<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" 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" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">tinro</journal-id><journal-title-group><journal-title xml:lang="ru">Известия ТИНРО</journal-title><trans-title-group xml:lang="en"><trans-title>Izvestiya TINRO</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">1606-9919</issn><issn pub-type="epub">2658-5510</issn><publisher><publisher-name>ТИНРО</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.26428/1606-9919-2025-205-518-534</article-id><article-id custom-type="elpub" pub-id-type="custom">tinro-1066</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>МЕТОДИКА ИССЛЕДОВАНИЙ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>METHODS OF INVESTIGATIONS</subject></subj-group></article-categories><title-group><article-title>Автоматизация беспилотного учета производителей кеты и кижуча методами искусственного интеллекта</article-title><trans-title-group xml:lang="en"><trans-title>Automation of unmanned counting for spawners of chum and coho salmon with methods of artificial intelligence</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-6060-1532</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Свиридов</surname><given-names>В. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Sviridov</surname><given-names>V. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Свиридов Владимир Владимирович, кандидат биологических наук, ведущий научный сотрудник</p><p>680038, г. Хабаровск, Амурский бульвар, 13а</p></bio><bio xml:lang="en"><p>Vladimir V. Sviridov, Ph.D., leading researcher</p><p>13a, Amursky Blvd, Khabarovsk, 680038</p></bio><email xlink:type="simple">sviridov@khabarovsk.vniro.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0000-7664-7458</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Поваров</surname><given-names>А. Ю.</given-names></name><name name-style="western" xml:lang="en"><surname>Povarov</surname><given-names>A. Yu.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Поваров Андрей Юрьевич, заведующий сектором</p><p>680038, г. Хабаровск, Амурский бульвар, 13а</p></bio><bio xml:lang="en"><p>Andrey Yu. Povarov, head of sector</p><p>13a, Amursky Blvd, Khabarovsk, 680038</p></bio><email xlink:type="simple">povarov@khabarovsk.vniro.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-7123-1792</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Коцюк</surname><given-names>Д. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Kotsyuk</surname><given-names>D. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Коцюк Денис Владимирович, кандидат биологических наук, руководитель филиала</p><p>680038, г. Хабаровск, Амурский бульвар, 13а</p></bio><bio xml:lang="en"><p>Denis V. Kotsyuk, Ph.D., director</p><p>13a, Amursky Blvd, Khabarovsk, 680038</p></bio><email xlink:type="simple">kotsyuk@khabarovsk.vniro</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Хабаровский филиал ВНИРО (ХабаровскНИРО)</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Khabarovsk branch of VNIRO (KhabarovskNIRO)</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>09</day><month>10</month><year>2025</year></pub-date><volume>205</volume><issue>3</issue><fpage>518</fpage><lpage>534</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Свиридов В.В., Поваров А.Ю., Коцюк Д.В., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Свиридов В.В., Поваров А.Ю., Коцюк Д.В.</copyright-holder><copyright-holder xml:lang="en">Sviridov V.V., Povarov A.Y., Kotsyuk D.V.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://izvestiya.tinro-center.ru/jour/article/view/1066">https://izvestiya.tinro-center.ru/jour/article/view/1066</self-uri><abstract><p>Опубликованные методики беспилотного учета тихоокеанских лососей позволяют получать силами специалистов дальневосточных филиалов ВНИРО качественные фотоматериалы, однако их обработка в целях подсчета на них производителей весьма трудоемка, а практика применения методов искусственного интеллекта, в частности моделей глубокого обучения (иначе — искусственных нейронных сетей), отсутствует. Публикации по автоматизации беспилотного учета тихоокеанских лососей посредством нейросетей посвящены лишь сненке кеты и носят предварительный характер. Нами создана модель глубокого обучения, способная эффективно проводить автоматическое видоспецифичное выявление производителей кеты и кижуча, а также сненки кеты в многовидовых скоплениях на материалах беспилотного учета. Нейросеть базируется на обширных обучающих материалах, работает на изображениях одновременно с несколькими классами объектов по их выявлению. Приведено подробное воспроизводимое техническое описание подготовки, проверки качества и эксплуатации модели глубокого обучения по тихоокеанским лососям на базе настольной ГИС. Описаны различные факторы, влияющие на качество работы нейросети, даны рекомендации по его повышению. Обосновано, почему показатели качества модели следует рассматривать лишь в контексте визуальных характеристик целевых объектов на обрабатываемых фотоматериалах, которые могут значительно варьировать. Предложены способы повышения качества результатов работы нейросети посредством задействования функционала геоинформационного программного обеспечения. Приведены рекомендации по оптимизации создания модели с помощью инструментария фотограмметрического и геоинформационного программного обеспечения. Предложена схема пересчета выдачи нейросети по обработанным фотоматериалам для получения скорректированной оценки тотального количества объектов на отснятой акватории.</p></abstract><trans-abstract xml:lang="en"><p>Published methods of unmanned counting of paciﬁc salmon allow to obtain high-quality photographic materials, but their processing is a rather hard labor. Practice of using the artiﬁcial intelligence methods, in particular deep learning models (otherwise — artiﬁcial neural networks), for this purpose is still insuﬃcient, preliminary and concerns the counts of post-spawn chum salmon only. In this study, a deep learning model was created capable for effective automatic species-speciﬁc detection of chum and coho salmon spawners and post-spawn chum salmon in multi-species aggregations using enumerated data of unmanned surveys. This neural network is based on wide training materials and is able to process simultaneously images with several classes of objects and identify all of them. Detailed and reproducible technical description of the preparation, quality control, and operation with the deep learning model for paciﬁc salmon is presented for a desktop GIS environment. Various factors aﬀecting quality of the neural network are described, and recommendations for improving its work are given. Quality indicators of the model should be considered in the context of visual characteristics of target objects in processed photographic materials, which can vary signiﬁcantly. Quality of the neural network output can be improved by using functionality of geoinformation software. Recommendations are given for optimizing the model development using the tools of photogrammetric and geoinformation software. Scheme for recalculating the neural network output based on processed photographic materials is proposed to obtain a corrected estimate of the total number of objects in the surveyed water area.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>тихоокеанские лососи</kwd><kwd>БПЛА</kwd><kwd>автоматизация</kwd><kwd>искусственный интеллект</kwd><kwd>глубокое обучение</kwd><kwd>нейросеть</kwd><kwd>ГИС</kwd></kwd-group><kwd-group xml:lang="en"><kwd>pacific salmon</kwd><kwd>UAV</kwd><kwd>automation</kwd><kwd>artificial intelligence</kwd><kwd>deep learning</kwd><kwd>neural network</kwd><kwd>GIS</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Авторы благодарят сотрудников Хабаровского филиала ВНИРО за участие в сборе материалов.</funding-statement><funding-statement xml:lang="en">Authors are grateful to colleagues from Khabarovsk branch of VNIRO for their assistance in materials collection.</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Методические рекомендации по проведению учета приплода байкальской нерпы (Pusa sibirica) с беспилотных летательных аппаратов в Байкальском рыбохозяйственном бассейне / сост. В.А. Бизиков, В.А. Петерфельд, В.И. Черноок и др. — М. : ВНИРО, 2021. — 56 с.</mixed-citation><mixed-citation xml:lang="en">Bizikov, V.A., Peterfeld, V.A., Chernook, V.I., Kuznetsov, N.V., Petrov, E.A., Bobkov, A.I., Tkachev, V.V., Sidorov, L.K., and Boltnev, E.A., Metodicheskiye rekomendatsii po provedeniyu ucheta priploda baykal’skoy nerpy (Pusa sibirica) s bespilotnykh letatel’nykh apparatov v Baykal’skom rybokhozyaystvennom basseyne (Methodological recommendations for the accounting of the oﬀspring of the Baikal seal (Pusa sibirica) from unmanned aerial vehicles in the Baikal ﬁshery basin), Moscow: VNIRO, 2021.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Свиридов В.В., Коцюк Д.В., Подорожнюк Е.В. Беспилотный фотограмметрический учет тихоокеанских лососей посредством БПЛА потребительского класса // Изв. ТИНРО. — 2022а. — Т. 202, вып. 2. — С. 429–449. DOI: 10.26428/1606-9919-2022-202-429-449. EDN: CNQHAF.</mixed-citation><mixed-citation xml:lang="en">Sviridov, V.V., Kotsyuk, D.V., and Podorozhnyuk, E.V., Photogrammetric counts of paciﬁc salmon by means of unmanned aerial vehicles of consumer grade, Izv. Tikhookean. Nauchno-Issled. Inst. Rybn. Khoz. Okeanogr., 2022, vol. 202, no. 2, pp. 429–449. doi 10.26428/1606-9919-2022-202-429-449. EDN: CNQHAF.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Свиридов В.В., Подорожнюк Е.В., Никитин В.Д., Скорик А.В. Модификации беспилотного учета производителей тихоокеанских лососей в реках Сахалинской области и Хабаровского края // Изв. ТИНРО. — 2022б. — Т. 202, вып. 4. — С. 1015–1031. DOI: 10.26428/1606-9919-2022-202-1015-1031. EDN: JULFRV.</mixed-citation><mixed-citation xml:lang="en">Sviridov, V.V., Podorozhnyuk, E.V., Nikitin, V.D., and Skorik, A.V., Modiﬁcations of unmanned aerial survey on spawners of paciﬁc salmons in the rivers of Sakhalin and Khabarovsk Regions, Izv. Tikhookean. Nauchno-Issled. Inst. Rybn. Khoz. Okeanogr., 2022, vol. 202, no. 4, pp. 1015–1031. doi 10.26428/1606-9919-2022-202-1015-1031. EDN: JULFRV.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Свиридов В.В., Поваров А.Ю. Применение методов искусственного интеллекта для автоматизации беспилотного учета отнерестившихся особей кеты в Хабаровском крае // Вопр. рыб-ва. — 2024. — Т. 25, № 4. — С. 113–124. DOI: 10.36038/0234-2774-2024-25-4-113-124.</mixed-citation><mixed-citation xml:lang="en">Sviridov, V.V. and Povarov, A.Yu., Application of artiﬁcial intelligence methods to automate post-spawn chum salmon individuals enumeration by means of unmanned aerial vehicles in Khabarovsk Territory, Vopr. rybolov., 2024, vol. 25, no. 4, pp. 113–124. doi 10.36038/0234-2774-2024-25-4-113-124</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Attard M.R., Phillips R.A., Bowler E. et al. Review of Satellite Remote Sensing and Unoccupied Aircraft Systems for Counting Wildlife on Land // Remote Sensing. — 2024. — Vol. 16, № 4. — P. 1–23. DOI: 10.3390/rs16040627.</mixed-citation><mixed-citation xml:lang="en">Attard, M.R.G., Phillips, R.A., Bowler E., Clarke, P.J., Cubaynes, H., Johnston, D.W., and Fretwell, P.T., Review of Satellite Remote Sensing and Unoccupied Aircraft Systems for Counting Wildlife on Land, Remote Sensing, 2024, vol. 16, no. 4, pp. 1–23. doi 10.3390/rs16040627</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Borowicz A., Le H., Humphries G. et al. Aerial-trained deep learning networks for surveying cetaceans from satellite imagery // PLoS ONE. — 2019. — Vol. 14, № 10: e0212532. DOI: 10.1371/journal.pone.0212532.</mixed-citation><mixed-citation xml:lang="en">Borowicz, A., Le, H., Humphries, G., Nehls, G., Höschle, C., Kosarev, V., and Lynch, H.J., Aerial-trained deep learning networks for surveying cetaceans from satellite imagery, PLoS ONE, 2019. vol. 14, no. 10, art. ID e0212532. doi 10.1371/journal.pone.0212532</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Boulent J., Charry B., Kennedy M. et al. Scaling whale monitoring using deep learning: A human-in-the-loop solution for analyzing aerial datasets // Frontiers in Marine Science. — 2023. — Vol. 10. — P. 1–13. DOI: 10.3389/fmars.2023.1099479.</mixed-citation><mixed-citation xml:lang="en">Boulent, J., Charry, B., Kennedy,M., Tissier, E., Fan, R., Marcoux, M., Watt, C., Gagné-Turcotte, A., Scaling whale monitoring using deep learning: A human-in-the-loop solution for analyzing aerial datasets, Frontiers in Marine Science, 2023, vol. 10, pp. 1–13. doi 10.3389/fmars.2023.1099479</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Butcher P., Colefax A., Gorkin I. et al. The drone revolution of shark science: A review // Drones. — 2021. — Vol. 5, № 1. — P. 1–8. DOI: 10.3390/drones5010008.</mixed-citation><mixed-citation xml:lang="en">Butcher, P., Colefax, A., Gorkin, I. Kajiura, S., López, N. , Mourier, J., Purcell, C. , Skomal, G., Tucker, Ja., Walsh, A., Williamson, Ja., and Raoult, V., The drone revolution of shark science: A review, Drones, 2021, vol. 5, no 1, pp. 1–8. doi 10.3390/drones5010008</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Desgarnier L., Mouillot D., Vigliola L. et al. Putting eagle rays on the map by coupling aerial video-surveys and deep learning // Biological Conservation. — 2022. — Vol. 267. — P. 109494. DOI: 10.1016/j.biocon.2022.109494.</mixed-citation><mixed-citation xml:lang="en">Desgarnier, L., Mouillot, D., Vigliola, L., Chaumont, M., and Mannocci, L., Putting eagle rays on the map by coupling aerial video-surveys and deep learning, Biological Conservation, 2022, vol. 267, pp. 109494. doi 10.1016/j.biocon.2022.109494</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Dujon A., Ierodiaconou D., Geeson J. et al. Machine learning to detect marine animals in UAV imagery: eﬀect of morphology, spacing, behaviour and habitat // Remote Sensing in Ecology and Conservation. — 2021. — Vol. 7, № 3. — P. 341–354. DOI: 10.1002/rse2.205.</mixed-citation><mixed-citation xml:lang="en">Dujon, A., Ierodiaconou, D., Geeson, J., Arnould, J., Allan, B., Katselidis, K., and Schofield, G., Machine learning to detect marine animals in UAV imagery: eﬀect of morphology, spacing, behaviour and habitat, Remote Sensing in Ecology and Conservation, 2021, vol. 7, no. 3, pp. 341–354. doi 10.1002/rse2.205</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Gorkin R., Adams K., Berryman M.J. et al. Sharkeye: Real-Time Autonomous Personal Shark Alerting via Aerial Surveillance // Drones. — 2020. — Vol. 4, № 2. — P. 1–18. DOI: 10.3390/drones4020018.</mixed-citation><mixed-citation xml:lang="en">Gorkin, R., Adams, K., Berryman, M.J., Aubin, S., Li, W., and Davis, A.R., Sharkeye: Real-Time Autonomous Personal Shark Alerting via Aerial Surveillance, Drones, 2020, vol. 4, no. 2, pp. 1–18. doi 10.3390/drones4020018</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Gray P., Bierlich K., Mantell S. et al. Drones and convolutional neural networks facilitate automated and accurate cetacean species identiﬁcation and photogrammetry // Methods in Ecology and Evolution. — 2019. — Vol. 10, № 9. — P. 1490–1500. DOI: 10.1111/2041-210X.13246.</mixed-citation><mixed-citation xml:lang="en">Gray, P., Bierlich, K., Mantell, S., Mantell, S., Friedlaender, A., Goldbogen, J., and Johnston, D., Drones and convolutional neural networks facilitate automated and accurate cetacean species identiﬁcation and photogrammetry, Methods in Ecology and Evolution, 2019, vol. 10, no. 9, pp. 1490–1500. doi 10.1111/2041-210X.13246</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Guirado E., Tabik S., Rivas M. et al. Whale counting in satellite and aerial images with deep learning // Scientiﬁc reports. — 2019. — Vol. 9, № 1. — P. 14259. DOI: 10.1038/s41598-019-50795-9.</mixed-citation><mixed-citation xml:lang="en">Guirado, E., Tabik, S., Rivas, M., Alcaraz-Segura, D., and Herrera, F., Whale counting in satellite and aerial images with deep learning, Scientiﬁc reports, 2019, vol. 9, no. 1, pp. 14259. doi 10.1038/s41598-019-50795-9</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Infantes E., Carroll D., Silva W. et al. An automated work-ﬂow for pinniped surveys: a new tool for monitoring population dynamics // Frontiers in Ecology and Evolution. — 2022. — Vol. 10. — P. 1–17. DOI: 10.3389/fevo.2022.905309.</mixed-citation><mixed-citation xml:lang="en">Infantes, E., Carroll, D., Silva ,W., Härkönen, T., Edwards, S.V., and Harding, K.C., An Automated Work-Flow For Pinniped Surveys: A New Tool For Monitoring Population Dynamics, Frontiers In Ecology And Evolution, 2022, vol. 10, pp. 1–17. doi 10.3389/Fevo.2022.905309</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Li J.Y., Duce S., Joyce K.E. et al. SeeCucumbers: Using Deep Learning and Drone Imagery to Detect Sea Cucumbers on Coral Reef Flats // Drones. — 2021. — Vol. 5, № 2. — P. 1–28. DOI: 10.3390/drones5020028.</mixed-citation><mixed-citation xml:lang="en">Li, J.Y., Duce, S., Joyce, K.E., and Xiang, W., SeeCucumbers: Using Deep Learning and Drone Imagery to Detect Sea Cucumbers on Coral Reef Flats, Drones, 2021, vol. 5, no. 2, pp. 1–28. doi 10.3390/drones5020028</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Rodoﬁli E., Lecours V., LaRue M. Remote sensing techniques for automated marine mammals detection: review of methods and current challenges // Peer J. — 2022. — Vol. 10. — P. 1–22. DOI: 10.7717/peerj.13540.</mixed-citation><mixed-citation xml:lang="en">Rodoﬁli, E., Lecours, V., and LaRue, M., Remote sensing techniques for automated marine mammals detection: review of methods and current challenges, Peer J., 2022, vol. 10, pp. 1–22. doi 10.7717/peerj.13540</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
