sibadiНаучный рецензируемый журнал "Вестник СибАДИ"The Russian Automobile and Highway Industry Journal2071-72962658-5626The Siberian State Automobile and Highway University10.26518/2071-7296-2025-22-6-916-927RGQURRsibadi-2116Research ArticleТРАНСПОРТTRANSPORTДетекция и классификация опасных маневров на основе видеоданных с дорожных камерDetection and classification of dangerous maneuvers based on traffic camera recordingshttps://orcid.org/0000-0002-7086-6278НовиковА. Н.NovikovA. N.

Новиков Александр Николаевич – д-р техн. наук, проф., заведующий кафедрой «Сервис и ремонт машин»

Scopus ID: 57225227480, Author ID: 143921, Researcher ID: M-4302-2017

302002, г. Орел, ул. Московская, д. 77 

Novikov Alexander N. – Doctor of Technical Sciences, Professor, Head of the Department of Machine Service and Repair

Scopus ID: 57225227480, Author ID: 143921, Researcher ID: M-4302-2017

77, Moskovskaya str., Orel, 302002 

novikovan57@gmail.comhttps://orcid.org/0000-0002-3564-6026КущенкоЛ. Е.KushchenkoL. E.

Кущенко Лилия Евгеньевна – д-р техн. наук, доц., проф. кафедры «Эксплуатация и организация движения автотранспорта»

Scopus ID: 57193997889, Author ID: 746460

308012, г. Белгород, ул. Костюкова, д. 46

Kushchenko Liliya E. – Doctor of Technical Sciences, Associate Professor, Professor of the Department of Vehicle Operation and Traffic Management

Scopus ID: 57193997889, Author ID: 746460

46 Kostyukova str., Belgorod, 308012 

lily-041288@mail.ruhttps://orcid.org/0009-0006-6181-5790КущенкоС. В.KushchenkoS. V.

Кущенко Сергей Викторович -– канд. техн. наук, доц. кафедры «Эксплуатация и организация движения автотранспорта»

Scopus ID: 57193997343, Author ID: 970275

308012, г. Белгород, ул. Костюкова, д. 46

Kushchenko Sergey V. – Candidate of Technical Sciences, Associate Professor, Associate Professor of the Department of Vehicle Operation and Traffic Management

Scopus ID: 57193997343, Author ID: 970275

46 Kostyukova str., Belgorod, 308012 

serega_ku@mail.ruУлинецИ. А.UlinetsI. A.

Улинец Иосиф Алексеевич – аспирант  

Author ID: 1272489 

308012, г. Белгород, ул. Костюкова, д. 46

Ulinets Iosif A. – Postgraduate Student 

Author ID: 1272489 

6 Kostyukova str., Belgorod, 308012 

ulinetz.iosif@yandex.ruОрловский государственный университет им. И.С. ТургеневаРоссияOrel State University named after I.S. TurgenevRussian FederationБелгородский государственный технологический университет имени В.Г. ШуховаРоссияBelgorod State Technological University named after V.G. ShukhovRussian Federation202512012026226916927Copyright © Новиков А.Н., Кущенко Л.Е., Кущенко С.В., Улинец И.А., 20252025Новиков А.Н., Кущенко Л.Е., Кущенко С.В., Улинец И.А.Novikov A.N., Kushchenko L.E., Kushchenko S.V., Ulinets I.A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.sibadi.org/jour/article/view/2116Введение

Введение. Дорожно-транспортные происшествия (ДТП) – одна из главных причин смертности. В 2024 г. в ЕС погибло 19 940 чел., в РФ – 14 400 чел. Значительная доля аварий связана с опасными маневрами: резкими перестроениями, обгонами, экстренным торможением и проездом на красный сигнал светофора. Традиционные методы контроля ограничены стоимостью и масштабируемостью. Цель – разработка системы автоматической детекции и классификации опасных маневров на основе видеоданных с использованием YOLOv8 и Deep SORT.

Материалы и методы

Материалы и методы. Предложена система из четырёх модулей: модифицированный YOLOv8n (с P2-слоем, LW_C2f, Wise-IoU) для детекции ТС; оптимизированный Deep SORT для трекинга; анализ траекторий с калибровкой камеры; классификация маневров по порогам ускорения (0,35g – смена полосы, 0,30g – торможение), пересечению разметки и состоянию светофора (YOLOv8). Обучено на 45 000 изображений ТС и 20 000 для re-ID.

Результаты

Результаты. Тестирование на 150 ч видео (разные условия) показало: mAP детекции ТС – 92,7%, MOTA трекинга – 86,3%, точность классификации маневров – 89,3% (F1: смена полосы – 89,4%, торможение – 89,7%, красный свет – 85,2%) при 28 FPS на RTX 3070. Задержка – 0,12 с.

Обсуждение и заключение

Обсуждение и заключение. Система превосходит аналоги по скорости и охвату маневров, применима для ИТС. Ограничения – снижение точности в тумане/дожде. Перспективы: расширение классов, edge-вычисления, предсказание рисков. Внедрение снизит аварийность и автоматизирует контроль ПДД.

Introduction

Introduction. Traffic accidents are a leading cause of death. In 2024, 19,940 people were killed in accidents in the EU, while in Russia this number amounts to 14,400 people. A significant proportion of accidents are associated with dangerous maneuvers: abrupt lane changes, overtaking, emergency braking, and running red lights. Traditional monitoring methods are limited by cost and scalability. The goal of this research is to develop a system for automatic detection and classification of dangerous maneuvers based on video data obtained with YOLOv8 and Deep SORT.

Materials and Methods

Materials and Methods. A system consisting of four modules is proposed: a modified YOLOv8n (with a P2 layer, LW_C2f, Wise-IoU) for vehicle detection; an optimized Deep SORT for tracking; trajectory analysis with camera calibration; maneuver classification based on acceleration thresholds (0.35g for lane change, 0.30g for braking), lane marking crossing, and traffic light status (YOLOv8). The system was trained on 45,000 vehicle images and on 20,000 images for re-ID.

Results

Results. Testing of 150 hours of video (various conditions) has shown the following results: mAP vehicle detection – 92.7%, MOTA tracking – 86.3%, maneuver classification accuracy – 89.3% (F1: lane change – 89.4%, braking – 89.7%, red light – 85.2%) at 28 FPS on RTX 3070. Latency – 0.12 s.

Discussion and conclusions. The system under investigation is superior to similar systems in speed and maneuver coverage, and is suitable for ITS applications. Limitations refer to decreased accuracy in foggy or rainy weather. Further research can lead to expanding the class range, edge computing, and risk prediction. The system implementation will reduce accidents and results in automated traffic enforcement.

компьютерное зрениедетекция опасных маневровYOLOv8Deep SORTбезопасность дорожного движения (БДД)видеоаналитиканейронные сетиклассификация нарушений ПДДcomputer visiondetection of dangerous maneuversYOLOv8Deep SORTroad safetyvideo analyticsneural networksclassification of traffic violationsработа выполнена в рамках реализации федеральной программы поддержки университетов «Приоритет-2030» с использованием оборудования на базе Центра высоких технологий БГТУ им. В.Г. Шухова.This research was completed under the Priority 2030 Program at the Belgorod State Technological University named after V.G. Shukhov. The equipment of High Technology Center at BSTU has been used.ReferencesЕремин С.В., Кущенко Л.Е., Кущенко С.В., Новиков А.Н. Повышение безопасности дорожного движения в городских агломерациях: монография. Белгород: БГТУ им. В.Г. Шухова, 2024. 158 с.Eremin S.V., Kushchenko L.E., Kushchenko S.V., Novikov A.N. Improving Road Traffic Safety in Urban Agglomerations: Monograph. Belgorod: Belgorod State Technological University named after V. G. Shukhov, 2024. 158 pp. (In Russ.)Road Safety Statistics for 2024: Progress continues amid persistent challenges // European Commission. 2025. URL: https://transport.ec.europa.eu/news-events/news/road-safety-statistics-2024-progress-continues-amid-persistent-challeng-es-2025-10-17_en (дата обращения: 22.10.2025).Road Safety Statistics for 2024: Progress continues amid persistent challenges. European Commission, 2025. URL: https://transport.ec.europa.eu/news-events/news/road-safety-statistics-2024-progress-continues-amid-persistent-challeng-es-2025-10-17_en (accessed: October 22, 2025).Новиков А.Н., Кущенко Л.Е., Кущенко С.В., Новиков И.А. Анализ существующих методов оценки вероятности возникновения ДТП на участках улично-дорожной сети города // Вестник гражданских инженеров. 2021. № 2 (85). С. 222–231.Novikov A.N., Kushchenko L.E., Kushchenko S.V., Novikov I.A. Analysis of existing methods for assessing the probability of road traffic accidents on sections of the urban street-road network. Bulletin of Civil Engineers. 2021; no. 2 (85): 222–231. (In Russ.)Новиков И.А., Кравченко А.А., Шевцова А.Г., Васильева В.В. Научно-методологический подход к снижению аварийности на дорогах Российской Федерации // Мир транспорта и технологических машин. 2019. № 3 (66). С. 58–64. Https://doi.org/10.33979/2073-7432-2019-66-3-58-64Novikov I.A., Kravchenko A.A., Shevtsova A.G., Vasilieva V.V. Scientific and methodological approach to reducing road accidents in the Russian Federation. World of Transport and Technological Machines. 2019; no. 3 (66): 58–64. (In Russ.) Https://doi.org/10.33979/2073-7432-2019-66-3-58-64Kushchenko L.E., Kushchenko S.V., Kravchenko A.A., Shatova J.S. Improving traffic safety and accident prediction at pedestrian crossings // IOP Conference Series: Materials Science and Engineering. 2020. Vol. 913. 042060. Https://doi.org/10.1088/1757-899X/913/4/042060Kushchenko L.E., Kushchenko S.V., Kravchenko A.A., Shatova J.S. Improving traffic safety and accident prediction at pedestrian crossings. IOP Conference Series: Materials Science and Engineering, 2020. vol. 913:042060. Https://doi.org/10.1088/1757-899X/913/4/042060.Kushchenko L., Kushchenko S., Novikov A., Koroleva L. The statistical assessment of the traffic situation based on sample data of traffic accidents in the urban agglomeration // Journal of Applied Engineering Science. 2023. Vol. 21, No. 4. Https://doi.org/10.5937/jaes0-42852Kushchenko L., Kushchenko S., Novikov A., Koroleva L. The statistical assessment of the traffic situation based on sample data of traffic accidents in the urban agglomeration. Journal of Applied Engineering Science. 2023; vol. 21, no. 4. Https://doi.org/10.5937/jaes0-42852Зырянов В.В., Кочерга В.Г., Поздняков М.Н. Современные подходы к разработке комплексных схем организации дорожного движения // Транспорт Российской Федерации. 2011. № 1. С. 28–33.Zyryanov V.V., Kocherga V.G., Pozdnyakov M.N. Modern approaches to developing comprehensive traffic management schemes. Transport of the Russian Federation. 2011; no. 1: 28–33. (In Russ.)Петров А.И., Евтюков С.А., Колесов В.И. Новые подходы к управлению безопасностью дорожного движения: парадигма организованности процессов обеспечения безопасности дорожного движения // Мир транспорта и технологических машин. 2019. №3 (66) C. 65–74. Https://doi.org/10.33979/2073-7432-2019-66-3-58-64Petrov A.I., Evtyukov S.A., Kolesov V.I. New approaches to road traffic safety management: the paradigm of organized safety assurance processes. World of Transport and Technological Machines. 2019; no. 3 (66): 65–74. (In Russ.) Https://doi.org/10.33979/2073-7432-2019-66-3-58-64Debbarma T., et al. Prediction of Dangerous Driving Behaviour Based on Computer Vision and Machine Learning // Procedia Computer Science. 2024. Vol. 235. P. 783-792. Https://doi.org/10.1016/j.procs.2024.04.178Debbarma T., et al. Prediction of Dangerous Driving Behaviour Based on Computer Vision and Machine Learning. Procedia Computer Science. 2024; vol. 235: 783–792. Https://doi.org/10.1016/j.procs.2024.04.178Zhou T., Zhang X., Chen H. A Dangerous Driving Behavior Detection Method Based on Improved YOLOv8s // Engineering Letters. 2025. Vol. 33, Issue 3. P. 721-731.Zhou T., Zhang X., Chen H. A. Dangerous Driving Behavior Detection Method Based on Improved YOLOv8s. Engineering Letters. 2025; vol. 33(3): 721– 731.Luo Z., Bi Y., Yang X., Li Y., Yu S., Wu M., Ye Q. Enhanced YOLOv5s + DeepSORT method for highway vehicle speed detection and multi-sensor verification // Frontiers in Physics. 2024. Vol. 12. Article 1371320. Https://doi.org/10.3389/fphy.2024.1371320Luo Z., Bi Y., Yang, X., Li Y., Yu S., Wu M., Ye Q. Enhanced YOLOv5s + DeepSORT method for highway vehicle speed detection and multi-sensor verification. Frontiers in Physics. 2024; vol. 12, Article 1371320. Https://doi.org/10.3389/fphy.2024.1371320Ong C.S., et al. Traffic Violation Detection Using Computer Vision Techniques // Journal of Imaging. 2024. Vol. 8, No. 3. P. 1264-1278. Https://doi.org/10.62527/joiv.8.3-2.2941Ong C.S. et al. Traffic Violation Detection Using Computer Vision Techniques. Journal of Imaging. 2024; vol. 8(3): 1264–1278. Https://doi.org/10.62527/joiv.8.3-2.2941Pramanik A., et al. A real-time video surveillance system for traffic pre-events detection // Accident Analysis & Prevention. 2021. Vol. 154. Article 106068. Https://doi.org/10.1016/j.aap.2021.106068Pramanik A. et al. A real-time video surveillance system for traffic pre-events detection. Accident Analysis & Prevention. 2021; vol. 154, Article 106068. Https://doi.org/10.1016/j.aap.2021.106068Han L., et al. Transformer-based modeling of abnormal driving events for freeway crash risk evaluation // Transportation Research Part C: Emerging Technologies. 2024. Vol. 156. Article 104481. Https://doi.org/10.1016/j.trc.2024.104481Han L., et al. Transformer-based modeling of abnormal driving events for freeway crash risk evaluation. Transportation Research Part C: Emerging Technologies. 2024; vol. 156, Article 104481. Https://doi.org/10.1016/j.trc.2024.104481Wei Z., et al. Vision-Based Lane-Changing Behavior Detection Using Deep Learning // IEEE Transactions on Intelligent Vehicles. 2019. Vol. 4, No. 3. P. 457-467. Https://doi.org/10.1109/TIV.2019.2934567Wei Z., et al. Vision-Based Lane-Changing Behavior Detection Using Deep Learning. IEEE Transactions on Intelligent Vehicles. 2019; vol. 4(3): 457– 467. Https://doi.org/10.1109/TIV.2019.2934567Li R., et al. YOLO-SGC: A Dangerous Driving Behavior Detection Method Based on Enhanced YOLOv8 // IEEE Transactions on Intelligent Transportation Systems. 2024. Https://doi.org/10.1109/TITS.2024.3456789Li R. et al. YOLO-SGC: A Dangerous Driving Behavior Detection Method Based on Enhanced YOLOv8. IEEE Transactions on Intelligent Transportation Systems. 2024; Https://doi.org/10.1109/TITS.2024.3456789Гай Л.Е., Шутов А.И., Воля П.А., Кущенко С.В. Заторовые явления. Возможности предупреждения // Вестник БГТУ им. В.Г. Шухова. 2013. № 3. С. 166–169.Gay L.E., Shutov A.I., Volya P.A., Kushchenko S.V. Congestion phenomena: opportunities for prevention. Bulletin of BSTU named after V. G. Shukhov. 2013; no. 3: 166–169. (In Russ.)Wang G., et al. Traffic sign detection method based on improved YOLOv8 // Scientific Reports. 2025. Vol. 15. Article 3792. Https://doi.org/10.1038/s41598-025-03792-0Wang G. et al. Traffic sign detection method based on improved YOLOv8. Scientific Reports. 2025; vol. 15, Article 3792. Https://doi.org/10.1038/s41598-025-03792-0Dou H., Chen S., Xu F., Liu Y., Zhao H. Analysis of vehicle and pedestrian detection effects of improved YOLOv8 model in drone-assisted urban traffic monitoring system // PLOS ONE. 2025. Vol. 20, No. 3. Article e0314817. Https://doi.org/10.1371/journal.pone.0314817Dou H., Chen S., Xu F., Liu Y., Zhao H. Analysis of vehicle and pedestrian detection effects of improved YOLOv8 model in drone-assisted urban traffic monitoring system. PLOS ONE. 2025; vol. 20(3). Article e0314817. Https://doi.org/10.1371/journal.pone.0314817Hassan O.F., et al. Real-time driver drowsiness detection using transformer architecture and transfer learning // Scientific Reports. 2025. Vol. 15. Article 2111. Https://doi.org/10.1038/s41598-025-02111-xHassan O.F. et al. Real-time driver drowsiness detection using transformer architecture and transfer learning. Scientific Reports. 2025; vol. 15, Article 2111. Https://doi.org/10.1038/s41598-025-02111-xЗырянов В.В., Кочерга В.Г., Поздняков М.Н. Современные подходы к разработке комплексных схем организации дорожного движения // Транспорт Российской Федерации. 2011. № 1. С. 28–33.Zyryanov V.V., Kocherga V.G., Pozdnyakov M.N. Modern approaches to developing comprehensive traffic management schemes. Transport of the Russian Federation. 2011; no. 1: 28–33. (In Russ.)Wojke N., Bewley A., Paulus D. Simple online and realtime tracking with a deep association metric // IEEE International Conference on Image Processing (ICIP). 2017. P. 3645-3649. Https://doi.org/10.1109/ICIP.2017.8296962Wojke N., Bewley A., Paulus D. Simple online and realtime tracking with a deep association metric. In: 2017 IEEE International Conference on Image Processing (ICIP). pp. 3645–3649. Https://doi.org/10.1109/ICIP.2017.8296962Печатнова Е.В., Кирюшин И.И., Нагорный Н.Н. Факторы дорожно-транспортной аварийности в пригородной зоне // Вестник СибАДИ. 2024. Т. 21, № 5 (99).Pechatnova E.V., Kiryushin I.I., Nagorny N.N. Factors of road traffic accident rate in the suburban area; Bulletin of the Siberian State Automobile and Highway University (SibADI). 2024; vol. 21, no. 5 (99). (In Russ.)

The authors declare that there are no conflicts of interest present.