Development of methodology for identification of tree species in mixed Latvian forests from LiDAR and multispectral data supplied by the customer. Used for forest inventory on the invidual tree level. EDI developed a method for classification of individual tree species based on two-stage Bayes approach. Published in: R. Dinuls, G. Erins, A. Lorencs, I. Mednieks, and J. Sinica-Sinavskis, “Tree species identification in mixed Baltic forest using LiDAR and multispectral data,” IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 5, no. 2, pp. 594–603, 2012.

Customer: LLC Forest Owners Consulting Center (www.mikc.lv)

Software package HyperEDI was developed within the project, featuring:

  • Multispectral and LiDAR data import / informative viewing
  • Choosing analysis & viewing parameters
  • Selection of analysis area
  • Definition of species
  • Training from known field data
  • Choosing design trees (analysis of spectra, RGB images)
  • Checking design set for representativeness
  • Clusterization (taking random trees from analysis regions)
  • Classification based on clusters’ parameters
  • Tree species identification
  • Viewing and comparing spectra of pixels, trees and regions