The machine training in problems of satellite images’s processing-Reference-Cited by-同舟云学术

The machine training in problems of satellite images’s processing

Published:2020 Issue:4 Volume: Page:15-37
ISSN:0132-4713
Container-title:Metrologiya
language:
Short-container-title:Metrologiya

Author:

Bass L. P.¹,Plastinin Yu. A.²,Skryabysheva I. Yu.²

Affiliation:

1. Keldysh Institute of Applied Mathematics (Russian Academy of Sciences)

2. Central Research Institute for Machine Building

Abstract

Use of the technical (computer) vision systems for Earth remote sensing is considered. An overview of software and hardware used in computer vision systems for processing satellite images is submitted. Algorithmic methods of the data processing with use of the trained neural network are described. Examples of the algorithmic processing of satellite images by means of artificial convolution neural networks are given. Ways of accuracy increase of satellite images recognition are defined. Practical applications of convolution neural networks onboard microsatellites for Earth remote sensing are presented.

Publisher

FSUE VNIIMS All-Russian Research Institute of Metrological Service

Subject

General Earth and Planetary Sciences,Water Science and Technology,Geography, Planning and Development

Reference19 articles.

1. Borzov S. M., Potaturkin O. I., Optoelectronics, Instrumentation and Data Processing, 2018, vol. 54, nо. 1, pp. 76–82. https://doi.org/10.3103/S8756699018010120

2. Debra Werner, HyperSat reveals hyperspectral plans, available at: https://spacenews.com/hypersat-funds/ (accessed: 05.10.2019).

3. David A. Forsyth, Jean Ponce, Computer Vision: A Modern Approach, Prentice Hall, Upper Saddle River, 2003.

4. Lapshin V. B., Syroeshkin A. V., Minligareev V. T. Mir izmerenii, 2013, no. 9, pp. 37–41 (in Russian).

5. Simonova G. V., Simonov D. P., Inetexpo Geo-Siberia, 2015, vol. 5, no. 3, pp. 42–45 (in Russian).