A new method to accurately and automatically recognize tree species from terrestrial laser scanner data might be applied to automate timber measurements during felling, selection of trees to be felled and, optimization ofReconstructed tree models can be stored in a database. Source: Natural Resources Institute Finland cutting.

Researchers from Tampere University of Technology and the Natural Resources Institute Finland developed a method to extract individual trees from forest plot level point cloud data, so that the structure of their crowns can be reconstructed as comprehensive 3-D models. The created tree models consist of consecutive cylinders, which determine the structure of the tree stem and branches as well as the branching structure.

Species recognition was based on 15 classification features, the values of which were calculated for each tree. Values can now be calculated more accurately, as information about the tree’s entire crown is available. Furthermore, the magnitude of the testing data far exceeds any previous study (see video).

Three different classification methods were applied to birch, pine, and spruce, three of the most common tree species in Finland.

“According to our results, automatic species recognition is possible with more than 95% accuracy...however, several combinations produced good results and all the classification methods had a maximum accuracy over 95%,”says Markku Åkerblom, member of the research team and a researcher at TUT.

In the future, the developed method will be tested with more tree species and with measurements taken from more diverse forests. The tree models calculated based on the laser scanning data can be stored in a database, which can be utilized for even more accurate species recognition when the number of included samples grows.