Tree Species Recognition with Fuzzy Texture Parameters

  • Ralf Reulke
  • Norbert Haala
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3322)


The management and planning of forests presumes the availability of up-to-date information on their current state. The relevant parameters like tree species, diameter of the bowl in defined heights, tree heights and positions are usually represented by a forest inventory. In order to allow the collection of these inventory parameters, an approach aiming at the integration of a terrestrial laser scanner and a high resolution panoramic camera has been developed. The integration of these sensors provides geometric information from distance measurement and high resolution texture information from the panoramic images. In order to enable a combined evaluation, in the first processing step a co-registration of both data sets is required. Afterwards geometric quantities like position and diameter of trees can be derived from the LIDAR data, whereas texture parameters are derived from the high resolution panoramic imagery. A fuzzy approach was used to detect trees and differentiate tree species.


Forest Inventory Range Image Combine Evaluation Lidar Data Terrestrial Laser Scanner 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
  2. 2.
    Besl, P.J.: Segmentation through variable order surface fitting. IEEE Transactions on Pattern Analysis and Machine Intelligence 10(2), 167–192 (1988)CrossRefGoogle Scholar
  3. 3.
    Friedlaender, K.B.H.: First experience in the application of laserscanner data for the assessment of vertical and horizontal forest structures. In: IAPRS, Part B7, vol. XXXIII, pp. 693–700 (2000)Google Scholar
  4. 4.
    Haralick, R.M.: Digital step edges from zero-crossings of second directional derivatives. IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-6(1), 58–68 (1984)Google Scholar
  5. 5.
    Pal, S.K., Kundu, M.K.: Automatic selection of object enhancement operator with quantitative justification based on fuzzy set theoretic measures. Pattern Recognition Letters 11, 811–829 (1990)zbMATHCrossRefGoogle Scholar
  6. 6.
    Pietikainen, M.K. (ed.): Texture Analysis in Machine Vision. World Scientific Publishing Company, Singapore (2000)Google Scholar
  7. 7.
    Korsitzky, H., Reulke, R., Scheele, M., Solbrig, M., Scheibe, K.: EYESCAN - a high resolution digital panoramic camera. In: Klette, R., Peleg, S., Sommer, G. (eds.) RobVis 2001. LNCS, vol. 1998, pp. 77–83. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  8. 8.
    Maas, H.-G., Schneider, D.: Geometric modelling and calibration of a high resolution panoramic camera. Optical 3-D Measurement Techniques VI II, 122–129 (2003)Google Scholar
  9. 9.
    Aschoff, T., Spiecker, H., Thies, M., Simonse, M.: Automatic determination of forest inventory parameters using terrestrial laserscanning. In: Proceedings of the ScandLaser Scientific Workshop on Airborne Laser Scanning of Forests, pp. 251–257 (2003)Google Scholar
  10. 10.
    Aschoff, T., Spiecker, H., Thies, M.: Terrestrische laserscanner im forst - für forstliche inventur und wissenschaftliche datenerfassung. AFZ/Der Wald 58 22, 1126–1129 (2003)Google Scholar
  11. 11.
    Gimel’farb, G., Yu, L.: Image retrieval using colour co-occurrence histograms. In: Image and Vision Computing New Zealand 2003, Palmerston North, New Zealand, pp. 42–47 (2003)Google Scholar
  12. 12.
    Zadeh, L.A.: Fuzzy sets as a basis for a theory of possibility. Fuzzy Sets and Systems 1, 3–28 (1978)zbMATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Ralf Reulke
    • 1
  • Norbert Haala
    • 2
  1. 1.Institut für Informatik, Computer VisionHumboldt-Universität zu BerlinBerlinDeutschland
  2. 2.Institut für Photogrammetrie (ifp)Universität StuttgartStuttgartDeutschland

Personalised recommendations