WILDFIRES IDENTIFICATION: SEMANTIC SEGMENTATION USING SUPPORT VECTOR MACHINE CLASSIFIER

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F23%3A10257433" target="_blank" >RIV/61989100:27240/23:10257433 - isvavai.cz</a>
Result on the web
<a href="https://dml.cz/handle/10338.dmlcz/703198" target="_blank" >https://dml.cz/handle/10338.dmlcz/703198</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.21136/panm.2022.16" target="_blank" >10.21136/panm.2022.16</a>

Result language
angličtina
Original language name
WILDFIRES IDENTIFICATION: SEMANTIC SEGMENTATION USING SUPPORT VECTOR MACHINE CLASSIFIER
Original language description
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 l1-loss and l2-loss functions and stopping criteria based on a projected gradient and duality gap in the presented benchmarks.
Czech name
—
Czech description
—

Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Programs and Algorithms of Numerical Mathematics 21 : Jablonec nad Nisou, June 19-24, 2022 : proceedings of seminar
ISBN
978-80-85823-73-8
ISSN
—
e-ISSN
—
Number of pages
13
Pages from-to
173-185
Publisher name
Institute of Mathematics, Academy of Sciences of the Czech Republic
Place of publication
Praha
Event location
Jablonec nad Nisou
Event date
Jun 19, 2022
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—

Similar results(10)