vmaitComputational Mathematics and Information TechnologiesComputational Mathematics and Information Technologies2587-8999Донской государственный технический университет10.23947/2587-8999-2022-1-2-70-80vmait-14Research ArticleСтатьиСРАВНИТЕЛЬНОЕ ИССЛЕДОВАНИЕ НЕЙРОННЫХ И ЛОКАЛЬНО- БИНАРНЫХ АЛГОРИТМОВ ИДЕНТИФИКАЦИИ ИЗОБРАЖЕНИЙ ПЛАНКТОННЫХ ПОПУЛЯЦИЙCOMPARATIVE INVESTIGATION OF NEURAL AND LOCALLY BINARY ALGORITHMS FOR IMAGE IDENTIFICATION OF PLANKTON POPULATIONSСухиновА. И.SukhinovA. I.

Сухинов Александр Иванович, член-корреспондент РАН, доктор физико-математических наук, профессор

344000 Ростов-на-Дону, пл. Гагарина, д. 1

Sukhinov Alexander I., corresponding Member of the Russian Academy of Sciences, Doctor of Science in Physics and Maths, Professor

1st Gagarin Square, Rostov-on-Don

sukhinov@gmail.comПанасенкоН. Д.PanasenkoN. D.

Панасенко Наталья Дмитриевна

344000 Ростов-на-Дону, пл. Гагарина, д. 1

Panasenko Natalia D.

1st Gagarin Square, Rostov-on-Don

 

natalija93_93@mail.ruДонской государственный технический университетРоссияDon State Technical UniversityRussian Federation202220022023627080Copyright © Сухинов А.И., Панасенко Н.Д., 20232023Сухинов А.И., Панасенко Н.Д.Sukhinov A.I., Panasenko N.D.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.cmit-journal.ru/jour/article/view/14

Работа посвящена методу «нейросеть-lbp» обработки спутниковых снимков водных прибрежных систем многоспектральной съемки для идентификации фитопланктонных популяций пятнистой структуры: определения их границ, распределения градаций цвета и на основе этого – определение распределения концентраций фитопланктона внутри пятен и расположения центра масс. Исследуется работоспособность и эффективность предложенного метода «нейросеть-lbp» в сравнении с методом, базирующимся на использовании трехслойной нейронной сети. Для анализа привлекается тестовый набор изображений –плоских фигур с достаточно сложными границами, что позволит количественно оценить качество сравниваемых алгоритмов. Результаты работы показывают возрастание точности распознавания на 1,5-3 % при применении предложенного метода.

The work is devoted to the «neural network-lbp» method of processing satellite images of multispectral water coastal systems for identification of phytoplankton populations of spotted structure: determination of their boundaries, distribution of color gradations and, based on this, determination of the distribution of phytoplankton concentrations inside the spots and the location of the center of mass. The efficiency and effectiveness of the proposed neural network-lbp method is investigated in comparison with the method based on the use of a three-layer neural network. For the analysis, a test set of images is involved – flat shapes with rather complex boundaries, which will allow us to quantify the quality of the algorithms being compared. The results of the work show an increase in recognition accuracy by 1.5-3% when using the proposed method.

математическое моделированиелокальные бинарные шаблонынейронная сетьмелководный водоемданные спутникового зондированияmathematical modelinglocal binary patternsneural networkshallow water reservoirsatellite sensing dataИсследование выполнено при поддержке Российского научного фонда (проект 20-01-00421)The research was supported by the Russian Science Foundation (project 20-01-00421)ReferencesLeontyev A L, Nikitina A V and Chumak M I Application of assimilation and filtration methods for satellite water sensing data for plankton population evolution processes predictive modeling Computational Mathematics and Information Technologies 2020 vol 1 №1 pp 1-11 doi:10.23947/2587-8999-2020-1-1-1-11Leontyev A L, Nikitina A V and Chumak M I Application of assimilation and filtration methods for satellite water sensing data for plankton population evolution processes predictive modeling Computational Mathematics and Information Technologies 2020 vol 1 №1 pp 1-11 doi:10.23947/2587-8999-2020-1-1-1-11Panasenko, N.D., Poluyan, A.Y., Motuz, N.S. Algorithm for monitoring the plankton population dynamics based on satellite sensing data // Journal of Physics: Conference Series. 2021. pp. 2131(3),032052Panasenko, N.D., Poluyan, A.Y., Motuz, N.S. Algorithm for monitoring the plankton population dynamics based on satellite sensing data // Journal of Physics: Conference Series. 2021. pp. 2131(3),032052Marchuk G I, Paton B E, Korotaev G K and Zalesny V B Data-computing technologies: a new stage in the development of operational oceanography Izvestiya. Atmospheric and Oceanic Physics 2013vol 49 № 6 pp 579-591 doi: 10.7868/S0002351513060114Marchuk G I, Paton B E, Korotaev G K and Zalesny V B Data-computing technologies: a new stage in the development of operational oceanography Izvestiya. Atmospheric and Oceanic Physics 2013vol 49 № 6 pp 579-591 doi: 10.7868/S0002351513060114Dymnikov V.P., Tyrtyshnikov E.E., Lykossov V.N., Zalesny V.B.Mathematical modeling of climate, dynamics atmosphere and ocean: to the 95th anniversary of g. i. marchuk and the 40th anniversary of the inm ras // Izvestiya, Atmospheric and Oceanic Physics. 2020. Т. 56. № 3. pp. 215-217.Dymnikov V.P., Tyrtyshnikov E.E., Lykossov V.N., Zalesny V.B.Mathematical modeling of climate, dynamics atmosphere and ocean: to the 95th anniversary of g. i. marchuk and the 40th anniversary of the inm ras // Izvestiya, Atmospheric and Oceanic Physics. 2020. Т. 56. № 3. pp. 215-217.Shutyaev V P Methods for observation data assimilation in problems of physics of atmosphere and ocean Izvestiya Atmospheric and Oceanic Physics 2019 vol 55 № 1 pp 17-31 doi: 10.31857/S0002-351555117-34Shutyaev V P Methods for observation data assimilation in problems of physics of atmosphere and ocean Izvestiya Atmospheric and Oceanic Physics 2019 vol 55 № 1 pp 17-31 doi: 10.31857/S0002-351555117-34Shutyaev V P, Parmuzin E I, and Le Dimet F X 2020 Sensitivity of response functions in variational data assimilation for joint parameter and initial state estimation Journal of Computational and Applied Mathematics vol 373 112368 doi: 10.1016/j.cam.2019.112368Shutyaev V P, Parmuzin E I, and Le Dimet F X 2020 Sensitivity of response functions in variational data assimilation for joint parameter and initial state estimation Journal of Computational and Applied Mathematics vol 373 112368 doi: 10.1016/j.cam.2019.112368Agoshkov V I, Lezina N R, Parmuzin E I, ... and Shutyaev V P, Zakharova N B Methods of variational data assimilation with application to problems of hydrothermodynamics of marine water areas Russian Journal of Numerical Analysis and Mathematical Modelling 2020 vol 35 №4 pp 189-202 doi: 10.1515/rnam-2020-0016Agoshkov V I, Lezina N R, Parmuzin E I, ... and Shutyaev V P, Zakharova N B Methods of variational data assimilation with application to problems of hydrothermodynamics of marine water areas Russian Journal of Numerical Analysis and Mathematical Modelling 2020 vol 35 №4 pp 189-202 doi: 10.1515/rnam-2020-0016Sukhinov A. A., G. B. Ostrobrod. Efficient Face Detection on Epiphany Multicore Processor // Computational mathematics and information technologies. 2017. V.1. № 1. pp. 113-127.Sukhinov A. A., G. B. Ostrobrod. Efficient Face Detection on Epiphany Multicore Processor // Computational mathematics and information technologies. 2017. V.1. № 1. pp. 113-127.Sukhinov A I, Atayan A M, Belova Yu V, V.N. Litvinov, Nikitina A V and Chistyakov A E Data processing of field measurements of expedition research for mathematical modeling of hydrodynamic processes in the Azov Sea Computational Continuum Mechanics 2020 vol 13 №2 pp 161-174 doi:10.7242/1999-6691/2020.13.2.13Sukhinov A I, Atayan A M, Belova Yu V, V.N. Litvinov, Nikitina A V and Chistyakov A E Data processing of field measurements of expedition research for mathematical modeling of hydrodynamic processes in the Azov Sea Computational Continuum Mechanics 2020 vol 13 №2 pp 161-174 doi:10.7242/1999-6691/2020.13.2.13Sukhinov A I, Chistyakov A E, Kuznetsova I Y, Protsenko E A, Strazhko A V and Atayan A M Parallel algorithms for modelling of suspended particles motion in channel for large peclet number Short articles and descriptions of posters. 2020. Parallel computing technologies (PAWT'2020) 2020pp100-108.Sukhinov A I, Chistyakov A E, Kuznetsova I Y, Protsenko E A, Strazhko A V and Atayan A M Parallel algorithms for modelling of suspended particles motion in channel for large peclet number Short articles and descriptions of posters. 2020. Parallel computing technologies (PAWT'2020) 2020pp100-108.Atayan AM, Nikitina AV, Sukhinov AI, Chistyakov AE (2022) Mathematical modeling of hazardous phenomena of a natural nature in a shallow reservoir. Journal of Computational Mathematics and Mathematical Physics vol 62 №2: pp. 270-288. Doi: 10.31857/S0044466921120048Atayan AM, Nikitina AV, Sukhinov AI, Chistyakov AE (2022) Mathematical modeling of hazardous phenomena of a natural nature in a shallow reservoir. Journal of Computational Mathematics and Mathematical Physics vol 62 №2: pp. 270-288. Doi: 10.31857/S0044466921120048Sukhinov A I Precision hydrodynamic models and experience of their application in prediction and reconstruction of emergency situations in the Azov Sea Izvestia TRTU 2006 №3(58) pp 228-235Sukhinov A I Precision hydrodynamic models and experience of their application in prediction and reconstruction of emergency situations in the Azov Sea Izvestia TRTU 2006 №3(58) pp 228-235Sukhinov A I and Sukhinov A A Reconstruction of 2001 ecological disaster in the Azov sea on the basis of precise hydrophysics models Parallel Computational Fluid Dynamics 2004: Multidisciplinary Applications 2005 pp 231-238 doi:10.1016/B978-044452024-1/50030-0Sukhinov A I and Sukhinov A A Reconstruction of 2001 ecological disaster in the Azov sea on the basis of precise hydrophysics models Parallel Computational Fluid Dynamics 2004: Multidisciplinary Applications 2005 pp 231-238 doi:10.1016/B978-044452024-1/50030-0Bondur V G, Ivanov V A, Vorobyev V E, Dulov V A, Dolotov V V, Zamshin V V, Kondratiev S I, Lee M E and Malinovsky V V Ground-to-Space Monitoring of Anthropogenic Impacts on the Coastal Zone of the Crimean Peninsula Physical Oceanography 2020 vol 27 № 1 pp 95-107 doi:10.22449/0233-7584-2020-1-103-115Bondur V G, Ivanov V A, Vorobyev V E, Dulov V A, Dolotov V V, Zamshin V V, Kondratiev S I, Lee M E and Malinovsky V V Ground-to-Space Monitoring of Anthropogenic Impacts on the Coastal Zone of the Crimean Peninsula Physical Oceanography 2020 vol 27 № 1 pp 95-107 doi:10.22449/0233-7584-2020-1-103-115Bondur V G, Vorobyev V E and Murynin A B Retrieving sea wave spectra using high resolution satellite imageryunder various conditions of wave generation Exploration of the Earth from space 2020 vol 3 pp 45-58 doi:10.31857/S0205961420030021Bondur V G, Vorobyev V E and Murynin A B Retrieving sea wave spectra using high resolution satellite imageryunder various conditions of wave generation Exploration of the Earth from space 2020 vol 3 pp 45-58 doi:10.31857/S0205961420030021Bondur V G, Zamshin V V, Zamshina A Sh and Vorobyev V E Registering from space the features of deep wastewater outfalls into coastal water areas due to discharge collector breaks Exploration of the Earth from space 2020vol 2 pp 3-14 doi: 10.31857/S0205961420020025Bondur V G, Zamshin V V, Zamshina A Sh and Vorobyev V E Registering from space the features of deep wastewater outfalls into coastal water areas due to discharge collector breaks Exploration of the Earth from space 2020vol 2 pp 3-14 doi: 10.31857/S0205961420020025Bondur VG Satellite Monitoring and Mathematical Modelling of Deep Runoff Turbulent Jets in Coastal Water Areas. In Waste Water-Evaluation and Management; Rijeka, Croatia: 2011 pp. 155–180.Bondur VG Satellite Monitoring and Mathematical Modelling of Deep Runoff Turbulent Jets in Coastal Water Areas. In Waste Water-Evaluation and Management; Rijeka, Croatia: 2011 pp. 155–180.The official website of NASA Worldview worldview.earthdata.nasa.govThe official website of NASA Worldview worldview.earthdata.nasa.govThe official website of Roscosmos Geoportal, www.gptl.ruThe official website of Roscosmos Geoportal, www.gptl.ruThe official website of Earth observing system, eos.com/landviewer/account/pricingThe official website of Earth observing system, eos.com/landviewer/account/pricingProcess JPEG photos online, https://www.imgonline.com.ua/similarity-percent.phpProcess JPEG photos online, https://www.imgonline.com.ua/similarity-percent.phpRu Python, https://www.rupython.com/1313-1313.htmlRu Python, https://www.rupython.com/1313-1313.html

The authors declare that there are no conflicts of interest present.