Skip to main content
SHARE
Publication

Wildfires identification: Semantic segmentation using support vector machine classifier

by Marek Pecha, Zachary L Langford, David Horak, Richard Mills
Publication Type
Conference Paper
Book Title
PANM 21: Programs and Algorithms of Numerical Mathematics. Proceedings of Seminar. Jablonec nad Nisou, June 19-24, 2022
Publication Date
Page Numbers
173 to 186
Issue
2022
Publisher Location
Prague, Czech Republic
Conference Name
PANM 21: Programs and Algorithms of Numerical Mathematics
Conference Location
Prague, Czech Republic
Conference Sponsor
Institute of Mathematics CAS
Conference Date
-

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.