Refinement of Individual Tree Detection Results Obtained from Airborne Laser Scanning Data for a Mixed Natural Forest

18346 6 99571 2 305482 document 99571 remotesensing-14-05345-v2.pdf application/pdf 71886d86822176be7795cc5ba6cb03cc MD5 3486823 2022-11-07 09:43:41 https://pure.iiasa.ac.at/id/eprint/18346/1/remotesensing-14-05345-v2.pdf 18346 1 1 application/pdf text en public cc_by_4

remotesensing-14-05345-v2.pdf

published 99572 1 305493 document 99572 indexcodes.txt text/x-c++ 262431fd123e6bf4995351e3b81c7428 MD5 15911 2022-11-07 09:53:48 https://pure.iiasa.ac.at/id/eprint/18346/2/indexcodes.txt 18346 2 2 text/x-c++ other Generate index codes conversion from text to indexcodes en public

indexcodes.txt

lightbox.jpg

preview.jpg

medium.jpg

small.jpg

http://eprints.org/relation/isVersionOf https://pure.iiasa.ac.at/id/document/99571 http://eprints.org/relation/isVolatileVersionOf https://pure.iiasa.ac.at/id/document/99571 http://eprints.org/relation/issmallThumbnailVersionOf https://pure.iiasa.ac.at/id/document/99571 archive 353 disk0/00/01/83/46 2022-11-07 09:45:07 2022-11-07 09:45:07 2022-11-07 09:45:07 article show Brodić N. Cvijetinović Ž. Milenkovic M. 2387 Kovačević J. Stančić N. Mitrović M. Mihajlović D. Refinement of Individual Tree Detection Results Obtained from Airborne Laser Scanning Data for a Mixed Natural Forest pub ASA NODES individual tree detection; airborne laser scanning; machine learning; Random Forest; Extreme Gradient Boosting; artificial neural network; Support Vector Machine Numerous semi- and fully-automatic algorithms have been developed for individual tree detection from airborne laser-scanning data, but different rates of falsely detected treetops also accompany their results. In this paper, we proposed an approach that includes a machine learning-based refinement step to reduce the number of falsely detected treetops. The approach involves the local maxima filtering and segmentation of the canopy height model to extract different segment-level features used for the classification of treetop candidates. The study was conducted in a mixed temperate forest, predominantly deciduous, with a complex topography and an area size of 0.6 km × 4 km. The classification model’s training was performed by five machine learning approaches: Random Forest (RF), Extreme Gradient Boosting, Artificial Neural Network, the Support Vector Machine, and Logistic Regression. The final classification model with optimal hyperparameters was adopted based on the best-performing classifier (RF). The overall accuracy (OA) and kappa coefficient (κ) obtained from the ten-fold cross validation for the training data were 90.4% and 0.808, respectively. The prediction of the test data resulted in an OA = 89.0% and a κ = 0.757. This indicates that the proposed method could be an adequate solution for the reduction of falsely detected treetops before tree crown segmentation, especially in deciduous forests. 2022-10-25 published Molecular Diversity Preservation International (MDPI) doi:10.3390/rs14215345 3524 public Remote Sensing 14 21 e5345 TRUE 2072-4292 no info:eu-repo/semantics/article