<?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">koz</journal-id><journal-title-group><journal-title xml:lang="ru">"Вестник Северо-Казахстанского университета имени Манаша Козыбаева"</journal-title><trans-title-group xml:lang="en"><trans-title>Bulletin of Manash Kozybayev North Kazakhstan University</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2958-003X</issn><issn pub-type="epub">2958-0048</issn><publisher><publisher-name>М. Қозыбаев атындағы СҚУ</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.54596/2958-0048-2025-2-194-206</article-id><article-id custom-type="elpub" pub-id-type="custom">koz-2233</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>ИНФОРМАЦИОННО-КОММУНИКАЦИОННЫЕ ТЕХНОЛОГИИ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>INFORMATION AND COMMUNICATION TECHNOLOGIES</subject></subj-group></article-categories><title-group><article-title>Масштабируемые конвейеры для мгновенного обнаружения объектов: развертывание моделей YOLO с Apache Kafka  для высокопроизводительного инференса</article-title><trans-title-group xml:lang="en"><trans-title>Scalable pipelines for instant object detection: deploying YOLO models with Apache Kafka for high-throughput inference</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>Озтел</surname><given-names>И.</given-names></name><name name-style="western" xml:lang="en"><surname>Oztel</surname><given-names>I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Исмаил Озтел</p><p>Кафедра компьютерной инженерии, Факультет компьютерных и информационных наук</p><p>Сакарья</p><p> </p></bio><bio xml:lang="en"><p>Ismail Oztel, Assistant Professor, Department of Computer Engineering, Faculty of Computer and Information Sciences, Intelligent Software Systems Research Lab</p><p>Sakarya</p><p> </p></bio><email xlink:type="simple">ioztel@sakarya.edu.tr</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>Чекен</surname><given-names>Дж.</given-names></name><name name-style="western" xml:lang="en"><surname>Ceken</surname><given-names>C.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Джелял Чекен</p><p>Университет Сакарьи, Кафедра компьютерной инженерии, Факультет компьютерных и информационных наук; НАО «Северо-Казахстанский университет имени Манаша Козыбаева» Международный кампус</p><p>Сакарья, Петропавловск</p><p> </p><p> </p></bio><bio xml:lang="en"><p>Celal Ceken, corresponding author, Professor, Department of Computer Engineering, Sakarya University; Professor, Manash Kozybayev North Kazakhstan University NPLC, International Campus</p><p>Sakarya, Petropavlovsk</p></bio><email xlink:type="simple">celalceken@sakarya.edu.tr</email><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru">Университет Сакарьи<country>Турция</country></aff><aff xml:lang="en">Sakarya University<country>Turkey</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru">Университет Сакарьи;&#13;
НАО «Северо-Казахстанский университет имени Манаша Козыбаева»<country>Турция</country></aff><aff xml:lang="en">Sakarya University;&#13;
Manash Kozybayev North Kazakhstan University NPLC<country>Turkey</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>04</day><month>07</month><year>2025</year></pub-date><volume>0</volume><issue>2 (66)</issue><fpage>194</fpage><lpage>206</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Озтел И., Чекен Д., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Озтел И., Чекен Д.</copyright-holder><copyright-holder xml:lang="en">Oztel I., Ceken C.</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://vestnik.ku.edu.kz/jour/article/view/2233">https://vestnik.ku.edu.kz/jour/article/view/2233</self-uri><abstract><p>Мгновенное обнаружение объектов является критически важной возможностью в современных приложениях, где необходимо оперативное принятие решений, например, в неотложной медицине, автономных системах и интеллектуальном видеонаблюдении. Эффективная обработка потоков изображений с высокой пропускной способностью и минимальной задержкой представляет собой значительную задачу, особенно в условиях высокой нагрузки. В данном исследовании представлена масштабируемая конвейерная архитектура для обнаружения объектов, интегрирующая модели YOLO с Apache Kafka – распределённой потоковой платформой, поддерживающей инференс в режиме just-in-time. Предлагаемая архитектура использует механизмы партиционирования и групп потребителей Kafka для обеспечения параллельной обработки, что позволяет достичь высокой производительности без необходимости в сложной логике балансировки нагрузки. Система развернута на виртуальном частном сервере (VPS) для демонстрации практической реализации. Представлены две конфигурации для иллюстрации масштабируемости Kafka: одна с одним разделом и одним потребителем, и другая с пятью разделами и пятью потребителями. Эти настройки наглядно демонстрируют, как Kafka эффективно распределяет рабочую нагрузку между несколькими потребителями. Хотя конкретные показатели задержки или пропускной способности не приведены, архитектура эффективно демонстрирует, как дизайн Kafka обеспечивает оперативную реакцию на вход с высоким объемом. Этот конвейер хорошо подходит для задач обнаружения объектов, чувствительных ко времени, и может быть расширен для широкого круга приложений моментальной аналитики, где критически важна быстрая обратная связь.</p></abstract><trans-abstract xml:lang="en"><p>Instant object detection is a critical capability in modern applications where timely decision-making is essential, such as in emergency medicine, autonomous systems, and intelligent surveillance. Efficiently handling high-throughput image streams with minimal delay presents significant challenges, particularly under demanding conditions. This study presents a scalable object detection pipeline that integrates YOLO models with Apache Kafka, a distributed streaming platform, to support just-in-time inference. The proposed architecture leverages Kafka’s partitioning and consumer group mechanisms to enable parallel processing, ensuring high throughput without requiring complex load-balancing logic. The system is deployed on a Virtual Private Server to demonstrate practical implementation. Two configurations are presented to illustrate Kafka’s native scalability: one with a single partition and a single consumer, and another with five partitions and five consumers. These setups visually demonstrate how Kafka efficiently distributes workloads across multiple consumers. Although specific latency or throughput metrics are not reported, the architecture effectively showcases how Kafka’s design enables prompt responses to high-volume input. This pipeline is well-suited for time-sensitive object detection tasks and can be extended to a wide range of instant analytics applications where rapid feedback is critical.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>Мгновенное обнаружение объектов</kwd><kwd>Высокопроизводительный инференс</kwd><kwd>Apache Kafka</kwd><kwd>Модель YOLO</kwd><kwd>Масштабируемая потоковая обработка</kwd></kwd-group><kwd-group xml:lang="en"><kwd>Instant object detection</kwd><kwd>High-Throughput Inference</kwd><kwd>Apache Kafka</kwd><kwd>YOLO model</kwd><kwd>Scalable stream processing</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">Redmon, J., Divvala, S., Girshick, R., &amp; Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779-788.</mixed-citation><mixed-citation xml:lang="en">Redmon, J., Divvala, S., Girshick, R., &amp; Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779-788.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Han, S., Lee, H., &amp; Park, Y. (2018). A Real-Time Object Detection System Based on Cloud and Edge Computing. In International Conference on Cloud Computing and Big Data (CloudCom), pp. 153-160.</mixed-citation><mixed-citation xml:lang="en">Han, S., Lee, H., &amp; Park, Y. (2018). A Real-Time Object Detection System Based on Cloud and Edge Computing. In International Conference on Cloud Computing and Big Data (CloudCom), pp. 153-160.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Shi, Y., Ding, G., &amp; Wu, Q. (2019). Edge Computing: Vision and Challenges. IEEE Internet of Things Journal, 6(3), 4724-4737.</mixed-citation><mixed-citation xml:lang="en">Shi, Y., Ding, G., &amp; Wu, Q. (2019). Edge Computing: Vision and Challenges. IEEE Internet of Things Journal, 6(3), 4724-4737.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Apache Kafka. Apache Kafka Documentation. Available at: https://kafka.apache.org/39/documentation.html (Accessed: May 2025).</mixed-citation><mixed-citation xml:lang="en">Apache Kafka. Apache Kafka Documentation. Available at: https://kafka.apache.org/39/documentation.html (Accessed: May 2025).</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">J. Redmon and A. Farhadi, “YOLO9000: Better, Faster, Stronger,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 6517-6525, Jul. 2017. doi: 10.1109/cvpr.2017.690.</mixed-citation><mixed-citation xml:lang="en">J. Redmon and A. Farhadi, “YOLO9000: Better, Faster, Stronger,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 6517-6525, Jul. 2017. doi: 10.1109/cvpr.2017.690.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">A. Soni and A. Rai, “YOLO for Medical Object Detection (2018-2024),” 2024 IEEE 3rd International Conference on Electrical Power and Energy Systems (ICEPES). IEEE, pp. 1-7, Jun. 21, 2024. doi: 10.1109/icepes60647.2024.10653506.</mixed-citation><mixed-citation xml:lang="en">A. Soni and A. Rai, “YOLO for Medical Object Detection (2018-2024),” 2024 IEEE 3rd International Conference on Electrical Power and Energy Systems (ICEPES). IEEE, pp. 1-7, Jun. 21, 2024. doi: 10.1109/icepes60647.2024.10653506.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">C.M. Badgujar, A. Poulose, and H. Gan, “Agricultural object detection with You Only Look Once (YOLO) Algorithm: A bibliometric and systematic literature review,” Computers and Electronics in Agriculture, vol. 223, p. 109090, Aug. 2024, doi: 10.1016/j.compag.2024.109090.</mixed-citation><mixed-citation xml:lang="en">C.M. Badgujar, A. Poulose, and H. Gan, “Agricultural object detection with You Only Look Once (YOLO) Algorithm: A bibliometric and systematic literature review,” Computers and Electronics in Agriculture, vol. 223, p. 109090, Aug. 2024, doi: 10.1016/j.compag.2024.109090.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">H. Chen, “YOLO Algorithm in Analysis and Design of Athletes’ Actions in College Physical Education,” 2024 International Conference on Interactive Intelligent Systems and Techniques (IIST). IEEE, pp. 764-768, Mar. 04, 2024. doi: 10.1109/iist62526.2024.00002.</mixed-citation><mixed-citation xml:lang="en">H. Chen, “YOLO Algorithm in Analysis and Design of Athletes’ Actions in College Physical Education,” 2024 International Conference on Interactive Intelligent Systems and Techniques (IIST). IEEE, pp. 764-768, Mar. 04, 2024. doi: 10.1109/iist62526.2024.00002.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">R. Girshick, “Fast R-CNN,” 2015 IEEE International Conference on Computer Vision (ICCV). IEEE, Dec. 2015. doi: 10.1109/iccv.2015.169.</mixed-citation><mixed-citation xml:lang="en">R. Girshick, “Fast R-CNN,” 2015 IEEE International Conference on Computer Vision (ICCV). IEEE, Dec. 2015. doi: 10.1109/iccv.2015.169.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Ultralytics, "YOLOv12 Models," Ultralytics Documentation. Available at: https://docs.ultralytics.com/tr/models/yolo12/. (Accessed: May 2025).</mixed-citation><mixed-citation xml:lang="en">Ultralytics, "YOLOv12 Models," Ultralytics Documentation. Available at: https://docs.ultralytics.com/tr/models/yolo12/. (Accessed: May 2025).</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Artillery Docs. Available at: https://www.artillery.io/docs (Accessed: May 2025).</mixed-citation><mixed-citation xml:lang="en">Artillery Docs. Available at: https://www.artillery.io/docs (Accessed: May 2025).</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>
