Cognitive technologies for processing optical images of high spatial and spectral resolution
V.V. Kozoderov1, E.V. Dmitriev2, V.P. Kamentsev3
1LomonosovMoscow State University, GSP-1, Leninskie Gory, Moscow, 119991, Russia
2The Institute of Numerical Mathematics of the Russian Academy of Sciences, Gubkin str., 8, Moscow, 119333, Russia
3Tver State University, 170100, 33, Zhelyabova, Tver
Keywords: remote sensing, optical images, pattern recognition, forest canopies of various species and age
Abstract
Main stages of development of technologies for natural and anthropogenic objects recognition (cognitive technologies for optical images processing) using remote sensing data are considered together with computational procedures of atmospheric correction of multispectral and hyperspectral airspace images. Main attention is paid to recognition of forest ecosystems of various species and age, based on in-flight testing of a domestic imaging spectrometer for a selected test area, where ground-based forest inventory and other observations were carried out. High accuracies of the recognition of separate gradations of ages for the selected pure birch and pine species are revealed, using the elaborated softwave for airborne hyperspectral image processing.
|
