Technical Physics
To authors
Volumes and Issues
- 2025
- 2024
- 2023
- 2022
The Development of a Synthetic Method for Planetary Object Recognition Based on Neural Networks
Andreev A.O.
1,2, Nefedyev Y.A.
2, Kolosov Y.A.
2
1Kazan State Power Engineering University, Kazan, Russia
2Kazan Federal University, Kazan, Russia
2Kazan Federal University, Kazan, Russia
Email: andreev.alexey93@gmail.com, star1955@yandex.ru, koloyra@gmail.com
The development of a synthetic method for planetary object recognition based on the integration of two architectures, Mask R-CNN and the convolutional neural network (CNN) U-Net, is presented. The proposed method was verified on lunar craters of various categories selected from images obtained by modern satellite missions. Object recognition is performed using criteria such as the ratio of stratigraphic characteristics, morphological features, and optical structure. Keywords: neural networks, planetophysical parameters, synthetic method.
- A. Esteva, B. Kuprel, R.A. Novoa. Nature, 542 (7639), 115 (2017). DOI: 10.1038/nature21056
- A. Silburt, M. Ali-Dib, C. Zhu. Icarus, 317, 27 (2019). DOI: 10.1016/j.icarus.2018.06.022
- C.I. Fassett, J.W. Head, S.J. Kadish. J. Geophys. Research: Planets, 117, E12 (2012). DOI: 10.1029/2011JE003951
- J.W. Head, C.I. Fassett, S.J. Kadish, D.E. Smith, M.T. Zuber, G.A. Neumann, E. Mazarico. Science, 329 (5998), 1504 (2010). DOI: 10.1126/science.1195050
- F. Scholten, J. Oberst, K.-D. Matz, T. Roatsch, M. Wahlisch, E.J. Speyerer, M.S. Robinson. J. Geophys. Research: Planets, 117 (2012). DOI: 10.1029/2011JE003926
- Electronic resource. Available at: http://gisstar.gsi.go.jp/selene/index-E.html
- Electronic resource. Available at: https://astrogeology.usgs.gov/search/map/moon_lro_lola_selene _kaguya_tc_dem_merge_60n60s_59m
Подсчитывается количество просмотров абстрактов ("html" на диаграммах) и полных версий статей ("pdf"). Просмотры с одинаковых IP-адресов засчитываются, если происходят с интервалом не менее 2-х часов.
Дата начала обработки статистических данных - 27 января 2016 г.