|
Trudy SPIIRAN, 2013, Issue 29, Pages 190–200
(Mi trspy651)
|
|
|
|
Neural technological approach to automated recognition of ground objects in images of space systems for remote sensing of the Earth
S. Pushkarskiya, E. Korneychukb, I. Vinogradovb a Open Joint Stock Company "Scientific and Production Corporation "REKOD "
b Space Systems Research and Development Institute, Khrunichev State Research and Production Space Center, Yubileinii
Abstract:
In this paper the ability to use neurocomputer technology to imaging remote sensing system are considered. The modeling of object classification is reviewed. The sequence and contents of the main stages of the construction of the neural network architecture are discussed. The spectral characteristics of different ground objects are used for classification and recognition of objects in satellite images. Comparative analysis of different types of neural networks in the classification of ground objects is given.
Keywords:
processing of satellite images, pattern recognition, neural networks, remote sensing of the Earth.
Received: 14.05.2013
Citation:
S. Pushkarskiy, E. Korneychuk, I. Vinogradov, “Neural technological approach to automated recognition of ground objects in images of space systems for remote sensing of the Earth”, Tr. SPIIRAN, 29 (2013), 190–200
Linking options:
https://www.mathnet.ru/eng/trspy651 https://www.mathnet.ru/eng/trspy/v29/p190
|
Statistics & downloads: |
Abstract page: | 344 | Full-text PDF : | 183 | References: | 43 | First page: | 1 |
|