Investigation of SVM and Level Set Interactive Methods for Road Extraction from Google Earth Images

  • Abolfazl Abdollahi
  • Hamid Reza Riyahi Bakhtiari
  • Mojgan Pashaei Nejad
Research Article


Currently, methods of extracting spatial information from satellite images are mainly based on visual interpretations and drawing the consequences by human factor, which is both costly and time consuming. A large volume of data collected by satellite sensors, and significant improvement in spatial and spectral resolution of these images require the development of new methods for optimal use of these data in order to produce rapid economic and updating road maps. In this study, a new automatic method is proposed for road extraction by integrating the SVM and Level Set methods. The estimated probability of classification by SVM is used as input in Level Set Method. The average of completeness, correctness, and quality was 84.19, 88.69 and 76.06% respectively indicate high performance of proposed method for road extraction from Google Earth images.


Road extraction Google Earth Level set SVM 


  1. Alshehhi, R., & Marpu, P. R. (2017). Hierarchical graph-based segmentation for extracting road networks from high-resolution satellite images. ISPRS Journal of Photogrammetry and Remote Sensing, 126, 245–260.CrossRefGoogle Scholar
  2. Bacher, U. & Mayer, H. (2004). Automatic road extraction from IRS satellite images in agricultural and desert areas. In Proceedings of ISPRS conference (pp. 12–23). Istanbul.Google Scholar
  3. Caddell, R., Hammond, P., & Reinmuth, S. (2009). Roadside features inventory program. In Washington state department of transportation.Google Scholar
  4. Cheng, M., & Weng, Q. (2017). Urban road extraction from combined data sets of high-resolution satellite imagery and lidar data using GEOBIA. In Integrating scale in remote sensing and GIS (p. 283).Google Scholar
  5. Chien, C. L., & Tseng, D. C. (2011). Color image enhancement with exact HIS color model. International Journal of Innovative Computing, Information and Contro, 7(12), 6691–6710.Google Scholar
  6. Christopher, J., & Burges, C. (1998). A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 2, 121–167.CrossRefGoogle Scholar
  7. Gang, X. U., Dawei, Z., & Xinyu, L. (2009). Road extraction in high resolution images from Google Earth. In Proceeding of ICICS09, 7th international conference on information, communications and signal processing, IEEE press piscataway (pp. 556–560). New Jersy.Google Scholar
  8. Huang, X., Lu, Q., & Zhang, L. (2014). A multi-index learning approach for classification of high-resolution remotely sensed images over urban areas. ISPRS Journal of Photogrammetry and Remote Sensing, 90, 36–48.CrossRefGoogle Scholar
  9. Jeyapalan K., & Bhagawati, D. (2000). As built surveys of road side features for GIS, visualization, and virtual reality. International Archives of Photogrammetry and Remote Sensing, 33(Part B5) Amsterdam.Google Scholar
  10. Kass, M., Witkin, A., & Terzopoulos, D. (1988). Snakes: Active contour models. International Journal of Computer Vision, 1(4), 321–331.CrossRefGoogle Scholar
  11. Keaton, T., & Brokish, J. (2002). A level set method for the extraction of roads from multispectral imagery. In Proceedings of the 31st applied imagery pattern recognition workshop (pp. 16–17, 141–147).Google Scholar
  12. Khattak, A. J., Hummer, J. E., & Karimi, H. A. (2000). New and existing roadway inventory data acquisition methods. Journal of Transportation and Statistics, 3(3), 33–46.Google Scholar
  13. Khesali, E., Zoej, M. J. V., Mokhtarzade, M., & Dehghani, M. (2016). Semi automatic road extraction by fusion of high resolution optical and radar images. Journal of the Indian Society of Remote Sensing, 44(1), 21–29.CrossRefGoogle Scholar
  14. Koutsias, N., Karteris, M., & Chuvico, E. (2000). The use of intensity-hue-saturation transformation of Landsat-5 Thematic Mapper data for burned land mapping. Photogrammetric Engineering and Remote Sensing, 66(7), 829–840.Google Scholar
  15. Lehtomäki, M., Jaakkola, A., Hyyppä, J., Kukko, A., & Kaartinen, H. (2010). Detection of vertical pole-like objects in a road environment using vehicle-based laser scanning data. Remote Sensing, 2(3), 641–664.CrossRefGoogle Scholar
  16. Mena, J. B. (2002). Vectorización automática de una imagen binaria mediante K-means degeneración de la triangulación de Delaunay. Revista de la Asociación Española de Teledetección, 17, 21–29.Google Scholar
  17. Miao, Z., Shi, W., Gamba, P., & Li, Z. (2015). An object-based method for road network extraction in VHR satellite images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(10), 4853–4862.CrossRefGoogle Scholar
  18. Mingjun, S., & Daniel, C. (2004). Road extraction using SVM and image segmentation. Photogrammetric Engineering & Remote Sensing., 70(12), 1365–1371.CrossRefGoogle Scholar
  19. Mohammadzadeh A., Tavakoli, A., & Valadan Zoej, M. J. (2004). Automatic linear feature extraction of Iranian roads from high resolution multi spectral satellite imagery. In Proceedings of ISPRS conference (pp. 12–23). Istanbul.Google Scholar
  20. Mokhtarzadeh, M., Waldan, M. J. Z., & Ebadi, H. (2008). The effect of automatic extraction from spatial scale large images using a combination of spectral data and image texture in neural network algorithms, doctoral dissertation in geomatics, photogrammetry. Tehran: K.N.Toosi University of Technology.Google Scholar
  21. Pigeon, L., Solaiman, B., & Toutin, T. (2001). Linear planimetric feature domains modelling for multi-sensors fusion in remote sensing. Proceedings of SPIE AeroSense-International Symposium on Aerospace/Defence Sensing, Simulation, & Controls, Orlando, 4051, 8.Google Scholar
  22. Qhods, V., & Behrad, R. (2010). Identification of road and vehicle detection in aerial images using the intensity of brightness and color. Journal of Research in electric technology, Second year, 2(6), 55–64.Google Scholar
  23. Rajeswari, M., Gurumurthy, K. S., Reddy, L., Omkar, S. N., & Senthilnath, J. (2011). Automatic road extraction based on level set, normalized cuts and mean shift methods. International Journal of Computer Science Issues 8(3), (pp. 1694–0814) No. 2, May 2011 ISSN (Online).Google Scholar
  24. Saati, M., & Amini, J. (2017). Road network extraction from high-resolution SAR imagery based on the network snake model. Photogrammetric Engineering & Remote Sensing, 83(3), 207–215.CrossRefGoogle Scholar
  25. Sghaier, M. O., & Lepage, R. (2016). Road extraction from very high resolution remote sensing optical images based on texture analysis and beamlet transform. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(5), 1946–1958.CrossRefGoogle Scholar
  26. Tang, J., & Zakhor, A. (2011). 3D object detection from roadside data using laser scanners. In IS&T/SPIE Electronic Imaging and International Society for Optics and Photonics (pp. 78640 V–78640 V).Google Scholar
  27. Vapnik, V. N. (1995). The nature of statistical learning theory (p. 188). New York: Springer.CrossRefGoogle Scholar
  28. Wallace, S., Hatcher, M. Priestnall, G. & Morton, R. (2001). Research into a framework for automatic linear feature identi-fication and extraction. In Automatic Extraction of Man-Made Objects from Aerial and Space Images (III) (pp. 381–390). Lisse: Balkema Publishers.Google Scholar
  29. Whitmeyer, S. J. (2012). Google Earth and virtual visualizations in geoscience education and research. In Geological society of America. 11(1390) AP-Science (p. 468 pages).Google Scholar
  30. Wiedemann, C., Heipke, C., Mayer, H., & Hinz, S. (1998). Automatic extraction and evaluation of road networks from MOMS- 2P imagery. International Archives of Photogrammetry and Remote Sensing, 30(3), 285–291.Google Scholar
  31. Yazdan, l A, Waldan, M. J. Z., Ebadi, h, & Mohammad Zadeh, A. (2014). Semi-automatic extraction of building using Snake model from aerial images with high spatial resolution. Research Journal of Survey Science and Technology, 4(2), 179–188.Google Scholar

Copyright information

© Indian Society of Remote Sensing 2017

Authors and Affiliations

  • Abolfazl Abdollahi
    • 1
  • Hamid Reza Riyahi Bakhtiari
    • 2
  • Mojgan Pashaei Nejad
    • 3
  1. 1.Faculty of GeographyKharazmi University of TehranTehranIran
  2. 2.Faculty of Natural Resources and Earth ScienceUniversity of ShahrekordShahrekordIran
  3. 3.Faculty of Natural ResourcesFerdowsi University of MashhadMashhadIran

Personalised recommendations