Previous |  Up |  Next


Title: Wildfires identification: Semantic segmentation using support vector machine classifier (English)
Author: Pecha, Marek
Author: Langford, Zachary
Author: Horák, David
Author: Tran Mills, Richard
Language: English
Journal: Programs and Algorithms of Numerical Mathematics
Volume: Proceedings of Seminar. Jablonec nad Nisou, June 19-24, 2022
Issue: 2022
Pages: 173-186
Category: math
Summary: 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. (English)
Keyword: wildfire identification
Keyword: semantic segmentation
Keyword: support vector machines
Keyword: distributed training
MSC: 68T09
MSC: 68T45
MSC: 68W15
DOI: 10.21136/panm.2022.16
Date available: 2023-04-13T06:26:38Z
Last updated: 2023-06-05
Stable URL:


Files Size Format View
PANM_21-2022-1_19.pdf 1.444Mb application/pdf View/Open
Back to standard record
Partner of
EuDML logo