Automatic Bird Identification for Offshore Wind Farms

  • Juha NiemiEmail author
  • Juha T. Tanttu


There is a need for automatic bird identification system at offshore wind farms in Finland. The developed system should be able to operate from onshore, which is cost-effective in terms of installations and maintenance. Indubitably, a radar is the obvious choice to detect flying birds, but external information is required for actual identification. A conceivable method is to exploit visual camera images. In the proposed system, the radar detects birds and provides the coordinates to camera steering system. The camera steering system tracks the flying birds, thus enabling capturing a series of images. Classification is based on the images, and it is implemented by a small convolutional neural network trained with a deep learning algorithm. We also propose a data augmentation method in which images are rotated and converted in accordance with the desired color temperatures. The final identification is based on a fusion of data provided by the radar and image data. We present the results of the number of correctly identified species based on manually taken images.


Image classification Deep learning Convolutional neural networks Machine learning Data augmentation 



The authors wish to thank Suomen Hyötytuuli for the financial support and Robin Radar Systems for the technical support with the applied radar system.


  1. 1.
    Baxter, A.T., Robinson, A.P.: A comparison of scavenging bird deterrence techniques at UK landfill sites. Int. J. Pest Manag. 53, pp. 347–356 (2007). Taylor & Francis Online.
  2. 2.
  3. 3.
    All About the Peregrine Falcon. U.S. Fish and Wildlife Service (1999).
  4. 4.
    Statistics. Finnish Meteorological Institute.
  5. 5.
    Robin Radar Models. Robin Radar Systems B.V.
  6. 6.
    Richards, M.A.: Fundamentals of Radar Signal Processing. The McGraw-Hill Companies, New York (2005). ISBN: 0-07-144474-2Google Scholar
  7. 7.
    Bruderer, B.: The Study of Bird Migration by Radar, Part1: The Technical Basis. Naturwissenschaften, vol. 84, pp. 1–8. Springer-Verlag, Heidelberg (1997)Google Scholar
  8. 8.
    Fuzzy Logic Toolbox Documentation. The MathWorks Inc.
  9. 9.
    Mamdani, E.H., Assilian, S.: An experiment in linguistic synthesis with a fuzzy logic controller. Int. J. Man Mach. Stud. 7(1), 1–13 (1975). ElsevierGoogle Scholar
  10. 10.
    Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning, pp. 330–371. MIT Press, Cambridge (2016).
  11. 11.
    Wang, J., Perez, L.: The Effectiveness of Data Augmentation in Image Classification Using Deep Learning. Stanford University, Stanford (2017). Google Scholar
  12. 12.
    Speranskaya, N.I.: Determination of spectrum color co-ordinates for twenty-seven normal observers. Opt. Spectrosc. 7, 424–428 (1959). SpringerGoogle Scholar
  13. 13.
    Stiles, W.S., Burch, J.M.: NPL colour-matching investigation: Final report. Opt. Acta 6, 1–26 (1959). Taylor & FrancisGoogle Scholar
  14. 14.
    Wyszecki, G., Stiles, W.S.: Color Science: Concepts and Methods, Quantitative Data and Formulae, 2nd edn. Wiley, New York (1982)Google Scholar
  15. 15.
    Stockman, A., Sharpe, L.T.: Spectral sensitivities of the middle- and long-wavelength sensitive cones derived from measurements in observers of known genotype. Vis. Res. 40, 1711–1737 (2000). ElsevierGoogle Scholar
  16. 16.
    CIE Proceedings, Vienna Session 1963. Committee Report E-1.4.1, vol. B, pp. 209–220. Bureau Central de la CIE, Paris (1964)Google Scholar
  17. 17.
  18. 18.
    Jarrett, K., Kavukcuoglu, K., Ranzato, M.A., LeCun, Y.: What is the best multi-stage architecture for object recognition. In: International Conference on Computer Vision, pp. 2146–2153. IEEE, Kyoto, Japan (2009)Google Scholar
  19. 19.
    Niemi, J., Tanttu, J.T.: Automatic bird identification for offshore Wind farms: a case study for deep learning. In: Proceedings of ELMAR-2017, 59th IEEE International Symposium ELMAR-2017, Croatian Society Electronics in Marine (2017). ISBN:978-953-184-230-3Google Scholar
  20. 20.
    Huang, J.F., LeCun, Y.: Large-scale learning with SVM and convolutional nets for generic object categorization. In: Computer Vision and Pattern Recognition Conference (CVPR06). IEEE Press, New York, NY (2006)Google Scholar
  21. 21.
    Desholm, M., Kahlert, J.: Avian collision risk at an offshore wind farm. Biol. Lett. 1, 296–298 (2005). The Royal Society Publishing
  22. 22.
    Marques, A.T., et al.: Understanding bird collisions at wind farms: an updated review on the causes and possible mitigation strategies. Biol. Conserv. 179, 40–52 (2014). ElsevierGoogle Scholar
  23. 23.
    Verhoef, J.P., Westra, C.A., Korterink, H., Curvers, A.: WT-Bird A Novel Bird Impact Detection System. ECN Research centre of the Netherlands (2002).
  24. 24.
    Wiggelinkhuizen, E.J., Barhorst, S.A.M., Rademakers, L.W.M.M., den Boon, H.J.: Bird Collision Monitoring System for Multi-Megawatt Wind Turbines, WT-Bird: Prototype Development and Testing. ECN Research Centre of the Netherlands (2006). Google Scholar
  25. 25.
    Wiggelinkhuizen, E.J., den Boon, H.J.: Monitoring of Bird Collisions in Wind Farm Under Offshore-Like Conditions Using WT-BIRD System: Final Report. ECN Research Centre of the Netherlands (2009).
  26. 26.
    DTBird.: Liquen Consultora Ambiental, S.L.
  27. 27.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Signal Processing LaboratoryTampere University of TechnologyPoriFinland
  2. 2.Mathematics LaboratoryTampere University of TechnologyPoriFinland

Personalised recommendations