Extending deep learning approaches for forest disturbance segmentation on very high-resolution satellite images

0547965 - BÚ 2022 RIV GB eng J - Článek v odborném periodiku
Kislov, D. E. - Korznikov, K. A. - Altman, Jan - Vozmishcheva, A. S. - Krestov, P. V.
Extending deep learning approaches for forest disturbance segmentation on very high-resolution satellite images.
Remote Sensing in Ecology and Conservation. Roč. 7, č. 3 (2021), s. 355-368. E-ISSN 2056-3485
Grant CEP: GA MŠMT(CZ) LTAUSA19137; GA ČR GJ20-05840Y
Institucionální podpora: RVO:67985939
Klíčová slova: deep learning * forest damage detection * vegetation recognition
Obor OECD: Ecology
Impakt faktor: 5.787, rok: 2021
Způsob publikování: Open access

We used satellite imagery of very high resolution in visual spectra represented as pansharpened images (RGB channels). When predicting forest damage, we obtained accuracies higher than 90% on test data for recognition of both windthrow areas and damaged trees impacted by bark beetles. A comparative analysis indicated that the DCNN-based approach outperforms traditional pixel-based classification methods (AdaBoost, random forest, support vector machine, quadratic discrimination) by at least several percentage points. DCNNs can learn a specific pattern of the area of interest and thus yield fewer false positive decisions than pixel-based algorithms. The ability of DCNNs to generalize makes them a good tool for delineating smooth and ill-defined boundaries of damaged forest areas, such as windthrow patches.
Trvalý link: http://hdl.handle.net/11104/0324138