale, grouping, and context,†Photogrammetric Engineering and Remote Sensing, Vol.65, No. 7, (1999), pp.777-785.

      [6] Ghule Swati A., and T. Rajani Mangala, "Road Network Extraction Using Support Vector Machines," International Journal of Scientific & Engineering Research, Vol. 6, No. 10, (October-2015), pp.521-526.

      [7] Cem U., Beril S., “Road network detection using probabilistic and graph theoretical methods,†IEEE Transactions on Geoscience and Remote Sensing, Vol. 50, No. 11, (2012), pp. 4441-4453.

      [8] Chen Z., “Research on High-resolution RS Image Classification Technology,†(Ph.D thesis). Chinese Academy of Science, Beijing. 2006.

      [9] Fua P. and Leclerc Y.G., “Model driven edge detection,†Machine Vision and Application, Vol. 3, No. 1, (1990), pp. 45- 56.

      [10] Heermann P.D., Khazenie N., “Classification of multispectral remote sensing data using a backpropagation neural network,†IEEE Transactions on Geoscience and Remote Sensing, Vol. 30, No.1, (1992), pp.81-88.

      [11] Hinz S. and Baumgartner A, “Automatic extraction of urban road networks from multi-view aerial imagery,†ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 58, No.1, (2003), pp. 83-98.

      [12] Hu J., Razdan A., Femiani J.C., “Road network extraction and intersection detection from aerial images by tracking road footprints,†IEEE Transactions on Geoscience and Remote Sensing, Vol. 45, No. 12, (2007), pp. 4144-4157.

      [13] Isola P, Zhu JY, Zhou T, Efros A., “Image-to-image translation with conditional adversarial networks,†arXiv preprint.in CVPR (2017).

      [14] Kirthika A., Mookambiga A., “Automated road network extraction using artificial neural network,†In IEEE International Conference on Recent Trends in Information Technology, Chennai, (2011).

      [15] Hangzhou Liu, J. and Wang H.Q., “An interactive image segmentation method based on graph theory,†Journal of Electronics and Information Technology, Vol. 8, No. 30, (2008), pp. 1973-1976.

      [16] Melgani, F., Bruzzone L., “Classification of hyper-spectral remote sensing images with support vector machines,†IEEE Transactions on Geoscience and Remote Sensing, Vol. 42, No. 8, (2004), pp. 1778-1790.

      [17] Miao Z.L., Wang B. and Shi W., “A semi-automatic method for road centerline extraction from VHR images,†IEEE Geoscience and Remote Sensing Letters, Vol. 11, No. 11, (2014), pp.1856-1860.

      [18] Mnih Volodymyr., "Machine learning for aerial image labeling" Ph.D diss., University of Toronto (Canada), (2013).

      [19] Mokhtarzade M. and Valadanzoej M.J., “Road detection from high-resolution satellite imagery using artificial neural networksâ€, International Journal of Applied Earth Observation and Geoinformation, Vol. 9, No.1, (2007), pp. 32-40.

      [20] Ronneberger O, Fischer P, Brox T. U-net, “Convolutional networks for biomedical image segmentationâ€, In International Conference on Medical image computing and computer-assisted intervention (2015), pp. 234-241.

      [21] Simler C., “An improved road and building detector on VHR images,†In International Geoscience and Remote Sensing Symposium, Vancouver, (2011).

      [22] Tu-Ko K., “A Hybrid Road Identification System Using Image Processing Techniques and Backpropagation Neural Network,†Mississippi State University, Starkville, (2003).

      [23] Tupin F., Maitre H. and Mangin J.F., “Detection of linear features in SAR images: application to road network extraction,†IEEE Transaction on Geoscience and Remote Sensing, Vol. 36, No. 2, (1998), pp. 434-453.

      [24] Wang J.H., Qin Q.M. and Yang X., “Automated road extraction from multi-resolution images using spectral information and texture,†In International Geoscience and Remote Sensing Symposium, Quebec City, (2014).

      [25] Wang M. and Luo J.C., “Extracting roads based on Gauss Markov random field texture model and support vector machine from high-resolution RS image,†IEEE Transaction on Geoscience and Remote Sensing, Vol. 9, No. 3, (2005), pp. 271-276.

      [26] Wang Y., Zheng Q., “Recognition of roads and bridges in SAR Images,†Pattern Recognition, Vol. 31, No. 7, (1998), pp. 953-962.

      [27] Yager N., Sowmya A., “Support vector machines for road extraction from remotely sensed images,†In Petkov, N.,Westenberg, M.A. (Eds.), Computer Analysis of Images and Patterns, Springer, Heidelberg, (2003.), pp. 285-292.

      [28] Yang C., Duraiswami R., Dementhon D., “Mean-shift analysis using quasi-newton methods,†In IEEE International Conference on Image Processing, Barcelona, (2003).

      [29] Yousif O., Ban Y.F., “Improving SAR-based urban change detection by combining MAP-MRF classifier and nonlocal means similarity weights,†Journal of Selected Topics in Applied Earth Observation and Remote Sensing, Vol. 7, No. 10, (2014), pp. 4288-4300.

      [30] Zhu C.Q., Wang G.Y. and Ma Q.H., “Extracting roads based on morphological segmentation from RS image,†Journal of Surveying and Mapping, Vol. 33, No. 4, (2004), pp. 347-351.

      [31] Zhu D.M., Wen X. and Ling C.L., “Road extraction based on the algorithm of MRF and hybrid model of SVM and FCM,†In International Symposium on Image and Data Fusion, Tengchong, (2011).

  • Downloads

  • How to Cite

    D. Dorathi Jayaseeli, J., Malathi, D., & S, G. (2018). Road Extraction using Deep Learning. International Journal of Engineering & Technology, 7(4.10), 1079-1084. https://doi.org/10.14419/ijet.v7i4.10.27923

    Received date: 2019-02-25

    Accepted date: 2019-02-25

    Published date: 2018-10-02