<?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">izvestswsu</journal-id><journal-title-group><journal-title xml:lang="ru">Известия Юго-Западного государственного университета</journal-title><trans-title-group xml:lang="en"><trans-title>Proceedings of the Southwest State University</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2223-1560</issn><issn pub-type="epub">2686-6757</issn><publisher><publisher-name>ЮЗГУ</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.21869/2223-1560-2021-25-3-152-166</article-id><article-id custom-type="elpub" pub-id-type="custom">izvestswsu-930</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>Информатика, вычислительная техника и управление</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>Computer science, computer engineering and IT managment</subject></subj-group></article-categories><title-group><article-title>Двухэтапный подход к распознаванию коррозии металлических конструкций с использованием сверточных нейронных сетей в ходе проведения инспекций промышленных объектов</article-title><trans-title-group xml:lang="en"><trans-title>Two-step Approach to Corrosion Detection of Metal Structures Using Convolutional Neural Networks When Inspecting Industrial Facilities</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-1895-8001</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Русаков</surname><given-names>К. Д.</given-names></name><name name-style="western" xml:lang="en"><surname>Rusakov</surname><given-names>K. D.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Русаков Константин Дмитриевич, научный сотрудник</p><p>ул. Профсоюзная,д. 65, стр. 1, г. Москва 117342</p></bio><bio xml:lang="en"><p>Konstantin D. Rusakov, Research Associate</p><p>65 Profsoyuznaya str., Moscow 117997</p></bio><email xlink:type="simple">rusakov.msk@yandex.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Чехов</surname><given-names>А. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Chekhov</surname><given-names>A. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Чехов Антон Валерьевич, ведущий эксперт</p><p>ул. Профсоюзная,д. 65, стр. 1, г. Москва 117342</p></bio><bio xml:lang="en"><p>Anton V. Chekhov, Leading Expert</p><p>65 Profsoyuznaya str., Moscow 117997</p></bio><email xlink:type="simple">achekhov@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Институт проблем управления им. В.А. Трапезникова РАН</institution></aff><aff xml:lang="en"><institution>V. A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences</institution></aff></aff-alternatives><pub-date pub-type="collection"><year>2021</year></pub-date><pub-date pub-type="epub"><day>29</day><month>01</month><year>2022</year></pub-date><volume>25</volume><issue>3</issue><fpage>152</fpage><lpage>166</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Русаков К.Д., Чехов А.В., 2022</copyright-statement><copyright-year>2022</copyright-year><copyright-holder xml:lang="ru">Русаков К.Д., Чехов А.В.</copyright-holder><copyright-holder xml:lang="en">Rusakov K.D., Chekhov A.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://izvestswsu.elpub.ru/jour/article/view/930">https://izvestswsu.elpub.ru/jour/article/view/930</self-uri><abstract><p>Цель исследования: Распознавание коррозии на металлических конструкциях является серьезной проблемой в проведение инспекций промышленных объектов. Существующие подходы к анализу изображений имеют тенденцию использовать все изображения для распознавания участков, поврежденных коррозией, что не подходит как для структурного анализа, так как процент ошибок при таком подходе очень велик. В условиях прогнозирования коррозии по всему изображению возможны ошибки, связанные с прогнозируемой маской не на металлической конструкции. В связи с этим необходимо удалять результаты прогнозирования положительного класса для участков, поврежденных коррозией, но не размещенных на металлической конструкции. Поэтому в данной работе авторы разработали двухэтапный подход к распознаванию коррозии металлических конструкций, тем самым достигая цель – повышение точности распознавания.Методы. В этой статье мы применяем две модели глубокого обучения, ориентированные на семантическую сегментацию (DeepLabv3, BiSeNetV2) для обнаружения коррозии, которые работают лучше с точки зрения точности и времени и требуют меньшего количества аннотированных образцов по сравнению с другими глубокими моделями, например, Unet, FCN, Mask-RCNN. В работе предложен новый подход к распознаванию металлических участков, поврежденных коррозией, на основе совмещения двух сверточных нейронных сетей для более точного пиксельного предсказания глубинными моделями архитектуры DeepLabv3 и BiSeNetV2.Результаты. В ходе экспериментальных исследований проводился расчет точности и F1 меры с использованием моделей FCN, Unet, Mask-RCNN, а также предложенного подхода. На основании полученных результатов был сделан вывод о том, что предложенный подход состоящий в совмещении сетей DeepLabv3 и BiSeNetV2 на 3 % повышает точность и F1 меру для алгоритма Unet, на 10% точность и 2% F1 меру для Mask R-CNN и на 12 % точности и 4 % F1 меру для FCN сети. Экспериментальные результаты и сравнения с реальными наборами данных подтверждают эффективность предложенной схемы даже для очень сложных изображений с множеством типов дефектов. Производительность оценивалась на базе данных, аннотированной экспертами.Заключение. В статье проведен анализ существующих решений в области распознавания металлических конструкций, поврежденных коррозией, и выявлены недостатки существующих решений, основанных либо на детекции очагов коррозии, либо на попиксельной сегментации полного изображения. В данной работе предложен новый подход к распознаванию металлических участков, поврежденных коррозией, на основе совмещения двух сверточных нейронных сетей для более точного пиксельного предсказания DeepLabv3 и BiSeNetV2. Производительность оценивается на базе данных, аннотированной экспертами по метрикам Precision и F1-score</p></abstract><trans-abstract xml:lang="en"><p>Purpose of research. Corrosion recognition on metal structures is a serious problem in conducting inspections of industrial facilities. Existing approaches to image analysis use all images to recognize areas damaged by corrosion, which is not suitable for structural analysis, since the percentage of errors in this approach is very large. Under conditions of corrosion prediction throughout the image, errors related to predictive mask not on metal structure are possible. Therefore, it is necessary to delete the results of positive class prediction for areas damaged by corrosion but not placed on metal structure. Therefore, in this work, the authors have developed two-step approach for recognizing corrosion of metal structures, thereby achieving the goal of improving recognition accuracy.Methods. We implement two deep learning models focused on Semantic segmentation (DeepLabv3, BiSeNetV2) for corrosion detection that work better in terms of accuracy and time and require fewer annotated samples compared to other deep models, such as Unet, FCN, Mask-RCNN. A new detection approach to metal areas damaged by corrosion, based on the combination of two convolutional neural networks for more accurate pixel prediction by depth architecture models: DeepLabv3 and BiSeNetV2.Results. Experimental studies have calculated the accuracy and F1 measures using FCN, Unet, Mask-RCNN models as well as the proposed approach. Based on obtained results, it was concluded that proposed approach of combining DeepLabv3 and BiSeNetV2 networks increases accuracy and F1 measure for Unet algorithm by 3%, accuracy by 10% and 2% F1 measure for Mask R-CNN and by 12% accuracy and 4% F1 measure for FCN network. Experimental results and comparisons with real data sets confirm the effectiveness of proposed scheme even for very complex images with many different defects. Productivity was assessed based on data annotated by experts.Conclusion. Analyses of existing solutions in the field of recognition of metal structures damaged by corrosion is described. Shortcomings of existing solutions based either on detection of corrosion sites or on pixel segmentation of full image are identified. A new approach to the recognition of metal areas damaged by corrosion based on the combination of two convolutional neural networks for more accurate pixel prediction of DeepLabv3 and BiSeNetV2 is indroduced. Production is evaluated based on data annotated by Precision and F1-score metrics experts.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>вертикальные инспекции</kwd><kwd>семантическая сегментация</kwd><kwd>глубокое обучение</kwd><kwd>обнаружение коррозии</kwd><kwd>сверточные нейронные сети</kwd></kwd-group><kwd-group xml:lang="en"><kwd>vertical inspections</kwd><kwd>semantic segmentation</kwd><kwd>deep learning</kwd><kwd>corrosion detection</kwd><kwd>convolutional neural networks</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">Image processing algorithms for crack detection in welded structures via pulsed eddy current thermal imaging / Z. Liu, G. Lu, X. Liu, X. Jiang, and G. Lodewijks // IEEE Instrumentation &amp; Measurement Magazine. 2017. Vol. 20. N. 4. P. 34–44.</mixed-citation><mixed-citation xml:lang="en">Liu Z., Lu G., Liu X., Jiang X., Lodewijks G. Image processing algorithms for crack detection in welded structures via pulsed eddy current thermal imaging. IEEE Instrumentation &amp; Measurement Magazine, 2017, vol. 20, no. 4, pp. 34–44.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">An application of swarm of quadcopters for searching operations / Р.В. Мещеряков, П.М. Трефилов, А.В. Чехов, С.А. Диане, К.Д. Русаков, Е.А. Лесив, М.А. Колодочка, К.О. Щукин, А.К. Новосельский, Е.И. Гончарова // IFAC-PapersOnLine. Sozopol, Bulgaria: Elsevier, 2019. Vol. 52, is. 25. P. 14-18 .</mixed-citation><mixed-citation xml:lang="en">Meshcheryakov R.V., Trefilov P.M., Chekhov A.V., Diana S.A., Rusakov K.D., Lesiv E.A., Kolodochka M.A., Shchukin K.O., Novoselsky A.K., Goncharova E.I. An application of swarm of quadcopters for searching operations. IFAC-PapersOnLine. Sozopol, Bulgaria, 2019, vol. 52, is. 25, pp. 14-18 .</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Automatic crack detection for tunnel inspection using deep learning and heuristic image post-processing / E. Protopapadakis, A. Voulodimos, A. Doulamis, N. Doulamis, T. Stathaki // Applied Intelligence. 2019. Vol. 49. No. 7. P. 2793–2806.</mixed-citation><mixed-citation xml:lang="en">Protopapadakis E., Voulodimos A., Doulamis A., Doulamis N., Stathaki T. Automatic crack detection for tunnel inspection using deep learning and heuristic image postprocessing. Applied Intelligence, 2019, vol. 49, no. 7, pp. 2793–2806.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Вычислительный метод распознавания образов по видеоизображениям с использованием глубинных нейронных сетей со сверточными и рекуррентными слоями с приложениями для транспортных систем / О.С. Амосов, С.Г. Амосова, С.В. Жиганов, Ю.С. Иванов // Информатика и системы управления. 2019. № 1 (59). С. 18-35.</mixed-citation><mixed-citation xml:lang="en">Amosov O.S., Amosova S.G., Zhiganov S.V., Ivanov Yu.S. Vychislitel'nyi metod raspoznavaniya obrazov po videoizobrazheniyam s ispol'zovaniem glubinnykh neironnykh setei so svertochnymi i rekurrentnymi sloyami s prilozheniyami dlya transportnykh sistem [Computational method of image recognition from video images using deep neural networks with convolutional and recurrent layers with applications for transport systems]. Informatika i sistemy upravleniya = Informatics and Control Systems, 2019, no. 1 (59), pp. 18-35.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Амосов О.С., Амосова С.Г. The Neural Network Method for Detection and Recognition of Moving Objects in Trajectory Tracking Tasks according to the Video Stream // Proceedings of the 26th Saint Petersburg International Conference on Integrated Navigation Systems (ICINS2019). СПб.: Institute of Electrical and Electronics Engineers Inc, 2019. С. 43-46.</mixed-citation><mixed-citation xml:lang="en">Amosov O.S., Amosova S.G. The Neural Network Method for Detection and Recognition of Moving Objects in Trajectory Tracking Tasks according to the Video Stream. Proceedings of the 26th Saint Petersburg International Conference on Integrated Navigation Systems (ICINS-2019). Saint Petersburg, 2019, pp. 43-46.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">1-D convolutional neural network based on the inner ear principle to automatically assess human’s emotional state / Topical Problems of Agriculture, Civil and Environmental Engineering (TPACEE 2020) / А.О. Исхакова, Д.А. Вольф, Р.Р. Галин, М.В. Мамченко // E3S Web of Conferences. Moscow: E3S Web Conf., 2020. Vol. 224.</mixed-citation><mixed-citation xml:lang="en">Iskhakova A.O., Wolf D.A., Galin R.R., Mamchenko M.V. 1-D convolutional neural network based on the inner ear principle to automatically assess human’s emotional state. Topical Problems of Agriculture, Civil and Environmental Engineering (TPACEE 2020). E3S Web of Conferences. Moscow, 2020, vol. 224.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Амосов О.С., Амосова С.Г., Иочков И.О. Вычислительный метод на основе глубоких нейронных сетей для обнаружения и классификации дефектов, возникающих в заклепочных соединениях авиационной техники // Материалы 12-й Международной конференции «Управление развитием крупномасштабных систем» (MLSD'2019, Москва). М.: ИПУ РАН, 2019. С. 736-738.</mixed-citation><mixed-citation xml:lang="en">Amosov O.S., Amosova S.G., Iochkov I.O. [Computational method based on deep neural networks for the detection and classification of defects arising in riveted joints of aircraft]. Materialy 12-i Mezhdunarodnoi konferentsii «Upravlenie razvitiem krupnomasshtabnykh sistem» (MLSD'2019, Moskva) [Materials of the 12th International Conference "Management of Large-Scale Systems Development" (MLSD'2019, Moscow)]. Moscow, IPU RAN Publ., 2019, pp. 736-738 (In Russ).</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Бобырь М. В. Проектирование нейронных и нечетких моделей в области вычислительной техники и систем управления. М.: Аргамак-Медиа, 2018. 110 с.</mixed-citation><mixed-citation xml:lang="en">Bobyr M.V. Proektirovanie neironnykh i nechetkikh modelei v oblasti vy-chislitel'noi tekhniki i sistem upravleniya [Design of neural and fuzzy models in the field of computer technology and control systems]. Moscow, Argamak-Media Publ., 2018. 110 p.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Corrosion Identification of Fittings Based on Computer Vision / Z. Tian, G. Zhang, Y. Liao, R. Li, F. Huang // International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM). 2019. P. 592-597. https://doi.org/10.1109/AIAM48774.2019.00123.</mixed-citation><mixed-citation xml:lang="en">Tian Z., Zhang G., Liao Y., Li R., Huang F. Corrosion Identification of Fittings Based on Computer Vision. International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM), 2019, pp. 592-597. https://doi.org/10.1109/AIAM48774.2019.00123.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Young-Jin Cha, Wooram Choi, Oral Buy¨ uk¨ ozt ¨ urk, ¨ Deep learning-based crack damage detection using convolutional neural networks // Computer-Aided Civil and Infrastructure Engineering. 2017. Vol. 32. No. 5. P. 361– 378.</mixed-citation><mixed-citation xml:lang="en">Young-Jin Cha, Wooram Choi, and Oral Buy¨ uk¨ ozt ¨ urk, Deep learning-based crack damage detection using convolutional neural networks. Computer-Aided Civil and Infrastructure Engineering, 2017, vol. 32, no. 5, pp. 361–378.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Road crack detection using deep convolutional neural network / L. Zhang, F. Yang, Y.D. Zhang, Y. J. Zhu // IEEE international conference on image processing (ICIP). IEEE, 2016. P. 3708–3712.</mixed-citation><mixed-citation xml:lang="en">Zhang L., Yang F., Zhang Y.D., Zhu Y. J. Road crack detection using deep convolutional neural network. IEEE international conference on image processing (ICIP). IEEE, 2016, pp. 3708–3712.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Soukup D., Huber-Mork R. Convolutional neural networks for steel surface defect detection from photometric stereo images, in International Symposium on Visual Computing. Springer, 2014. P. 668–677.</mixed-citation><mixed-citation xml:lang="en">Soukup D., Huber-Mork R. Convolutional neural networks for steel surface defect detection from photometric stereo images in International Symposium on Visual Computing. Springer, 2014, pp. 668–677.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Fu-Chen Chen, Mohammad R Jahanshahi. Nbcnn: Deep learning-based crack detection using convolutional neural network and na¨ıve bayes data fusion // IEEE Transactions on Industrial Electronics. 2017. Vol. 65. N. 5. P. 4392–4400.</mixed-citation><mixed-citation xml:lang="en">Fu-Chen Chen, Mohammad R Jahanshahi Nbcnn: Deep learning-based crack detection using convolutional neural network and na¨ıve bayes data fusion. IEEE Transactions on Industrial Electronics, 2017, vol. 65, no. 5, pp. 4392–4400.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Chen LC., Zhu Y., Papandreou G., Schroff F., Adam H. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. In: Ferrari V., Hebert M., Sminchisescu C., Weiss Y. (eds) Computer Vision – ECCV 2018. ECCV 2018. Lecture Notes in Computer Science. Vol 11211. Springer, Cham.</mixed-citation><mixed-citation xml:lang="en">Chen LC., Zhu Y., Papandreou G., Schroff F., Adam H. Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. In: Ferrari V., Hebert M., Sminchisescu C., Weiss Y. (eds) Computer Vision – ECCV 2018. ECCV 2018. Lecture Notes in Computer Science, 2018, vol 11211. Springer, Cham.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Yu Changqian, Gao Changxin, Wang,Jingbo, Yu,Gang, Shen Chunhua, Sang Nong. BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation. 2020</mixed-citation><mixed-citation xml:lang="en">Yu Changqian, Gao Changxin, Wang Jingbo, Yu Gang, Shen Chunhua, Sang Nong. BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation. 2020.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Automatic brain tumor detection and segmentation using u-net based fully convolutional networks / H. Dong, G. Yang, F. Liu, Y. Mo, Y. Guo // Annual conference on medical image understanding and analysis. Springer, 2017. P. 506–517.</mixed-citation><mixed-citation xml:lang="en">Dong H., Yang G., Liu F., Mo Y., Guo Y., Automatic brain tumor detection and segmentation using u-net based fully convolutional networks. Annual conference on medical image understanding and analysis. Springer, 2017, pp. 506–517.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Das S., Hollander C. D., Suliman S. Automating Visual Inspection with Convolutional Neural Networks // Annual Conference of the PHM Society, 2019. N. 11(1).</mixed-citation><mixed-citation xml:lang="en">Das S., Hollander C. D., Suliman, S. Automating Visual Inspection with Convolutional Neural Networks. Annual Conference of the PHM Society, 2019, 11(1).</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Chollet F.: Xception: Deep learning with depthwise separable convolutions. In: CVPR. 2017.</mixed-citation><mixed-citation xml:lang="en">Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In: CVPR. 2017.</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Воротнев Д. В., Голованов Р. В. Методика обучения бинарных классификаторов в задачах сегментации изображений // Известия высших учебных заведений. Электроника. 2019. Т. 24. № 3. С. 279-290. https://doi.org/10.24151/1561-5405-2019-24-3-279-290.</mixed-citation><mixed-citation xml:lang="en">Vorotnev D.V., Golovanov R.V. Metodika obucheniya binarnykh klassifikatorov v zadachakh segmentatsii izobrazhenii [Methodology for teaching binary classifiers in image segmentation problems]. Izvestiya vysshikh uchebnykh zavedenii. Elektronika = Proceedings of Higher Educational Institutions. Electronics, 2019, vol. 24, no. 3, pp. 279-290. https://doi.org/10.24151/1561-5405-2019-24-3-279-290.</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Бобырь М. В., Ноливос С. К. А., Матиез Л. А. С. Алгоритм ускоренной обработки изображений в системах технического зрения интеллектуальных мобильных роботов // Медико-экологические информационные технологии - 2020 : сборник научных статей по материалам XХIII Международной научно-технической конференции: в 2 ч. Курск, 2020. С. 200-205.</mixed-citation><mixed-citation xml:lang="en">Bobyr M. V., Nolivos S. K. A., Matiez L. A. [Algorithm of accelerated image processing in technical vision systems of intelligent mobile robots]. Mediko-ekologicheskie informatsionnye tekhnologii - 2020. Sbornik nauch-nykh statei po materialam XXIII Mezhdunarodnoi nauchno-tekhnicheskoi konferentsii [Medico-ecological information technologies - 2020. Collection of scientific articles based on the materials of the XXIII International Scientific and Technical Conference]. Kursk, Southwest State University Publ., 2020, pp. 200-205 (In Russ).</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>
