SEMIAUTOMATED PROCEDURES FOR TREE SPECIES IDENTIFICATION IN HIGH-SPATIAL-RESOLUTION DATA FROM DIGITIZED COLOR INFRARED-AERIAL PHOTOGRAPHY

A semi-automated classification procedure is presented in this paper f or identification of forest species from digitized large-scale, colour -infrared (CIR) aerial photographs to simulate imagery from future sen sors with high spatial resolution capability (below 0.5 m). The applie d computer-assisted classification approaches involving a tree by tree approach consist of basically four steps: the digitization of crown s hapes (polygons); the actual classification within these polygons; the determination of the most frequent class within the polygons; and the filling of the polygons with this particular class. The best result w as achieved with a parallelepiped classifier involving the original ne ar-infrared channel, a texture feature (standard deviation), and four features produced with a principal component/colour enhancement. An av erage of about 80% of the trees could be correctly classified.