Number of the records: 1
Using the U-Net-like deep convolutional neural networks for precise tree recognition in very high resolution RGB (red, green, blue) satellite images
- 1.0547970 - BÚ 2022 RIV CH eng J - Journal Article
Korznikov, K. A. - Kislov, D. E. - Altman, Jan - Doležal, Jiří - Vozmishcheva, A. S. - Krestov, P. V.
Using the U-Net-like deep convolutional neural networks for precise tree recognition in very high resolution RGB (red, green, blue) satellite images.
Forests. Roč. 12, č. 1 (2021), č. článku 66. E-ISSN 1999-4907
Institutional support: RVO:67985939
Keywords : tree recognition * machine learning * convolutional neural network
OECD category: Ecology
Impact factor: 3.282, year: 2021
Method of publishing: Open access
In this study, we have demonstrated an example of the use of the DL algorithm, relying on the proposed U-Net-like CNN architecture for the recognition of particular tree species in high-resolution RGB satellite images. We showed that traditional pixel-based ML approaches are influenced by false-positive decisions when objects captured in satellite images have the same color composition as tree crowns.
Permanent Link: http://hdl.handle.net/11104/0324109
File Download Size Commentary Version Access AltmanDolezal Forests.pdf 0 7.6 MB Publisher’s postprint open-access
Number of the records: 1