Article

Article title RECOGNITION OF BURNED AREAS IN MULTISPECTRAL IMAGES USING ADAPTIVE CLOUD MASK
Authors V.G. Bondur, I.A. Matveev, A.B. Murynin, A.N. Trekin
Section SECTION IV. MATHEMATICAL METHODS OF AN ARTIFICIAL INTELLECT
Month, Year 06, 2012 @en
Index UDC 528.854:004.932.2
DOI
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.

Download PDF

Keywords Multispectral images; wildfire recognition; cloud mask.
References 1. Бондур В.Г. Актуальность и необходимость космического мониторинга природных пожаров в России // Вестник ОНЗ РАН, NZ11001. – 2010 (а). – Т. 2.
2. Ackerman S.A., Strabala K.I., Menzel W.P., Frey R.A., Moeller C.C., Gumley L.E., Baum B.A., Schaaf C., Riggs G. 1997: Discriminating clear-sky from cloud with MODIS algorithm theoretical basis document (MOD35). EOS ATBD web site. – 125 p.
3. Айвазян С.А., Бухштабер В.М., Енюков И.С., Мешалкин Л.Д. Прикладная статистика: классификация и снижение размерности. – М.: Финансы и статистика, 1989.
4. Журавлёв Ю.И. Распознавание. Классификация. Прогноз. Математические методы и их применение. Вып. 2. – М.: Наука, 1989.

Comments are closed.