<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE root>
<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" article-type="other" dtd-version="1.2" xml:lang="en"><front><journal-meta><journal-id journal-id-type="publisher-id">Frontier Materials &amp; Technologies</journal-id><journal-title-group><journal-title xml:lang="en">Frontier Materials &amp; Technologies</journal-title><trans-title-group xml:lang="ru"><trans-title>Frontier Materials &amp; Technologies</trans-title></trans-title-group></journal-title-group><issn publication-format="print">2782-4039</issn><issn publication-format="electronic">2782-6074</issn><publisher><publisher-name xml:lang="en">Togliatti State University</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="publisher-id">872</article-id><article-id pub-id-type="doi">10.18323/2782-4039-2023-3-65-9</article-id><article-categories><subj-group subj-group-type="toc-heading" xml:lang="en"><subject>Articles</subject></subj-group><subj-group subj-group-type="toc-heading" xml:lang="ru"><subject>Статьи</subject></subj-group><subj-group subj-group-type="article-type"><subject></subject></subj-group></article-categories><title-group><article-title xml:lang="en">Determination of the volume fraction of primary carbides in the microstructure of composite coatings using semantic segmentation</article-title><trans-title-group xml:lang="ru"><trans-title>Определение объемной доли первичных карбидов в микроструктуре композиционных покрытий с применением семантической сегментации</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-7598-2980</contrib-id><name-alternatives><name xml:lang="en"><surname>Soboleva</surname><given-names>Natalia N.</given-names></name><name xml:lang="ru"><surname>Соболева</surname><given-names>Наталья Николаевна</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>PhD (Engineering), senior researcher</p></bio><bio xml:lang="ru"><p>кандидат технических наук, старший научный сотрудник</p></bio><email>natashasoboleva@list.ru</email><xref ref-type="aff" rid="aff1"/><xref ref-type="aff" rid="aff2"/></contrib><contrib contrib-type="author"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-7073-6476</contrib-id><name-alternatives><name xml:lang="en"><surname>Mushnikov</surname><given-names>Aleksandr N.</given-names></name><name xml:lang="ru"><surname>Мушников</surname><given-names>Александр Николаевич</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>PhD (Engineering), researcher</p></bio><bio xml:lang="ru"><p>кандидат технических наук, научный сотрудник</p></bio><email>mushnikov@imach.uran.ru</email><xref ref-type="aff" rid="aff1"/></contrib></contrib-group><aff-alternatives id="aff1"><aff><institution xml:lang="en">Institute of Engineering Science of the Ural Branch of RAS, Yekaterinburg</institution></aff><aff><institution xml:lang="ru">Институт машиноведения имени Э.С. Горкунова Уральского отделения РАН, Екатеринбург</institution></aff></aff-alternatives><aff-alternatives id="aff2"><aff><institution xml:lang="en">M.N. Mikheev Institute of Metal Physics of the Ural Branch of RAS, Yekaterinburg</institution></aff><aff><institution xml:lang="ru">Институт физики металлов имени М.Н. Михеева Уральского отделения РАН, Екатеринбург</institution></aff></aff-alternatives><pub-date date-type="pub" iso-8601-date="2023-09-29" publication-format="electronic"><day>29</day><month>09</month><year>2023</year></pub-date><issue>3</issue><issue-title xml:lang="en"/><issue-title xml:lang="ru"/><fpage>95</fpage><lpage>102</lpage><history><date date-type="received" iso-8601-date="2023-09-29"><day>29</day><month>09</month><year>2023</year></date></history><permissions><ali:free_to_read xmlns:ali="http://www.niso.org/schemas/ali/1.0/"/></permissions><self-uri xlink:href="https://vektornaukitech.ru/jour/article/view/872">https://vektornaukitech.ru/jour/article/view/872</self-uri><abstract xml:lang="en"><p>In the process of formation of composite coatings, partial dissolution of strengthening particles (most often carbides) in the matrix is possible; therefore, in some cases, the material creation mode is chosen taking into account the volume fraction of primary carbides not dissolved during coating deposition. The methods currently widely used for calculating the volume fraction of carbides in the structure of composite coatings (manual point method and programs implementing classical computer vision methods) have limitations in terms of the possibility of automation. It is expected that performing semantic segmentation using convolutional neural networks will improve both the performance of the process and the accuracy of carbide detection. In the work, multiclass semantic segmentation was carried out including the classification on the image of pores and areas that are not a microstructure. The authors used two neural networks based on DeepLab-v3 trained with different loss functions (IoU Loss and Dice Loss). The initial data were images of various sizes from electron and optical microscopes, with spherical and angular carbides darker and lighter than the matrix, in some cases with pores and areas not related to the microstructure. The paper presents mask images consisting of four classes, created manually and by two trained neural networks. The study shows that the networks recognize pores, areas not related to the microstructure, and perfectly segment spherical carbides in images, regardless of their color relative to the matrix and the presence of pores in the structure. The authors compared the proportion of carbides in the microstructure of coatings determined by two neural networks and a manual point method.</p></abstract><trans-abstract xml:lang="ru"><p>В процессе формирования композиционных покрытий возможно частичное растворение упрочняющих частиц (чаще всего карбидов) в матрице, поэтому в ряде случаев выбор режима создания материала осуществляется с учетом объемной доли первичных, не растворившихся при нанесении покрытий карбидов. Широко используемые в настоящее время методы расчета объемной доли карбидов в структуре композиционных покрытий (ручной точечный метод и программы, реализующие классические методы машинного зрения) имеют ограничения по возможности автоматизации. Ожидается, что выполнение семантической сегментации с использованием сверточных нейронных сетей повысит как производительность процесса, так и точность определения карбидов. В работе проводилась многоклассовая семантическая сегментация, включающая классификацию на изображении пор и областей, не являющихся микроструктурой. Использовались две нейронные сети на основе DeepLab-v3, обученные с разными функциями потерь (IoU Loss и Dice Loss). Исходными данными были изображения различных размеров с электронного и оптического микроскопов, с карбидами сферической и угловатой формы темнее и светлее матрицы, в ряде случаев – с порами и областями, не относящимися к микроструктуре. В работе представлены изображения-маски, состоящие из четырех классов, созданные вручную и двумя обученными нейронными сетями. Показано, что сети распознают поры, области, не относящиеся к микроструктуре, и отлично сегментируют на изображениях карбиды сферической формы, независимо от их цвета относительно матрицы и наличия пор в структуре. Проведено сравнение доли карбидов в микроструктуре покрытий, определенной двумя нейронными сетями и ручным точечным методом. </p></trans-abstract><kwd-group xml:lang="en"><kwd>composite coatings</kwd><kwd>carbides</kwd><kwd>optical microscopy</kwd><kwd>scanning electron microscopy</kwd><kwd>semantic segmentation</kwd><kwd>neural networks</kwd></kwd-group><kwd-group xml:lang="ru"><kwd>композиционные покрытия</kwd><kwd>карбиды</kwd><kwd>оптическая микроскопия</kwd><kwd>растровая электронная микроскопия</kwd><kwd>семантическая сегментация</kwd><kwd>нейронные сети</kwd></kwd-group><funding-group><funding-statement xml:lang="en">The work was carried out within the state assignment to the Institute of Engineering Science, UB RAS on the topics No. AAAA-A18-118020790147-4 and No. АААА-А18-118020790148-1 and the Institute of Metal Physics, UB RAS on the topic “Additivity” No. 121102900049-1. Microscopic images were obtained using the equipment of the “Plastometry” Core Facility Center of the IES UB RAS. The paper was written on the reports of the participants of the XI International School of Physical Materials Science (SPM-2023), Togliatti, September 11–15, 2023.</funding-statement><funding-statement xml:lang="ru">Работа выполнена в рамках государственных заданий ИМАШ УрО РАН по темам № АААА-А18-118020790147-4 и № АААА-А18-118020790148-1 и ИФМ УрО РАН по теме «Аддитивность» № 121102900049-1. Микроскопические изображения получены с использованием оборудования ЦКП «Пластометрия» ИМАШ УрО РАН. Статья подготовлена по материалам докладов участников XI Международной школы «Физическое материаловедение» (ШФМ-2023), Тольятти, 11–15 сентября 2023 года.</funding-statement></funding-group></article-meta></front><body></body><back><ref-list><ref id="B1"><label>1.</label><citation-alternatives><mixed-citation xml:lang="en">Savrai R.A., Gladkovsky S.V., Lepikhin S.V., Kolobylin Yu.M. Approaches to the development of wear-resistant laminated metal composites. Diagnostics, Resource and Mechanics of materials and structures, 2021, no. 5, pp. 24–35. DOI: 10.17804/2410-9908.2021.5.24-35.</mixed-citation><mixed-citation xml:lang="ru">Savrai R.A., Gladkovsky S.V., Lepikhin S.V., Kolobylin Yu.M. Approaches to the development of wear-resistant laminated metal composites // Diagnostics, Resource and Mechanics of materials and structures. 2021. № 5. P. 24–35. DOI: 10.17804/2410-9908.2021.5.24-35.</mixed-citation></citation-alternatives></ref><ref id="B2"><label>2.</label><citation-alternatives><mixed-citation xml:lang="en">Soboleva N.N., Nikolaeva E.P., Makarov A.V., Malygina I.Yu. The influence of chromium carbide additive on the structure and abrasive wear resistance of the NiCrBSi coating formed by laser cladding. Vektor nauki Tolyattinskogo gosudarstvennogo universiteta, 2020, no. 1, pp. 68–76. DOI: 10.18323/2073-5073-2020-1-68-76.</mixed-citation><mixed-citation xml:lang="ru">Соболева Н.Н., Николаева Е.П., Макаров А.В., Малыгина И.Ю. Влияние добавки карбида хрома на структуру и абразивную износостойкость NiCrBSi покрытия, сформированного лазерной наплавкой // Вектор науки Тольяттинского государственного университета. 2020. № 1. С. 68–76. DOI: 10.18323/2073-5073-2020-1-68-76.</mixed-citation></citation-alternatives></ref><ref id="B3"><label>3.</label><citation-alternatives><mixed-citation xml:lang="en">Pribytkov G.A., Kalita V.I., Komlev D.I. et al. Hardness and wear resistance of plasma coatings sprayed by SHS-TiC + Ti-binder composite powders. Uprochnyayushchie tekhnologii i pokrytiya, 2019, vol. 15, no. 8, pp. 359–364. EDN: MROUSQ.</mixed-citation><mixed-citation xml:lang="ru">Прибытков Г.А., Калита В.И., Комлев Д.И. и др. Твердость и износостойкость плазменных покрытий, напыленных СВС-композиционными порошками TiC + Ti-связка // Упрочняющие технологии и покрытия. 2019. Т. 15. № 8. C. 359–364. EDN: MROUSQ.</mixed-citation></citation-alternatives></ref><ref id="B4"><label>4.</label><citation-alternatives><mixed-citation xml:lang="en">Makarov A.V., Soboleva N.N., Malygina I.Yu., Osintseva A.L. The tribological performances of a NiCrBSi – TiC laser-clad composite coating under abrasion and sliding friction. Diagnostics, Resource and Mechanics of materials and structures, 2015, no. 3, pp. 83–97. DOI: 10.17804/2410-9908.2015.3.083-097.</mixed-citation><mixed-citation xml:lang="ru">Makarov A.V., Soboleva N.N., Malygina I.Yu., Osintseva A.L. The tribological performances of a NiCrBSi – TiC laser-clad composite coating under abrasion and sliding friction // Diagnostics, Resource and Mechanics of materials and structures. 2015. № 3. P. 83–97. DOI: 10.17804/2410-9908.2015.3.083-097.</mixed-citation></citation-alternatives></ref><ref id="B5"><label>5.</label><citation-alternatives><mixed-citation xml:lang="en">Nurminen J., Näkki J., Vuoristo P. Microstructure and properties of hard and wear resistant MMC coatings deposited by laser cladding. International Journal of Refractory Metals and Hard Materials, 2009, vol. 27, no. 2, pp. 472–478. DOI: 10.1016/j.ijrmhm.2008.10.008.</mixed-citation><mixed-citation xml:lang="ru">Nurminen J., Näkki J., Vuoristo P. Microstructure and properties of hard and wear resistant MMC coatings deposited by laser cladding // International Journal of Refractory Metals and Hard Materials. 2009. Vol. 27. № 2. P. 472–478. DOI: 10.1016/j.ijrmhm.2008.10.008.</mixed-citation></citation-alternatives></ref><ref id="B6"><label>6.</label><citation-alternatives><mixed-citation xml:lang="en">Enrici T.M., Dedry O., Boschini F., Tchuindjang J.T., Mertens A. Microstructural and Thermal Characterization of 316L+WC Composite Coatings obtained by Laser Cladding. Advanced Engineering Materials, 2020, vol. 22, no. 12, article number 2000291. DOI: 10.1002/adem.202000291.</mixed-citation><mixed-citation xml:lang="ru">Enrici T.M., Dedry O., Boschini F., Tchuindjang J.T., Mertens A. Microstructural and Thermal Characterization of 316L+WC Composite Coatings obtained by Laser Cladding // Advanced Engineering Materials. 2020. Vol. 22. № 12. Article number 2000291. DOI: 10.1002/adem.202000291.</mixed-citation></citation-alternatives></ref><ref id="B7"><label>7.</label><citation-alternatives><mixed-citation xml:lang="en">Deschuyteneer D., Petit F., Gonon M., Cambier F. Processing and characterization of laser clad NiCrBSi/WC composite coatings – Influence of microstructure on hardness and wear. Surface and Coatings Technology, 2015, vol. 283, pp. 162–171. DOI: 10.1016/j.surfcoat.2015.10.055.</mixed-citation><mixed-citation xml:lang="ru">Deschuyteneer D., Petit F., Gonon M., Cambier F. Processing and characterization of laser clad NiCrBSi/WC composite coatings – Influence of microstructure on hardness and wear // Surface and Coatings Technology. 2015. Vol. 283. P. 162–171. DOI: 10.1016/j.surfcoat.2015.10.055.</mixed-citation></citation-alternatives></ref><ref id="B8"><label>8.</label><citation-alternatives><mixed-citation xml:lang="en">Zhang Z., Liu H.X., Zhang X.W., Ji S.W., Jiang Y.H. Dissolution Behavior of WC Reinforced Particles on Carbon Steel Surface during Laser Cladding Process. Advanced Materials Research, 2012, vol. 430-432, pp. 137–141. DOI: 10.4028/www.scientific.net/AMR.430-432.137.</mixed-citation><mixed-citation xml:lang="ru">Zhang Z., Liu H.X., Zhang X.W., Ji S.W., Jiang Y.H. Dissolution Behavior of WC Reinforced Particles on Carbon Steel Surface during Laser Cladding Process // Advanced Materials Research. 2012. Vol. 430-432. P. 137–141. DOI: 10.4028/www.scientific.net/AMR.430-432.137.</mixed-citation></citation-alternatives></ref><ref id="B9"><label>9.</label><citation-alternatives><mixed-citation xml:lang="en">Xu H., Huang H. Plasma remelting and injection method for fabricating metal matrix composite coatings reinforced with tungsten carbide. Ceramics International, 2022, vol. 48, no. 2, pp. 2645–2659. DOI: 10.1016/j.ceramint.2021.10.048.</mixed-citation><mixed-citation xml:lang="ru">Xu H., Huang H. Plasma remelting and injection method for fabricating metal matrix composite coatings reinforced with tungsten carbide // Ceramics International. 2022. Vol. 48. № 2. P. 2645–2659. DOI: 10.1016/j.ceramint.2021.10.048.</mixed-citation></citation-alternatives></ref><ref id="B10"><label>10.</label><citation-alternatives><mixed-citation xml:lang="en">Kazakov A.A., Kiselev D. Industrial Application of Thixomet Image Analyzer for Quantitative Description of Steel and Alloy’s Microstructure. Metallography, Microstructure, and Analysis, 2016, vol. 5, pp. 294–301. DOI: 10.1007/s13632-016-0289-6.</mixed-citation><mixed-citation xml:lang="ru">Kazakov A.A., Kiselev D. Industrial Application of Thixomet Image Analyzer for Quantitative Description of Steel and Alloy’s Microstructure // Metallography, Microstructure, and Analysis. 2016. Vol. 5. P. 294–301. DOI: 10.1007/s13632-016-0289-6.</mixed-citation></citation-alternatives></ref><ref id="B11"><label>11.</label><citation-alternatives><mixed-citation xml:lang="en">Schneider C.A., Rasband W.S., Eliceiri K.W. NIH Image to ImageJ: 25 years of image analysis. Nature Methods, 2012, vol. 9, pp. 671–675. DOI: 10.1038/nmeth.2089.</mixed-citation><mixed-citation xml:lang="ru">Schneider C.A., Rasband W.S., Eliceiri K.W. NIH Image to ImageJ: 25 years of image analysis // Nature Methods. 2012. Vol. 9. P. 671–675. DOI: 10.1038/nmeth.2089.</mixed-citation></citation-alternatives></ref><ref id="B12"><label>12.</label><citation-alternatives><mixed-citation xml:lang="en">Rose D., Forth J., Henein H., Wolfe T., Qureshi A.J. Automated semantic segmentation of NiCrBSi-WC optical microscopy images using convolutional neural networks. Computational Materials Science, 2022, vol. 210, article number 111391. DOI: 10.1016/j.commatsci.2022.111391.</mixed-citation><mixed-citation xml:lang="ru">Rose D., Forth J., Henein H., Wolfe T., Qureshi A.J. Automated semantic segmentation of NiCrBSi-WC optical microscopy images using convolutional neural networks // Computational Materials Science. 2022. Vol. 210. Article number 111391. DOI: 10.1016/j.commatsci.2022.111391.</mixed-citation></citation-alternatives></ref><ref id="B13"><label>13.</label><citation-alternatives><mixed-citation xml:lang="en">Wang M., Wu F., Zhao J. A Comprehensive Research and Strategy of Transfer Learning for Image Segmentation. Lecture Notes on Data Engineering and Communications Technologies book series, 2021, vol. 88, pp. 1394–1406. DOI: 10.1007/978-3-030-70665-4_152.</mixed-citation><mixed-citation xml:lang="ru">Wang M., Wu F., Zhao J. A Comprehensive Research and Strategy of Transfer Learning for Image Segmentation // Lecture Notes on Data Engineering and Communications Technologies book series. 2021. Vol. 88. P. 1394–1406. DOI: 10.1007/978-3-030-70665-4_152.</mixed-citation></citation-alternatives></ref><ref id="B14"><label>14.</label><citation-alternatives><mixed-citation xml:lang="en">Benjdira B., Bazi Y., Koubaa A., Ouni K. Unsupervised domain adaptation using generative adversarial networks for semantic segmentation of aerial images. Remote Sensing, 2019, vol. 11, no. 11, article number 1369. DOI: 10.3390/rs11111369.</mixed-citation><mixed-citation xml:lang="ru">Benjdira B., Bazi Y., Koubaa A., Ouni K. Unsupervised domain adaptation using generative adversarial networks for semantic segmentation of aerial images // Remote Sensing. 2019. Vol. 11. № 11. Article number 1369. DOI: 10.3390/rs11111369.</mixed-citation></citation-alternatives></ref><ref id="B15"><label>15.</label><citation-alternatives><mixed-citation xml:lang="en">Chen L.C., Papandreou G., Kokkinos I., Murphy K., Yuille A.L. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, vol. 40, pp. 834–848. DOI: 10.1109/TPAMI.2017.2699184.</mixed-citation><mixed-citation xml:lang="ru">Chen L.C., Papandreou G., Kokkinos I., Murphy K., Yuille A.L. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs // IEEE Transactions on Pattern Analysis and Machine Intelligence. 2018. Vol. 40. P. 834–848. DOI: 10.1109/TPAMI.2017.2699184.</mixed-citation></citation-alternatives></ref><ref id="B16"><label>16.</label><citation-alternatives><mixed-citation xml:lang="en">Long J., Shelhamer E., Darrell T. Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 3431–3440. DOI: 10.1109/CVPR.2015.7298965.</mixed-citation><mixed-citation xml:lang="ru">Long J., Shelhamer E., Darrell T. Fully convolutional networks for semantic segmentation // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015. P. 3431–3440. DOI: 10.1109/CVPR.2015.7298965.</mixed-citation></citation-alternatives></ref><ref id="B17"><label>17.</label><citation-alternatives><mixed-citation xml:lang="en">Emelyanov A.V. Analysis of image semantic segmentation methods based on neural networks. Matematicheskie metody v tekhnike i tekhnologiyakh – MMTT, 2019, vol. 12-1, pp. 195–201. EDN: GCGRLL.</mixed-citation><mixed-citation xml:lang="ru">Емельянов А.В. Анализ методов семантической сегментации изображений на основе нейронных сетей // Математические методы в технике и технологиях – ММТТ. 2019. Т. 12-1. С. 195–201. EDN: GCGRLL.</mixed-citation></citation-alternatives></ref><ref id="B18"><label>18.</label><citation-alternatives><mixed-citation xml:lang="en">Chen L.C., Papandreou G., Schroff F., Adam H. Rethinking Atrous Convolution for Semantic Image Segmentation. arXiv:1706.05587, 2017. DOI: 10.48550/arXiv.1706.05587.</mixed-citation><mixed-citation xml:lang="ru">Chen L.C., Papandreou G., Schroff F., Adam H. Rethinking Atrous Convolution for Semantic Image Segmentation // arXiv:1706.05587. 2017. DOI: 10.48550/arXiv.1706.05587.</mixed-citation></citation-alternatives></ref><ref id="B19"><label>19.</label><citation-alternatives><mixed-citation xml:lang="en">Xu H., He H., Zhang Y., Ma L., Li J. A comparative study of loss functions for road segmentation in remotely sensed road datasets. International Journal of Applied Earth Observations and Geoinformation, 2023, vol. 116, article number 103159. DOI: 10.1016/j.jag.2022.103159.</mixed-citation><mixed-citation xml:lang="ru">Xu H., He H., Zhang Y., Ma L., Li J. A comparative study of loss functions for road segmentation in remotely sensed road datasets // International Journal of Applied Earth Observations and Geoinformation. 2023. Vol. 116. Article number 103159. DOI: 10.1016/j.jag.2022.103159.</mixed-citation></citation-alternatives></ref><ref id="B20"><label>20.</label><citation-alternatives><mixed-citation xml:lang="en">Rastorguev D.A., Sevastyanov A.A. Development of turning process digital twin based on machine learning. Vektor nauki Tolyattinskogo gosudarstvennogo universiteta, 2021, no. 1, pp. 32–41. DOI: 10.18323/2073-5073-2021-1-32-41.</mixed-citation><mixed-citation xml:lang="ru">Расторгуев Д.А., Севастьянов А.А. Разработка цифрового двойника процесса точения на основе машинного обучения // Вектор науки Тольяттинского государственного университета. 2021. № 1. С. 32–41. DOI: 10.18323/2073-5073-2021-1-32-41.</mixed-citation></citation-alternatives></ref><ref id="B21"><label>21.</label><citation-alternatives><mixed-citation xml:lang="en">Vik K.V., Druki A.A., Grigorev D.S., Spitsyn V.G. Application of deep learning neural networks for solving the problem of forest fire segmentation on satellite images. Vestnik Tomskogo gosudarstvennogo universiteta. Upravlenie, vychislitelnaya tekhnika i informatika, 2021, no. 55, pp. 18–25. DOI: 10.17223/19988605/55/3.</mixed-citation><mixed-citation xml:lang="ru">Вик К.В., Друки А.А., Григорьев Д.С., Спицын В.Г. Применение нейронных сетей глубокого обучения для решения задачи сегментации лесных пожаров на спутниковых снимках // Вестник Томского государственного университета. Управление, вычислительная техника и информатика. 2021. № 55. С. 18–25. DOI: 10.17223/19988605/55/3.</mixed-citation></citation-alternatives></ref></ref-list></back></article>
