期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2004
卷号：XXXVI-8/W2
出版社：Copernicus Publications
摘要：Analysis of terrestrial laser point clouds in a 3D voxel space has been applied recently during a cooperation between Delft University of Technology and the Institute for Forest Growth (IWW) in Freiburg. The purpose was 3D model reconstruction of trees in a forest. Forest experts can use these, for example to calculate the wood volume and other geometric parameters, allowing to draw conclusions about the timber quality. The reconstruction of the tree crowns is the basis for investigations about he vitality or the competitive status of forest tress. The ability to create explorable three-dimensional models of the forest stands is another goal of this approach. A crucial phase in the reconstruction process is segmentation of the laser points according to the different branches of the tree. As a result, to each point a label is assigned that is unique for each branch, whereas points are removed (labeled 0) that do not belong to the stem or a significant branch (leafs, twigs, noise). The problem resembles that of recognizing linear structures is 2- dimensional imagery, such as roads in aerial photography. Therefore we decided to tackle it in a similar manner, i.e. by transferring a variety of image processing operators to the 3D domain, such as erosion, dilation, overlay, skeletonization, distance transform and connected component labeling. Also Dijkstra's shortest-route algorithm plays an important role during the reconstruction
