<?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">inttrans</journal-id><journal-title-group><journal-title xml:lang="ru">Интеллектуальный транспорт</journal-title><trans-title-group xml:lang="en"><trans-title>Intelligent transport</trans-title></trans-title-group></journal-title-group><issn pub-type="epub">3033-6007</issn><publisher><publisher-name>АО «НИИАС»</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.24412/3033-6007-2026-339-69-84</article-id><article-id custom-type="elpub" pub-id-type="custom">inttrans-117</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>ИНТЕЛЛЕКТҮАЛbНЫЕ ТРАНСПОРТНЫЕ СИСТЕМЫ</subject></subj-group></article-categories><title-group><article-title>Интерпретируемое управление инициацией треков с заранее заданными границами вмешательства в системах восприятия беспилотных летательных аппаратов</article-title><trans-title-group xml:lang="en"><trans-title>Interpretable Control of Track Initiation with Predefined Intervention Bounds in Unmanned Aerial Vehicle Perception Systems</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Трофимов</surname><given-names>Ю. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Trofimov</surname><given-names>Yu. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>ассистент кафедры системного анализа и управления, младший научный сотрудник</p></bio><bio xml:lang="en"><p>Assistant Lecturer, Department of Systems Analysis and Management, Junior Researcher</p></bio><email xlink:type="simple">ura_trofim@bk.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>Аверкин</surname><given-names>А. Н.</given-names></name><name name-style="western" xml:lang="en"><surname>Averkin</surname><given-names>A. N.</given-names></name></name-alternatives><bio xml:lang="ru"><p>ведущий научный сотрудник; доцент, ведущий научный сотрудник</p></bio><bio xml:lang="en"><p>Leading Researcher; Associate Professor, Leading Researcher</p></bio><email xlink:type="simple">averkin2003@inbox.ru</email><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Шевченко</surname><given-names>А. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Shevchenko</surname><given-names>A. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>старший преподаватель, научный сотрудник</p></bio><bio xml:lang="en"><p>Senior Lecturer, Researcher</p></bio><email xlink:type="simple">leviathan0909@gmail.com</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>Кузнецов</surname><given-names>Е. М.</given-names></name><name name-style="western" xml:lang="en"><surname>Kuznetsov</surname><given-names>E. M.</given-names></name></name-alternatives><bio xml:lang="ru"><p>программист научно-исследовательского центра ИИ</p></bio><bio xml:lang="en"><p>Programmer at the Artificial Intelligence Research Center</p></bio><email xlink:type="simple">kem.22@uni-dubna.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>Лебедев</surname><given-names>А. Д.</given-names></name><name name-style="western" xml:lang="en"><surname>Lebedev</surname><given-names>A. D.</given-names></name></name-alternatives><bio xml:lang="ru"><p>техник научно-исследовательского центра ИИ</p></bio><bio xml:lang="en"><p>Technician at the Artificial Intelligence Research Center</p></bio><email xlink:type="simple">lad.24@uni-dubna.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Государственный университет «Дубна»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Dubna State University</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Федеральный исследовательский центр «Информатика и управление» Российской академии наук (ФИЦ ИУ РАН); Государственный университет «Дубна»</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Federal Research Center «Computer Science and Control» of the Russian Academy of Sciences; Dubna State University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>27</day><month>09</month><year>2026</year></pub-date><volume>10</volume><issue>3(39)</issue><fpage>69</fpage><lpage>84</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Трофимов Ю.В., Аверкин А.Н., Шевченко А.В., Кузнецов Е.М., Лебедев А.Д., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Трофимов Ю.В., Аверкин А.Н., Шевченко А.В., Кузнецов Е.М., Лебедев А.Д.</copyright-holder><copyright-holder xml:lang="en">Trofimov Y.V., Averkin A.N., Shevchenko A.V., Kuznetsov E.M., Lebedev A.D.</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://www.intelligent-transport.ru/jour/article/view/117">https://www.intelligent-transport.ru/jour/article/view/117</self-uri><abstract><p>В системах воздушного наблюдения единичная ошибка обнаружения может закрепиться в виде устойчивого ложного трека и повлиять на данные, передаваемые последующим компонентам. Цель работы – уменьшить число таких ошибок, заранее ограничив масштаб вмешательства и сохранив возможность проследить логику каждого решения. Предложен внешний метод кратковременной задержки эпизодов инициации треков с низкой поддержкой. Число задержек регулируется накопительным бюджетом, а для каждого эпизода сохраняются оценка поддержки, текущий баланс бюджета, причина вмешательства и конечный статус. Метод апробирован на семи видеопоследовательностях из общедоступного набора аэросъёмки, содержащего малые объекты, частичные перекрытия и заметные изменения масштаба. В эксперименте сравнивались три алгоритма сопровождения и обучаемый метод на основе ансамбля решающих деревьев. Для ByteTrack задержка была применена к 2,62% эпизодов инициации, из оперативного выхода исключены 425 ложных наблюдений и 176 ложных инициаций, а изменение объединённого показателя точности и полноты осталось в пределах установленного допуска. Для OC-SORT и SORT снижение ложных наблюдений по принятому статистическому критерию не подтверждено. Проверка 29 385 начальных фрагментов видеозаписей не выявила нарушений заранее заданных ограничений. Средние дополнительные вычислительные затраты составили 0,901 миллисекунды на кадр. Результаты показывают, что кратковременная задержка может сократить число ложных наблюдений при контролируемом масштабе вмешательства.</p></abstract><trans-abstract xml:lang="en"><p>In aerial monitoring systems, a single detection error may develop into a persistent false track and affect data passed to downstream components. The study aims to reduce such errors while bounding the scale of intervention in advance and retaining a traceable account of each decision. An external method is proposed that briefly delays low-support track-initiation episodes. The number of delays is controlled by an accumulated budget, while the support estimate, current budget balance, reason for intervention, and final status are recorded for each episode. The method was evaluated on seven video sequences from a publicly available aerial-imagery dataset containing small objects, partial occlusions, and substantial scale changes. Three tracking algorithms and a supervised ensemble of decision trees were compared. For ByteTrack, the delay was applied to 2.62 percent of track-initiation episodes, removing 425 false observations and 176 false initiations from the operational output, while the change in the combined precision-recall measure remained within the predefined tolerance. For OC-SORT and SORT, the reduction in false observations was not confirmed under the adopted statistical criterion. An examination of 29,385 initial video fragments found no violations of the predefined limits. The additional processing time averaged 0.901 milliseconds per frame. The results show that a short delay can reduce the number of false observations while keeping the scale of intervention under control.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>интеллектуальные транспортные системы</kwd><kwd>беспилотные летательные аппараты</kwd><kwd>сопровождение объектов</kwd><kwd>инициация треков</kwd><kwd>ограниченное вмешательство</kwd><kwd>интерпретируемый искусственный интеллект</kwd><kwd>кратковременная задержка</kwd></kwd-group><kwd-group xml:lang="en"><kwd>intelligent transport systems</kwd><kwd>unmanned aerial vehicles</kwd><kwd>object tracking</kwd><kwd>track initiation</kwd><kwd>bounded intervention</kwd><kwd>interpretable artificial intelligence</kwd><kwd>short-term delay</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Исследование выполнено в рамках государственного задания Министерства науки и высшего образования Российской Федерации, тема № 124112200072-2.</funding-statement><funding-statement xml:lang="en">The study was carried out within the framework of the state assignment of the Ministry of Science and Higher Education of the Russian Federation, topic No. 124112200072-2.</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">Kalman, R. E. A New Approach to Linear Filtering and Prediction Problems / R. E. Kalman // Journal of Basic Engineering. – 1960. – Vol. 82, No. 1. – P. 35–45. – DOI 10.1115/1.3662552.</mixed-citation><mixed-citation xml:lang="en">Kalman, R. E. (1960). A new approach to linear filtering and prediction problems. Journal of Basic Engineering, 82(1), 35–45. https://doi.org/10.1115/1.3662552</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Simple Online and Realtime Tracking / A. Bewley, Z. Ge, L. Ott [et al.] // Proceedings of the IEEE International Conference on Image Processing. – Piscataway, NJ : IEEE, 2016. – P. 3464–3468. – DOI 10.1109/ICIP.2016.7533003.</mixed-citation><mixed-citation xml:lang="en">Bewley, A., Ge, Z., Ott, L., Ramos, F., &amp; Upcroft, B. (2016). Simple online and realtime tracking. In Proceedings of the IEEE International Conference on Image Processing (pp. 3464–3468). IEEE. https://doi.org/10.1109/ICIP.2016.7533003</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">ByteTrack: Multi-Object Tracking by Associating Every Detection Box / Y. Zhang, P. Sun, Y. Jiang [et al.] // European Conference on Computer Vision. – Cham : Springer, 2022. – P. 1–21. – DOI 10.1007/978-3-031-20047-2_1.</mixed-citation><mixed-citation xml:lang="en">Zhang, Y., Sun, P., Jiang, Y., Yu, D., Weng, F., Yuan, Z., Luo, P., Liu, W., &amp; Wang, X. (2022). ByteTrack: Multi-object tracking by associating every detection box. In European Conference on Computer Vision (pp. 1–21). Springer. https://doi.org/10.1007/978-3-031-20047-2_1</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking / J. Cao, J. Pang, X. Weng [et al.] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. – Piscataway, NJ : IEEE, 2023. – P. 9686–9696. – DOI 10.1109/CVPR52729.2023.00934.</mixed-citation><mixed-citation xml:lang="en">Cao, J., Pang, J., Weng, X., Khirodkar, R., &amp; Kitani, K. (2023). Observation-centric SORT: Rethinking SORT for robust multi-object tracking. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 9686–9696). IEEE. https://doi.org/10.1109/CVPR52729.2023.00934</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">StrongSORT: Make DeepSORT Great Again / Y. Du, Z. Zhao, Y. Song [et al.] // IEEE Transactions on Multimedia. – 2023. – Vol. 25. – P. 8725–8737. – DOI 10.1109/TMM.2023.3240881.</mixed-citation><mixed-citation xml:lang="en">Du, Y., Zhao, Z., Song, Y., Zhao, Y., Su, F., Gong, T., &amp; Meng, H. (2023). StrongSORT: Make DeepSORT great again. IEEE Transactions on Multimedia, 25, 8725–8737. https://doi.org/10.1109/TMM.2023.3240881</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Wojke, N. Simple Online and Realtime Tracking with a Deep Association Metric / N. Wojke, A. Bewley, D. Paulus // Proceedings of the IEEE International Conference on Image Processing. – Piscataway, NJ : IEEE, 2017. – P. 3645–3649. – DOI 10.1109/ICIP.2017.8296962.</mixed-citation><mixed-citation xml:lang="en">Wojke, N., Bewley, A., &amp; Paulus, D. (2017). Simple online and realtime tracking with a deep association metric. In Proceedings of the IEEE International Conference on Image Processing (pp. –3649). IEEE. https://doi.org/10.1109/ICIP.2017.8296962</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Bergmann, P. Tracking Without Bells and Whistles / P. Bergmann, T. Meinhardt, L. Leal-Taix´e // Proceedings of the IEEE/CVF International Conference on Computer Vision. – Piscataway, NJ : IEEE, 2019. – P. 941–951. – DOI 10.1109/ICCV.2019.00103.</mixed-citation><mixed-citation xml:lang="en">Bergmann, P., Meinhardt, T., &amp; Leal-Taixé, L. (2019). Tracking without bells and whistles. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 941–951). IEEE. https://doi.org/10.1109/ICCV.2019.00103</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Breiman, L. Random Forests / L. Breiman // Machine Learning. – 2001. – Vol. 45, No. 1. – P. 5–32. – DOI 10.1023/A:1010933404324.</mixed-citation><mixed-citation xml:lang="en">Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1/A:1010933404324</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Geifman, Y. Selective Classification for Deep Neural Networks / Y. Geifman, R. El-Yaniv // Advances in Neural Information Processing Systems. – 2017. – Vol. 30. – P. 4878–4887.</mixed-citation><mixed-citation xml:lang="en">Geifman, Y., &amp; El-Yaniv, R. (2017). Selective classification for deep neural networks. In Advances in Neural Information Processing Systems (Vol. 30, pp. 4878–4887). Curran Associates.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">VisDrone-VDT2018: The Vision Meets Drone Video Detection and Tracking Challenge Results / P. Zhu, L. Wen, D. Du [et al.] // Computer Vision – ECCV 2018 Workshops. – Cham : Springer, 2019. – P. 496–518. – DOI 10.1007/978-3-030-11021-5_29.</mixed-citation><mixed-citation xml:lang="en">Zhu, P., Wen, L., Du, D., et al. (2019). VisDrone-VDT2018: The vision meets drone video detection and tracking challenge results. In Computer Vision – ECCV 2018 Workshops (pp.–518). Springer. https://doi.org/10.1007/978-3-030-11021-5_29</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">U2UData: A Large-scale Cooperative Perception Dataset for Swarm UAVs Autonomous Flight / T. Feng, X. Wang, F. Han [et al.] // Proceedings of the 32nd ACM International Conference on Multimedia. – New York : ACM, 2024. – P. 7600–7608. – DOI 10.1145/3664647.3681151.</mixed-citation><mixed-citation xml:lang="en">Feng, T., Wang, X., Han, F., Zhang, L., &amp; Zhu, W. (2024). U2UData: A large-scale cooperative perception dataset for swarm UAVs autonomous flight. In Proceedings of the 32nd ACM International Conference on Multimedia (pp. 7600–7608). ACM. https://doi.org/10.1145/363681151</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">V2U4Real: A Real-world Large-scale Dataset for Vehicle-to-UAV Cooperative Perception / W. Li, H. Xiang, T. Wang [et al.] // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. – Piscataway, NJ : IEEE, 2026. – P. 4728–4737.</mixed-citation><mixed-citation xml:lang="en">Li, W., Xiang, H., Wang, T., Wu, S., Xia, Q., Wang, C., &amp; Wen, C. (2026). V2U4Real: A real-world large-scale dataset for vehicle-to-UAV cooperative perception. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4728–4737). IEEE.</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>
