Advertisement

A Framework for Collecting and Classifying Objects in Satellite Imagery

  • Aswathnarayan Radhakrishnan
  • Jamie Cunningham
  • Jim DavisEmail author
  • Roman Ilin
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11845)

Abstract

A major issue with data-hungry deep learning algorithms is the lack of annotated ground truth for specific applications. The high volume of satellite imagery available today, coupled with crowd-sourced map data can enable a new means for training and classifying objects in wide-area imagery. In this work, we present an automated pipeline for collecting and labeling satellite imagery to facilitate building custom deep learning models. We demonstrate this approach by automatically collecting labeled imagery of solar power plants and building a classifier to detect the structures. This framework can be used to collect labeled satellite imagery of any object mapped by spatial databases.

Keywords

Satellite imagery Data generation Automated ground truthing OpenStreetMap Deep learning Solar power plants 

References

  1. 1.
    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 ACM SIGKDD (2017)Google Scholar
  2. 2.
    Audebert, N., Le Saux, B., Lefèvre, S.: Joint learning from earth observation and openstreetmap data to get faster better semantic maps. In: Proceedings CVPR Workshop: Large Scale Computer Vision for Remote Sensing Imagery (2017)Google Scholar
  3. 3.
    Byers, L., et al.: A global database of power plants. World Resources Institute, p. 18 (2018)Google Scholar
  4. 4.
    Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2017)CrossRefGoogle Scholar
  5. 5.
    European Space Agency: Copernicus Sentinel-2 data (2019). https://sentinel.esa.int/web/sentinel/missions/sentinel-2
  6. 6.
    Ishii, T., et al.: Detection by classification of buildings in multispectral satellite imagery. In: ICPR (2016)Google Scholar
  7. 7.
    Johnson, B.A., Iizuka, K.: Integrating OpenStreetMap crowdsourced data andLandsat time-series imagery for rapid land use/land cover (LULC) mapping: case study of the Laguna de Bay area of the Philippines. Appl. Geogr. 67, 140–149 (2016)CrossRefGoogle Scholar
  8. 8.
    Kaiser, P., Wegner, J.D., Lucchi, A., Jaggi, M., Hofmann, T., Schindler, K.: Learning aerial image segmentation from online maps. IEEE Trans. Geosci. Remote Sensing 55(11), 6054–6068 (2017)CrossRefGoogle Scholar
  9. 9.
    Kussul, N., Lavreniuk, M., Skakun, S., Shelestov, A.: Deep learning classification of land cover and crop types using remote sensing data. IEEE Geosci. Remote Sensing Lett. 14(5), 778–782 (2017)CrossRefGoogle Scholar
  10. 10.
    Nordpil: World database of large urban areas, pp. 1950–2050 (2019). https://nordpil.com/resources/world-database-of-large-cities/
  11. 11.
    OpenStreetMap contributors: Planet dump (2017). https://planet.osm.org, https://www.openstreetmap.org
  12. 12.
  13. 13.
  14. 14.
  15. 15.
    Schultz, M., Voss, J., Auer, M., Carter, S., Zipf, A.: Open land cover from OpenStreetMap and remote sensing. Int. J. Appl. Earth Observ. Geoinf. 63, 206–213 (2017)CrossRefGoogle Scholar
  16. 16.
    SimpleMaps- Pareto Software, LLC: World Cities Database (2019). https://simplemaps.com/data/world-cities
  17. 17.
    Sinergise Ltd.: Modified Copernicus Sentinel data. Sentinel Hub (2019). https://sentinel-hub.com/
  18. 18.
    Sui, D., Goodchild, M., Elwood, S.: Volunteered geographic information, the exaflood, and the growing digital divide. In: Sui, D., Elwood, S., Goodchild, M. (eds.) Crowdsourcing Geographic Knowledge, pp. 1–12. Springer, Dordrecht (2013).  https://doi.org/10.1007/978-94-007-4587-2_1CrossRefGoogle Scholar
  19. 19.
    Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of CVPR (2017)Google Scholar
  20. 20.
    Zhao, W., Bo, Y., Chen, J., Tiede, D., Thomas, B., Emery, W.J.: Exploring semantic elements for urban scene recognition: deep integration of high-resolution imagery and OpenStreetMap (OSM). ISPRS J. Photogram. Remote Sensing 151, 237–250 (2019)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Aswathnarayan Radhakrishnan
    • 1
  • Jamie Cunningham
    • 1
  • Jim Davis
    • 1
    Email author
  • Roman Ilin
    • 2
  1. 1.Ohio State UniversityColumbusUSA
  2. 2.AFRL/RYAP, Wright-Patterson AFBDaytonUSA

Personalised recommendations