Распознавание выгоревших территорий на мультиспектральных изображениях с адаптируемой маской облачности
Year: 2012
Type: article
Abstract: Estimation of areas burned as result of wildfires is an important problem in Earth remote sensing. Two approaches can be exploited: recognition of fire itself and recognition of burned areas. Recognition of visible fires is quite reliable however not every fire is visible due to clouds. Recognition of burned areas can be done for any point of surface in the moment when it is not covered with clouds, but the precision is low. Combination of the two methods is proposed, particularly by using data on fires obtained by the first approach to construct the classifier to be used in second method. It is necessary to effectively discriminate images areas covered with clouds. Peculiarities of using MODIS cloud mask in these tasks are studied.
Language: Russian
Topic: Fire effects on ecosystems
Subfield: Global and Planetary Change
Field: Environmental Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W658246981
