Original title: Semantic segmentation using support vector machine classifier
Authors: Pecha, Marek ; Langford, Z. ; Horák, David ; Tran Mills, R.
Document type: Papers
Conference/Event: Programs and Algorithms of Numerical Mathematics /21./, Jablonec nad Nisou (CZ), 20220619
Year: 2023
Language: eng
Abstract: This paper deals with wildfire identification in the Alaska regions as a semantic segmentation task using support vector machine classifiers. Instead of colour information represented by means of BGR channels, we proceed with a normalized reflectance over 152 days so that such time series is assigned to each pixel. We compare models associated with $\mathcal{l}1$-loss and $\mathcal{l}2$-loss functions and stopping criteria based on a projected gradient and duality gap in the presented benchmarks.
Keywords: distributed training; semantic segmentation; support vector machines; wildfire identification
Project no.: 847593
Host item entry: Programs and Algorithms of Numerical Mathematics 21 : Proceedings of Seminar, ISBN 978-80-85823-73-8

Institution: Institute of Geonics AS ČR (web)
Document availability information: Fulltext is available at external website.
External URL: https://dml.cz/bitstream/handle/10338.dmlcz/703198/PANM_21-2022-1_19.pdf
Original record: https://hdl.handle.net/11104/0342781

Permalink: http://www.nusl.cz/ntk/nusl-524979


The record appears in these collections:
Research > Institutes ASCR > Institute of Geonics
Conference materials > Papers