Version 1
: Received: 30 August 2024 / Approved: 2 September 2024 / Online: 2 September 2024 (16:57:35 CEST)
How to cite:
Silva, D. A.; dos Santos, D. R. Individual Urban Trees Clustering in LiDAR Data with 3-D Gestalt Measures. Preprints2024, 2024090117. https://doi.org/10.20944/preprints202409.0117.v1
Silva, D. A.; dos Santos, D. R. Individual Urban Trees Clustering in LiDAR Data with 3-D Gestalt Measures. Preprints 2024, 2024090117. https://doi.org/10.20944/preprints202409.0117.v1
Silva, D. A.; dos Santos, D. R. Individual Urban Trees Clustering in LiDAR Data with 3-D Gestalt Measures. Preprints2024, 2024090117. https://doi.org/10.20944/preprints202409.0117.v1
APA Style
Silva, D. A., & dos Santos, D. R. (2024). Individual Urban Trees Clustering in LiDAR Data with 3-D Gestalt Measures. Preprints. https://doi.org/10.20944/preprints202409.0117.v1
Chicago/Turabian Style
Silva, D. A. and Daniel Rodrigues dos Santos. 2024 "Individual Urban Trees Clustering in LiDAR Data with 3-D Gestalt Measures" Preprints. https://doi.org/10.20944/preprints202409.0117.v1
Abstract
Despite the technological advancements of 3-D city models, the 3-D shape abstraction methods for urban vegetation are recent and still limited to support spatial analysis of individual or groups of trees and forest patches. In this paper, a scheme for individual urban tree abstraction, which retains the semantic complexity of the object, is proposed. Our contribution is three-fold. First, an initial tree structure based on a new 3-D aggregation operator is proposed. Second, we developed Gestalt rules for 3-D urban vegetation mapping. Third, current state-of-the-art deep learning is adapted for the abstraction of individual urban trees. Quantitative and qualitative results show the effectiveness of our proposed approach in accurately reducing the spatial density of trees and the degree of fragmentation of the total green area, which can access information about the location, size, and spatial distribution of mapped urban trees.
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.