<?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">ntv</journal-id><journal-title-group><journal-title xml:lang="ru">Научно-технический вестник информационных технологий, механики и оптики</journal-title><trans-title-group xml:lang="en"><trans-title>Scientific and Technical Journal of Information Technologies, Mechanics and Optics</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2226-1494</issn><issn pub-type="epub">2500-0373</issn><publisher><publisher-name>Университет ИТМО</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.17586/2226-1494-2024-24-2-190-197</article-id><article-id custom-type="elpub" pub-id-type="custom">ntv-62</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>ОПТИЧЕСКИЕ СИСТЕМЫ И ТЕХНОЛОГИИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>OPTICAL ENGINEERING</subject></subj-group></article-categories><title-group><article-title>Способ быстрой разметки сверхбольших данных аэросъемки</article-title><trans-title-group xml:lang="en"><trans-title>Fast labeling pipeline approach for a huge aerial sensed dataset</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-6951-4681</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Федулин</surname><given-names>А. М.</given-names></name><name name-style="western" xml:lang="en"><surname>Fedulin</surname><given-names>A. M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Федулин Андрей Михайлович — директор центра разработки программного обеспечения</p><p>Санкт-Петербург, 199178</p><p>sc 57514263700</p></bio><bio xml:lang="en"><p>Andrei M. Fedulin — Director for Software Development</p><p>Saint Petersburg, 199178</p><p>sc 57514263700</p></bio><email xlink:type="simple">af@kronshtadt.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/0000-0001-9435-9580</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Волошина</surname><given-names>Н. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Voloshina</surname><given-names>N. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Волошина Наталия Викторовна — кандидат технических наук, доцент</p><p>Санкт-Петербург, 197101</p><p> sc 55511854200</p></bio><bio xml:lang="en"><p>Natalia V. Voloshina — PhD, Associate Professor</p><p>Saint Petersburg, 197101</p><p>sc 55511854200</p></bio><email xlink:type="simple">nvvoloshina@itmo.ru</email><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>АО «КТ — Беспилотные Системы»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>“KT — Unmanned Systems” JSC</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Университет ИТМО</institution><country>Россия</country></aff><aff xml:lang="en"><institution>ITMO University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2024</year></pub-date><pub-date pub-type="epub"><day>11</day><month>12</month><year>2024</year></pub-date><volume>24</volume><issue>2</issue><fpage>190</fpage><lpage>197</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Федулин А.М., Волошина Н.В., 2024</copyright-statement><copyright-year>2024</copyright-year><copyright-holder xml:lang="ru">Федулин А.М., Волошина Н.В.</copyright-holder><copyright-holder xml:lang="en">Fedulin A.M., Voloshina N.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://ntv.elpub.ru/jour/article/view/62">https://ntv.elpub.ru/jour/article/view/62</self-uri><abstract><p>Введение. Современные нейросетевые технологии активно применяются для беспилотных летательных аппаратов. Для решения задач детектирования, классификации и сопровождения объектов, расположенных на поверхности Земли, используются сверточные нейронные сети. Для повышения эффективности работы сверточных нейронных сетей требуется периодическое дообучение применяемых моделей нейронных сетей на вновь поступающих полетных данных. Такие обучающие данные необходимо дополнительно размечать. Это приводит к увеличению общего времени подготовки дообученной модели нейронной сети. Задача сокращения времени разметки чаще всего решается путем применения процедуры авторазметки и трекинга размеченных объектов. Однако существующие подходы не являются эффективными при разметке сверхбольших данных аэросъемки со стандартной для беспилотных летательных аппаратов большой продолжительностью полета (более 8 ч). Таким образом, задача поиска дополнительных способов сокращения времени разметки является актуальной. В данной работе предложен способ быстрой разметки данных аэросъемки, собранных с видеокамер в процессе полетов беспилотных летательных аппаратов. Метод. Стандартная процедура разметки дополнена прореживанием сильно перекрывающихся кадров в сочетании с последующим переносом результирующей разметки на все кадры размечаемого видео. Для каждого оставшегося после прореживания кадра вычисляется значение его потенциальной информативности (Potential Information Value, PIV), как совокупная оценка аномалий кадра, его качества и количества автоматически детектированных объектов. Полученные значения PIV используются для ранжирования кадров по уровню значимости. Таким образом, оператору беспилотного летательного аппарата предоставляются в начале процедуры разметки наиболее значимые кадры. Основные результаты. Экспериментальное исследование эффективности предложенного подхода выполнено на подготовленных наборах данных аэросъемки, полученных с беспилотного летательного аппарата с продолжительностью съемки не менее 8 ч. Показано, что время разметки может быть уменьшено в среднем на 50 % относительно применения существующих программных средств. При этом первые 40 % отсортированных кадров содержат 80 % размеченных объектов. Обсуждение. Предложенный способ позволяет существенно уменьшить итоговое время разметки вновь поступающих полетных видеоданных для дальнейшего дообучения модели сверточных нейронных сетей. Это позволяет провести разметку непосредственно в межполетный интервал времени, составляющий в среднем 2–3 ч. Предлагаемый подход может быть применен для уменьшения загрузки операторов беспилотного летательного аппарата.</p></abstract><trans-abstract xml:lang="en"><p>Modern neural network technologies are actively used for Unmanned Aerial Vehicles (UAVs). Convolutional Neural Networks (CNN), are mostly used for object detection, classification, and tracking tasks, for example, for such objects as fires, deforestations, buildings, cars, or people. However, to improve effectiveness of CNNs it is necessary to perform their fine-tuning on new flight data periodically. Such training data should be labeled, which increases total CNN finetuning time. Nowadays, the common approach to decrease labeling time is to apply auto-labeling and labeled objects tracking. These approaches are not effective enough for labeling of 8 hours’ huge aerial sensed datasets that are common for long-endurance USVs. Thus, reducing data labeling time is an actual task nowadays. In this research, we propose a fast aerial data labeling pipeline especially for videos gathered by long-endurance UAVs cameras. The standard labeling pipeline was supplemented with several steps such as overlapped frames pruning, final labeling spreading over video frames. The other additional step is to calculate a Potential Information Value (PIV) for each frame as a cumulative estimation of frame anomality, frame quality, and auto-detected objects. Calculated PIVs are used than to sort out frames. As a result, an operator who labels video gets informative frames at the very beginning of the labeling process. The effectiveness of proposed approach was estimated on collected datasets of aerial sensed videos obtained by longendurance UAVs. It was shown that it is possible to decrease labeling time by 50 % in average in comparison with other modern labeling tools. The percentage of average number of labeled objects was 80 %, with them being labeled for 40 % of total pre-ranged frames. Proposed approach allows us to decrease labeling time for a new long-endurance flight video data significantly. This makes it possible to speed up neural network fine-tuning process. As a result, it became possible to label new data during the inter-flight time that usually takes about two or three hours and is too short for other labeling instruments. Proposed approach is recommended to decrease UAVs operators working time and labeled dataset creating time that could positively influence on the time necessary for the fine-tuning a new effective CNN models.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>способ быстрой разметки</kwd><kwd>беспилотный летательный аппарат</kwd><kwd>БПЛА</kwd><kwd>продолжительность полета БПЛА</kwd><kwd>состязательные атаки</kwd><kwd>величина потенциальной информативности кадра</kwd><kwd>PIV</kwd></kwd-group><kwd-group xml:lang="en"><kwd>fast labeling pipeline</kwd><kwd>FLP</kwd><kwd>unmanned aerial vehicle</kwd><kwd>UAVs</kwd><kwd>long-endurance UAVs</kwd><kwd>adversarial attack</kwd><kwd>frames potential information value</kwd><kwd>PIV</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Zhao Z., Zheng P., Xu S., Wu X. Object detection with deep learning: A review. arXiv, 2019, arXiv:1807.05511. https://doi.org/10.48550/arXiv.1807.05511</mixed-citation><mixed-citation xml:lang="en">Zhao Z., Zheng P., Xu S., Wu X. Object detection with deep learning: A review // arXiv. 2019. arXiv:1807.05511. https://doi.org/10.48550/arXiv.1807.05511</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Ren S., He K., Girshick R., Sun J. Faster R-CNN: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, 2015, vol. 28, pp. 91–99.</mixed-citation><mixed-citation xml:lang="en">Ren S., He K., Girshick R., Sun J. Faster R-CNN: Towards real-time object detection with region proposal networks // Advances in Neural Information Processing Systems. 2015. V. 28. P. 91–99.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Liu S., Liu Z. Multi-channel CNN-based object detection for enhanced situation awareness. Sensors &amp; Electronics Technology (SET) panel Symposium SET-241 on 9th NATO Military Sensing Symposium, 2017.</mixed-citation><mixed-citation xml:lang="en">Liu S., Liu Z. Multi-channel CNN-based object detection for enhanced situation awareness // Sensors &amp; Electronics Technology (SET) panel Symposium SET-241 on 9th NATO Military Sensing Symposium. 2017.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Mahalanobis A., McIntosh B. A comparison of target detection algorithms using DSIAC ATR algorithm development data set. Proceedings of SPIE, 2019, vol. 10988, pp. 1098808. https://doi.org/10.1117/12.2517423</mixed-citation><mixed-citation xml:lang="en">Mahalanobis A., McIntosh B. A comparison of target detection algorithms using DSIAC ATR algorithm development data set // Proceedings of SPIE. 2019. V. 10988. P. 1098808. https://doi.org/10.1117/12.2517423</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Liu W., Anguelov D., Erhan D., Szegedy C., Reed S., Fu C.-Y., Berg A. SSD: Single shot multibox detector. Lecture Notes in Computer Science, 2016, vol. 9905, pp. 21–37. https://doi.org/10.1007/978-3-319-46448-0_2</mixed-citation><mixed-citation xml:lang="en">Liu W., Anguelov D., Erhan D., Szegedy C., Reed S., Fu C.-Y., Berg A. SSD: Single shot multibox detector // Lecture Notes in Computer Science. 2016. V. 9905. P. 21–37. https://doi.org/10.1007/978-3-319-46448-0_2</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Ronneberger O., Fischer P., Brox T. U-Net: Convolutional networks for biomedical image segmentation. Lecture Notes in Computer Science, 2015, vol. 9351, pp. 234–241. https://doi.org/10.1007/978-3-319-24574-4_28</mixed-citation><mixed-citation xml:lang="en">Ronneberger O., Fischer P., Brox T. U-Net: Convolutional networks for biomedical image segmentation // Lecture Notes in Computer Science. 2015. V. 9351. P. 234–241. https://doi.org/10.1007/978-3-319-24574-4_28</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Redmon J. Farhadi A. YOLO9000: better, faster, stronger. Proc. of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 6517–6525. https://doi.org/10.1109/ CVPR.2017.690</mixed-citation><mixed-citation xml:lang="en">Redmon J. Farhadi A. YOLO9000: better, faster, stronger // Proc. of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017. P. 6517–6525. https://doi.org/10.1109/CVPR.2017.690</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Chen H-W., Reyes M., Marquand B., Robie D. Advanced automated target recognition (ATR) and multi-target tracker (MTT) with electrooptical (EO) sensors. Proceedings of SPIE, 2020, vol. 11511, pp. 115110V. https://doi.org/10.1117/12.2567178</mixed-citation><mixed-citation xml:lang="en">Chen H-W., Reyes M., Marquand B., Robie D. Advanced automated target recognition (ATR) and multi-target tracker (MTT) with electrooptical (EO) sensors // Proceedings of SPIE. 2020. V. 11511. P. 115110V. https://doi.org/10.1117/12.2567178</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Redmon J., Farhadi A. YOLOv3: An Incremental Improvement. arXiv, 2018, ar.Xiv:1804.02767v1. https://doi.org/10.48550/arXiv.1804.02767</mixed-citation><mixed-citation xml:lang="en">Redmon J., Farhadi A. YOLOv3: An Incremental Improvement // arXiv. 2018. ar.Xiv:1804.02767v1. https://doi.org/10.48550/arXiv.1804.02767</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Wang C.Y., Bochkovskiy A., Liao M. YOLOv7: Trainable bag-offreebies sets new state-of-the-art for real-time object detectors. Proc. of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. https://doi.org/10.1109/CVPR52729.2023.00721</mixed-citation><mixed-citation xml:lang="en">Wang C.Y., Bochkovskiy A., Liao M. YOLOv7: Trainable bag-offreebies sets new state-of-the-art for real-time object detectors // Proc. of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2023. https://doi.org/10.1109/CVPR52729.2023.00721</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Fedulin A.M., Evstaf’ev D.V., Kondrashova G.L., Artemenko N.V. Human-autonomy teaming interface design for multiple-UAV control. Russian Aeronautics, 2022, vol. 65, no. 2, pp. 419–424. https://doi.org/10.3103/S1068799822020222</mixed-citation><mixed-citation xml:lang="en">Fedulin A.M., Evstaf’ev D.V., Kondrashova G.L., Artemenko N.V. Human-autonomy teaming interface design for multiple-UAV control // Russian Aeronautics. 2022. V. 65. N 2. P. 419–424. https://doi.org/10.3103/S1068799822020222</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Barnell M., Raymond C., Capraro Ch., Isereau D., Cicotta Ch., Stokes N. High-performance computing (HPC) and machine learning demonstrated in flight using agile condor. Proc. of the 2018 IEEE High Performance extreme Computing Conference (HPEC), 2018, pp. 1–4. https://doi.org/10.1109/HPEC.2018.8547797</mixed-citation><mixed-citation xml:lang="en">Barnell M., Raymond C., Capraro Ch., Isereau D., Cicotta Ch., Stokes N. High-performance computing (HPC) and machine learning demonstrated in flight using agile condor // Proc. of the 2018 IEEE High Performance extreme Computing Conference (HPEC). 2018. P. 1–4. https://doi.org/10.1109/HPEC.2018.8547797</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Fedulin A.M., Driagin D.M. Prospects of MALE-class UAVs using for the huge territories aerial survey. Izvestiya SFedU. Engineering Sciences, 2021, no. 1(218), pp. 271–281. (in Russian). https://doi.org/10.18522/2311-3103-2021-1-271-281</mixed-citation><mixed-citation xml:lang="en">Федулин А.М., Дрягин Д.М. Перспективы применения крупноразмерных БПЛА при решении задач комплексного обследования территорий // Известия ЮФУ. Технические науки. 2021. № 1(218). С. 271–281. https://doi.org/10.18522/2311-3103-2021-1-271-281</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Fei-Fei L., Fergus R., Perona P. One-shot learning of object categories. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, vol. 28, no. 4, pp. 594–611. https://doi.org/10.1109/tpami.2006.79</mixed-citation><mixed-citation xml:lang="en">Fei-Fei L., Fergus R., Perona P. One-shot learning of object categories // IEEE Transactions on Pattern Analysis and Machine Intelligence. 2006. V. 28. N 4. P. 594–611. https://doi.org/10.1109/tpami.2006.79</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Fink M. Object classifcation from a single example utilizing class relevance metrics. Advances in Neural Information Processing Systems, 2004, vol. 17, pp. 449–456.</mixed-citation><mixed-citation xml:lang="en">Fink M. Object classifcation from a single example utilizing class relevance metrics // Advances in Neural Information Processing Systems. 2004. V. 17. P. 449–456.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Alajaji D., Alhichri H.S., Ammour N., Alajlan N. Few-shot learning for remote sensing scene classification. Proc. of the 2020 Mediterranean and Middle-East Geoscience and Remote Sensing Symposium (M2GARSS), pp. 81–84. https://doi.org/10.1109/ M2GARSS47143.2020.9105154</mixed-citation><mixed-citation xml:lang="en">Alajaji D., Alhichri H.S., Ammour N., Alajlan N. Few-shot learning for remote sensing scene classification // Proc. of the 2020 Mediterranean and Middle-East Geoscience and Remote Sensing Symposium (M2GARSS). P. 81–84. https://doi.org/10.1109/M2GARSS47143.2020.9105154</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Sager Ch., Janiesch Ch., Zschech P. A survey of image labelling for computer vision applications. Journal of Business Analytics, 2021, vol. 4, no. 2, pp. 91–110. https://doi.org/10.1080/2573234X.2021.1908861</mixed-citation><mixed-citation xml:lang="en">Sager Ch., Janiesch Ch., Zschech P. A survey of image labelling for computer vision applications // Journal of Business Analytics. 2021. V. 4. N 2. P. 91–110. https://doi.org/10.1080/2573234X.2021.1908861</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Oprea A., Vassilev A., Fordyce A., Anderson H. Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations: Report NIST AI100-2E2023. 107 p. https://doi.org/10.6028/NIST. AI.100-2e2023</mixed-citation><mixed-citation xml:lang="en">Oprea A., Vassilev A., Fordyce A., Anderson H. Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations: Report NIST AI100-2E2023. 107 p. https://doi.org/10.6028/NIST. AI.100-2e2023</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Choi J.I., Tian Q. Adversarial attack and defense of YOLO detectors in autonomous driving scenarios. Proc. of the 2022 IEEE Intelligent Vehicles Symposium (IV), 2022, pp. 1011–1017. https://doi.org/10.1109/IV51971.2022.9827222</mixed-citation><mixed-citation xml:lang="en">Choi J.I., Tian Q. Adversarial attack and defense of YOLO detectors in autonomous driving scenarios // Proc. of the 2022 IEEE Intelligent Vehicles Symposium (IV). 2022. P. 1011–1017. https://doi.org/10.1109/IV51971.2022.9827222</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Wang C.Y., Bochkovskiy A., Liao H.Y.M. YOLOv7: Trainable bagof-freebies sets new state-of-the-art for real-time object detectors. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 7464–7475. https://doi.org/10.1109/cvpr52729.2023.00721</mixed-citation><mixed-citation xml:lang="en">Wang C.Y., Bochkovskiy A., Liao H.Y.M. YOLOv7: Trainable bagof-freebies sets new state-of-the-art for real-time object detectors // Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2023. P. 7464–7475. https://doi.org/10.1109/cvpr52729.2023.00721</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Defard T., Setkov A., Loesch A., Audigier R. PaDiM: A Patch distribution modeling framework for anomaly detection and localization. Lecture Notes in Computer Science, 2021, vol. 12664, pp. 475–489. https://doi.org/10.1007/978-3-030-68799-1_35</mixed-citation><mixed-citation xml:lang="en">Defard T., Setkov A., Loesch A., Audigier R. PaDiM: A Patch distribution modeling framework for anomaly detection and localization // Lecture Notes in Computer Science. 2021. V. 12664. P. 475–489. https://doi.org/10.1007/978-3-030-68799-1_35</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">Ilg E., Mayer N., Saikia T., Keuper M., Dosovitskiy A., Brox T. Flownet 2.0: Evolution of optical flow estimation with deep networks. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 1647–1655. https://doi.org/10.1109/cvpr.2017.179</mixed-citation><mixed-citation xml:lang="en">Ilg E., Mayer N., Saikia T., Keuper M., Dosovitskiy A., Brox T. Flownet 2.0: Evolution of optical flow estimation with deep networks // Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017. P. 1647–1655. https://doi.org/10.1109/cvpr.2017.179</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">Guillermo M., Billones R.K., Bandala A., Vicerra R.R., Sybingco E., Dadios E.P., Fillone A. Implementation of automated annotation through mask RCNN Object Detection Model in CVAT using AWS EC2 Instance. Proc.of the 2020 IEEE REGION 10 CONFERENCE (TENCON), 2020, pp. 708–713. https://doi.org/10.1109/tencon50793.2020.9293906</mixed-citation><mixed-citation xml:lang="en">Guillermo M., Billones R.K., Bandala A., Vicerra R.R., Sybingco E., Dadios E.P., Fillone A. Implementation of automated annotation through mask RCNN Object Detection Model in CVAT using AWS EC2 Instance // Proc.of the 2020 IEEE REGION 10 CONFERENCE (TENCON). 2020. P. 708–713. https://doi.org/10.1109/tencon50793.2020.9293906</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>
