Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B3, 575-582, 2016
https://doi.org/10.5194/isprs-archives-XLI-B3-575-2016
© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.
 
09 Jun 2016
AUTOMATIC TREE-CROWN DETECTION IN CHALLENGING SCENARIOS
Dimitri Bulatov, Isabell Wayand, and Hendrik Schilling Fraunhofer IOSB, Department Scene Analysis, Gutleuthausstr., 1, 76265, Ettlingen, Germany
Keywords: 3D-modeling, Classification, Hotspots detection, Surface reconstruction, Tree, Watershed Transformation Abstract. In this paper, a new procedure for individual tree detection and modeling is presented. The input of this procedure consists of a normalized digital surface model NDSM, and a possibly error-prone classification result. The procedure is modular so that the functionality, the advantages and the disadvantages for every single module will be explained. The most important technical contributions of the paper are: Employing watershed transformation combined with classification results, applying hotspots detectors for identifying treetops in groups of trees, and correcting NDSM by detecting and geometric reconstruction of small anomalies, such as earth walls. Two minor contributions are made up by a detailed literature research on available methods for individual tree detection and estimation of tree-crowns for clearly identified trees in order to reduce arbitrariness by assigning trees to one of the few types in the output model.
Conference paper (PDF, 4744 KB)


Citation: Bulatov, D., Wayand, I., and Schilling, H.: AUTOMATIC TREE-CROWN DETECTION IN CHALLENGING SCENARIOS, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B3, 575-582, https://doi.org/10.5194/isprs-archives-XLI-B3-575-2016, 2016.

BibTeX EndNote Reference Manager XML