TREE DETECTION IN URBAN REGIONS FROM AERIAL IMAGERY AND DSM BASED ON LOCAL MAXIMA POINTS

In this study, we propose an automatic approach for tree detection and classification in registered 3-band aerial images and associated digital surface models (DSM). This problem is especially challenging when trees are in close proximity to each other or to other objects such as rooftops in the scenes. This study presents a method for locating individual trees and estimation of crown size based on local maxima from DSM accompanied by color and texture information. For this purpose, segment level classifier trained via Neural Networks for 10 classes and classification results are improved by using Digital Terrain Model (DTM) and the class probabilities of neighbour segments. Later, the tree classes under a certain height were eliminated using the DTM. For the tree classes, local maxima points are obtained and the tree radius estimate is made from the vertical and horizontal height profiles passing through these points. We obtained a candidate tree list that contains some overlapping trees. The final tree list containing the centers and radius of the trees is obtained by selecting from the list of tree candidates according to a selection parameter. Tree classification and localization results are competitive over limited number of train sets used in this study.