ZXi
0e18ee5e2b
* Major upgrade of dependencies and running time 1. Removed the Boost dependency by adopting a newer cut-pursuit version from the authors (resulting in a 5–15× speed improvement). 2. Fixed an issue with the nearest neighbor search caused by an incorrect 2D array order input to the knn_cpp query function. 3. Enabled customization of the number of threads for knn-cpp, yielding a slight speed improvement. 4. Optimized array calculations through enhanced use of STL algorithms. * Change log added * Smoothened the progress bar and added ground detectioned - Improved progress bar increment - Added rapid detection of ground points based on quantile distribution - Added warning of ground points before continuing initial segmentation * Crash fix - Avoided crashes by adding error handling once the maximum component limit is reached - Improved the speed of unique and get_subset functions
TreeIso (plugin)
Individual-tree isolation (treeiso) from terrestrial laser scanning
Zhouxin Xi, Chris Hopkinson (Department of Geography & Environment, University of Lethbridge, Canada)
TreeIso can be utilized to separate individual trees from terrestrial laser scanning point clouds, assigning tree IDs as supplementary scalar fields.
Please cite the following paper if you find this tool helpful:
Xi, Z.; Hopkinson, C. 3D Graph-Based Individual-Tree Isolation (Treeiso) from Terrestrial Laser Scanning Point Clouds. Remote Sens. 2022, 14, 6116. https://doi.org/10.3390/rs14236116
This tool relies on the cut-pursuit algorithm, please also consider citing: Landrieu, L.; Obozinski, G. Cut Pursuit: Fast Algorithms to Learn Piecewise Constant Functions on General Weighted Graphs. SIAM J. Imaging Sci. 2017, 10, 1724–1766. hal link Raguet, H.; Landrieu, L. Cut-pursuit algorithm for regularizing nonsmooth functionals with graph total variation. In Proceedings of the International Conference on Machine Learning, Stockholm, Sweden, 10–15 July 2018; Volume 80, pp. 4247–4256.
The cut-pursuit files are licensed under the MIT license - see the LICENSE-MIT file for details.
A Matlab version shared via: https://github.com/truebelief/artemis_treeiso
The development of the treeiso plugin was inspired by the CSF plugin originating from: Zhang W, Qi J, Wan P, Wang H, Xie D, Wang X, Yan G. An Easy-to-Use Airborne LiDAR Data Filtering Method Based on Cloth Simulation. Remote Sensing. 2016; 8(6):501
Command line mode
Command line is supported. The plugin consists of three stages of segmentation. In the command line mode, please configure the segmentation parameters for each stage to activate the corresponding stage. If no parameters are provided for a specific stage, the segmentation for that stage will not be executed.
Available options
| Command | Description |
|---|---|
-TREEISO |
Runs the TREEISO plugin
Optional settings are:
|
