<?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="research-article" dtd-version="1.2" xml:lang="en"><front><journal-meta><journal-id journal-id-type="publisher-id">Infokommunikacionnye tehnologii</journal-id><journal-title-group><journal-title xml:lang="en">Infokommunikacionnye tehnologii</journal-title><trans-title-group xml:lang="ru"><trans-title>Инфокоммуникационные технологии</trans-title></trans-title-group></journal-title-group><issn publication-format="print">2073-3909</issn><publisher><publisher-name xml:lang="en">Povolzhskiy State University of Telecommunications and Informatics</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="publisher-id">689815</article-id><article-id pub-id-type="doi">10.18469/ikt.2024.22.1.01</article-id><article-categories><subj-group subj-group-type="toc-heading" xml:lang="en"><subject>Theoretical technological basis of information transmission and signals</subject></subj-group><subj-group subj-group-type="toc-heading" xml:lang="ru"><subject>Теоретические основы технологий передачи и обработки информации и сигналов</subject></subj-group><subj-group subj-group-type="article-type"><subject>Research Article</subject></subj-group></article-categories><title-group><article-title xml:lang="en">Suppression ofn the video stream frames processed by unmanned systems using FPV control</article-title><trans-title-group xml:lang="ru"><trans-title>Нивелирование артефактов кадров видеопотока при FPV-управлении беспилотными системам</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><name-alternatives><name xml:lang="en"><surname>Berezkin</surname><given-names>А. А.</given-names></name><name xml:lang="ru"><surname>Березкин</surname><given-names>А. А.</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>Associate Professor of Program Engineering and Computer Science Department, PhD in Technical Science</p></bio><bio xml:lang="ru"><p>к.т.н., доцент кафедры программной инженерии и вычислительной техники (ПИиВТ)</p></bio><email>berezkin.aa@sut.ru</email><xref ref-type="aff" rid="aff1"/></contrib><contrib contrib-type="author"><name-alternatives><name xml:lang="en"><surname>Chenskiy</surname><given-names>A. A.</given-names></name><name xml:lang="ru"><surname>Ченский</surname><given-names>А. А.</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>Master’s Degree Student of Program Engineering and Computer Science Department</p></bio><bio xml:lang="ru"><p>магистрант кафедры ПИиВТ</p></bio><email>chenskii.aa@sut.ru</email><xref ref-type="aff" rid="aff1"/></contrib><contrib contrib-type="author"><name-alternatives><name xml:lang="en"><surname>Kirichek</surname><given-names>R. V.</given-names></name><name xml:lang="ru"><surname>Киричек</surname><given-names>Р. В.</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>Rector, Professor of Program Engineering and Computer Science Department, Doctor of Technical Science</p></bio><bio xml:lang="ru"><p>д.т.н., ректор, профессор кафедры ПИиВТ</p></bio><email>kirichek@sut.ru</email><xref ref-type="aff" rid="aff1"/></contrib></contrib-group><aff-alternatives id="aff1"><aff><institution xml:lang="en">Bonch-Bruevich Saint Petersburg State University of Telecommunications</institution></aff><aff><institution xml:lang="ru">Санкт-Петербургский государственный университет телекоммуникаций им. проф. М.А. Бонч-Бруевича</institution></aff></aff-alternatives><pub-date date-type="pub" iso-8601-date="2025-03-09" publication-format="electronic"><day>09</day><month>03</month><year>2025</year></pub-date><volume>22</volume><issue>1</issue><issue-title xml:lang="en"/><issue-title xml:lang="ru"/><fpage>7</fpage><lpage>17</lpage><history><date date-type="received" iso-8601-date="2025-08-23"><day>23</day><month>08</month><year>2025</year></date><date date-type="accepted" iso-8601-date="2025-08-23"><day>23</day><month>08</month><year>2025</year></date></history><permissions><copyright-statement xml:lang="en">Copyright ©; 2025, Berezkin А.А., Chenskiy A.A., Kirichek R.V.</copyright-statement><copyright-statement xml:lang="ru">Copyright ©; 2025, Березкин А.А., Ченский А.А., Киричек Р.В.</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="en">Berezkin А.А., Chenskiy A.A., Kirichek R.V.</copyright-holder><copyright-holder xml:lang="ru">Березкин А.А., Ченский А.А., Киричек Р.В.</copyright-holder><ali:free_to_read xmlns:ali="http://www.niso.org/schemas/ali/1.0/"/><license><ali:license_ref xmlns:ali="http://www.niso.org/schemas/ali/1.0/">https://creativecommons.org/licenses/by-nc-nd/4.0</ali:license_ref></license></permissions><self-uri xlink:href="https://journals.eco-vector.com/2073-3909/article/view/689815">https://journals.eco-vector.com/2073-3909/article/view/689815</self-uri><abstract xml:lang="en"><p>Using packet networks for first-person control of unmanned systems arises a problem of large transmitted data volumes. The largest volume of traffic during first-person control is presented by video stream frames. So, to improve the efficiency of the communication network between unmanned systems and external pilot station, it is necessary to compress video stream frames. A high compression degree can be provided by using variational autoencoders. One of the problems of using variational autoencoders for frame compression is the occurrence of specific artifacts in frames. This article proposes methods for suppressing the occurrence of artifacts when restoring frames from the latent space by a neural network decoder, as well as an empirical scale for assessing autoencoder artifacts. The approach proposed encompasses preparing pixel data of a video stream frame for encoding and further reconstruction after decoding. It is experimentally shown that one of the proposed methods allows eliminating the absolute majority of artifacts without introducing significant distortions into the reconstructed frames.</p></abstract><trans-abstract xml:lang="ru"><p>При использовании пакетных сетей для управления беспилотными системами от первого лица возникает проблема большого объема передаваемых данных. Наибольший объем трафика при управлении от первого лица формируют кадры видеопотока. Соответственно, для повышения эффективности использования сети связи между беспилотными системами и станцией внешнего пилота необходимо осуществлять сжатие кадров видеопотока. Высокую степень сжатия обеспечивает использование вариационных автокодировщиков. Одной из проблем использования вариационных автокодировщиков для сжатия изображений является возникновение на изображениях специфичных артефактов. В настоящей статье предлагаются способы нивелирования возникновения артефактов при восстановлении изображений из латентного пространства нейросетевым декодером, а также предлагается эмпирическая шкала оценки артефактов автокодировщиков. Предложенный подход заключается в подготовке пиксельных данных кадра видеопотока к кодированию и восстановлению их после декодирования. Экспериментальным путем показано, что один из предложенных методов позволяет устранять абсолютное большинство артефактов без внесения существенных искажений в восстанавливаемые кадры. </p></trans-abstract><kwd-group xml:lang="en"><kwd>neural network</kwd><kwd>artifact suppression</kwd><kwd>frame artifacts</kwd><kwd>video stream transmission</kwd><kwd>variational autoencoder</kwd><kwd>neural codec</kwd><kwd>FPV-control</kwd><kwd>first person view control</kwd><kwd>unmanned systems</kwd><kwd>UAV</kwd><kwd>unmanned aircraft vehicles</kwd></kwd-group><kwd-group xml:lang="ru"><kwd>нейронная сеть</kwd><kwd>подавление артефактов</kwd><kwd>нивелирование артефактов</kwd><kwd>артефакты изображения</kwd><kwd>передача видеопотока</kwd><kwd>вариационный автокодировщик</kwd><kwd>нейросетевой кодек</kwd><kwd>FPV-управление</kwd><kwd>управление от первого лица</kwd><kwd>беспилотные системы</kwd><kwd>беспилотные воздушные суда</kwd></kwd-group><funding-group/></article-meta></front><body></body><back><ref-list><ref id="B1"><label>1.</label><citation-alternatives><mixed-citation xml:lang="en">Berezkin A.A. et al. Research of latent video stream compression methods for FPV control of uavs. Elektrosvjaz’, 2024, no. 6, pp. 26–36. (In Russ.)</mixed-citation><mixed-citation xml:lang="ru">Исследование методов латентного сжатия видеопотока при FPV управлении беспилотными системами / А.А. Березкин [и др.] // Электросвязь. 2024. № 6. С. 26–36.</mixed-citation></citation-alternatives></ref><ref id="B2"><label>2.</label><citation-alternatives><mixed-citation xml:lang="en">Berezkin A.A. et al. Research of latent space quantization methods of variational autoencoder for FPV video stream frames. Part I. Elektrosvjaz’, 2024, no. 6, pp. 10–16. (In Russ.)</mixed-citation><mixed-citation xml:lang="ru">Исследование методов квантования латентного пространства вариационного автокодировщика для кадров FPV видеопотока. Часть I / А.А. Березкин [и др.] // Электросвязь. 2024. № 6. С. 10–16.</mixed-citation></citation-alternatives></ref><ref id="B3"><label>3.</label><citation-alternatives><mixed-citation xml:lang="en">Project of the strategy for the development of the telecommunications industry of the Russian Federation for the period up to 2035 [adopted by the Government of Russian Federation on November 24, 2023]. URL: https://digital.gov.ru/ru/documents/9120/ (accessed: 27.07.2024). (In Russ.)</mixed-citation><mixed-citation xml:lang="ru">Проект стратегии развития отрасли связи Российской Федерации на период до 2035 года [утвержден Правительством Российской Федерации 24 ноября 2023 г.]. URL: https://digital.gov.ru/ru/documents/9120/ (дата обращения: 27.07.2024).</mixed-citation></citation-alternatives></ref><ref id="B4"><label>4.</label><citation-alternatives><mixed-citation xml:lang="en">ITU-Т Recommendation H.264. Improved Image Encoding for General Audiovisual Services. Geneva, 2008, 342 p. (In Russ.)</mixed-citation><mixed-citation xml:lang="ru">Рекомендация МСЭ Т Н.264. Усовершенствованное кодирование изображения для общихаудиовизуальных услуг. Женева, 2008. 342 с.</mixed-citation></citation-alternatives></ref><ref id="B5"><label>5.</label><citation-alternatives><mixed-citation xml:lang="en">ITU-T Recommendation H.265 (V9). High Efficiency Video Coding. Geneva, 2023, 718 p.</mixed-citation><mixed-citation xml:lang="ru">Recommendation ITU-T H.265 (V9). High Efficiency Video Coding. Geneva, 2023. 718 p.</mixed-citation></citation-alternatives></ref><ref id="B6"><label>6.</label><citation-alternatives><mixed-citation xml:lang="en">ISO/IEC 10918-1:1994. Information Technology – Digital Compression and Coding of Continuous-Tone Still Images: Requirements and Guidelines. URL: https://www.iso.org/ru/standard/ 18902.html (accessed: 27.07.2024).</mixed-citation><mixed-citation xml:lang="ru">ISO/IEC 10918-1:1994. Information Technology – Digital Compression and Coding of Continuous-Tone Still Images: Requirements and Guidelines. URL: https:// www.iso.org/ru/standard/18902.html (дата обращения: 27.07.2024).</mixed-citation></citation-alternatives></ref><ref id="B7"><label>7.</label><citation-alternatives><mixed-citation xml:lang="en">Barman N., Martini M.G. An evaluation of the next-generation image coding standard AVIF. 2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX), 2020, pp. 1–4.</mixed-citation><mixed-citation xml:lang="ru">Barman N., Martini M.G. An evaluation of the next-generation image coding standard AVIF // 2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX). 2020. P. 1–4.</mixed-citation></citation-alternatives></ref><ref id="B8"><label>8.</label><citation-alternatives><mixed-citation xml:lang="en">Ginesu G., Pintus M., Giusto D.D. Objective assessment of the WebP image coding algorithm. Signal Processing: Image Communication, 2012, vol. 27, no. 8, pp. 867–874.</mixed-citation><mixed-citation xml:lang="ru">Ginesu G., Pintus M., Giusto D.D. Objective assessment of the WebP image coding algorithm // Signal Processing: Image Communication. 2012. Vol. 27, no. 8. P. 867–874.</mixed-citation></citation-alternatives></ref><ref id="B9"><label>9.</label><citation-alternatives><mixed-citation xml:lang="en">Berezkin A.A. et al. Research of methods of quantization of latent space of variational autoencoder for FPV video stream frames. Part II. Elektrosvjaz’, 2024, no. 7, pp. 16–25. (In Russ.)</mixed-citation><mixed-citation xml:lang="ru">Исследование методов квантования латентного пространства вариационного автокодировщика для кадров FPV видеопотока. Часть II / А.А. Березкин [и др.] // Электросвязь. 2024. № 7. С. 16–25.</mixed-citation></citation-alternatives></ref><ref id="B10"><label>10.</label><citation-alternatives><mixed-citation xml:lang="en">Jiang J., Zhang K., Timofte R. Towards flexible blind JPEG artifacts removal. IEEE/CVF International Conference on Computer Vision, 2021, pp. 4997–5006.</mixed-citation><mixed-citation xml:lang="ru">Jiang J., Zhang K., Timofte R. Towards flexible blind JPEG artifacts removal // IEEE/CVF International Conference on Computer Vision. 2021. P. 4997–5006.</mixed-citation></citation-alternatives></ref><ref id="B11"><label>11.</label><citation-alternatives><mixed-citation xml:lang="en">Saveljev V., Kim S. K., Kim J. Moire effect in displays: A tutorial. Optical Engineering, 2018, vol. 57, no. 3. URL: https://www.researchgate.net/publication/324074641_Moire_effect_in_displays_A_tutorial (accessed: 07.2024).</mixed-citation><mixed-citation xml:lang="ru">Saveljev V., Kim S.K., Kim J. Moire effect in displays: A tutorial // Optical Engineering. 2018. Vol. 57, no. 3. URL: https://www.researchgate.net/publication/324074641_Moire_effect_in_displays_A_tutorial (дата обращения: 22.07.2024).</mixed-citation></citation-alternatives></ref><ref id="B12"><label>12.</label><citation-alternatives><mixed-citation xml:lang="en">Zaitsev M., Maclaren J., Herbst M. Motion artifacts in MRI: A complex problem with many partial solutions. Journal of Magnetic Resonance Imaging, 2015, vol. 42, no. 4, pp. 887–901.</mixed-citation><mixed-citation xml:lang="ru">Zaitsev M., Maclaren J., Herbst M. Motion artifacts in MRI: a complex problem with many partial solutions // Journal of Magnetic Resonance Imaging. 2015. Vol. 42, no. 4. P. 887–901.</mixed-citation></citation-alternatives></ref><ref id="B13"><label>13.</label><citation-alternatives><mixed-citation xml:lang="en">Castellanos N.P., Makarov V.A. Recovering EEG brain signals: Artifact suppression with wavelet enhanced independent component analysis. Journal of Neuroscience Methods, 2006, vol. 158, no. 2, pp. 300–312.</mixed-citation><mixed-citation xml:lang="ru">Castellanos N.P., Makarov V.A. Recovering EEG brain signals: artifact suppression with wavelet enhanced independent component analysis // Journal of Neuroscience Methods. 2006. Vol. 158, no. 2. P. 300–312.</mixed-citation></citation-alternatives></ref><ref id="B14"><label>14.</label><citation-alternatives><mixed-citation xml:lang="en">Wagenaar D.A., Potter S.M. Real-time multi-channel stimulus artifact suppression by local curve fitting. Journal of Neuroscience Methods, 2002, vol. 120, no. 2, pp. 113–120.</mixed-citation><mixed-citation xml:lang="ru">Wagenaar D.A., Potter S.M. Real-time multichannel stimulus artifact suppression by local curve fitting // Journal of Neuroscience Methods. 2002. Vol. 120, no. 2. P. 113–120.</mixed-citation></citation-alternatives></ref><ref id="B15"><label>15.</label><citation-alternatives><mixed-citation xml:lang="en">Galteri L. et al. Deep generative adversarial compression artifact removal. IEEE International Conference on Computer Vision (ICCV), 2017, pp. 4826–4835.</mixed-citation><mixed-citation xml:lang="ru">Deep generative adversarial compression artifact removal / L. Galteri [et al.] // IEEE International Conference on Computer Vision (ICCV). 2017. P. 4826–4835.</mixed-citation></citation-alternatives></ref><ref id="B16"><label>16.</label><citation-alternatives><mixed-citation xml:lang="en">Cavigelli L., Hager P., Benini L. CAS-CNN: A deep convolutional neural network for image compression artifact suppression. 2017 International Joint Conference on Neural Networks (IJCNN), 2017, pp. 752–759.</mixed-citation><mixed-citation xml:lang="ru">Cavigelli L., Hager P., Benini L. CAS-CNN: A deep convolutional neural network for image compression artifact suppression // 2017 International Joint Conference on Neural Networks (IJCNN). 2017. P. 752–759.</mixed-citation></citation-alternatives></ref><ref id="B17"><label>17.</label><citation-alternatives><mixed-citation xml:lang="en">Yeh C.H. et al. Deep learning-based compressed image artifacts reduction based on multi-scale image fusion. Information Fusion, 2021, vol. 67, no. 4, pp. 195–207.</mixed-citation><mixed-citation xml:lang="ru">Deep learning-based compressed image artifacts reduction based on multi-scale image fusion / C.H. Yeh [et al.] // Information Fusion. 2021. Vol. 67, no. 4. P. 195–207.</mixed-citation></citation-alternatives></ref><ref id="B18"><label>18.</label><citation-alternatives><mixed-citation xml:lang="en">Github. Stable diffusion: development repository. URL: https://github.com/pesser/stable-diffusion/tree/main (accessed: 28.07.2024).</mixed-citation><mixed-citation xml:lang="ru">Github. Stable diffusion: development repository. URL: https://github.com/pesser/stable-diffusion/tree/main (дата обращения: 28.07.2024).</mixed-citation></citation-alternatives></ref><ref id="B19"><label>19.</label><citation-alternatives><mixed-citation xml:lang="en">Github. Lossy Image compression with conditional diffusion models.URL: https://github.com/buggyyang/CDC_compression (accessed: 28.07.2024).</mixed-citation><mixed-citation xml:lang="ru">Github. Lossy image compression with conditional diffusion models. URL: https://github.com/buggyyang/CDC_compression (дата обращения: 28.07.2024).</mixed-citation></citation-alternatives></ref></ref-list></back></article>
