سیاست گذاری پیشرفت شهری

سیاست گذاری پیشرفت شهری

بررسی عملکرد مدل YOLOv8 در تشخیص علائم ترافیکی برای سامانه‌های حمل‌ونقل هوشمند

نوع مقاله : مقاله پژوهشی

نویسندگان
ثنا نظری‌نژاد 1
الهام فراهانی 2
1 کارشناسی ارشد مهندسی فناوری اطلاعات، گروه فناوری اطلاعات، دانشکدۀ مهندسی صنایع، دانشگاه صنعتی خواجه نصیرالدین طوسی، تهران، ایران
2 استادیار، دانشکدۀ مهندسی کامپیوتر، مؤسسۀ آموزش عالی الکترونیکی ایرانیان، تهران، ایران
10.22034/judpm.2025.514770.1029
چکیده
با توجه به رشد روزافزون شهرنشینی و افزایش تعداد وسایل نقلیه، سیستم‌های حمل‌ونقل سنتی دیگر پاسخ‌گوی نیازهای جمعیتی نیستند و استفاده از راهکارهای هوشمند مبتنی بر داده، ضروری به نظر می‌رسد. در این راستا، مقالۀ حاضر به بررسی چگونگی بهره‌گیری از هوش مصنوعی، به‌ویژه بینایی کامپیوتری، در مدیریت ترافیک شهری می‌پردازد. در این پژوهش، از مدل YOLOv8، جدیدترین نسخه از مدل‌های YOLO، برای تشخیص علائم راهنمایی و رانندگی استفاده شده است. این مدل با استفاده از معماری بهبود می‌یابد، سرعت و دقت بیشتری نسبت به نسخه‌های قبلی ارائه می‌دهد و امکان تشخیص اشیا در زمان واقعی را فراهم می‌کند. برای آموزش و ارزیابی مدل، از دیتاست Self-Driving Cars استفاده شده است که شامل تصاویر علائم ترافیکی مختلف است. نتایج ارزیابی مدل نشان می‌دهد YOLOv8 عملکرد قابل قبولی در تشخیص علائم ترافیکی دارد. این مدل می‌تواند به عنوان یک راهکار مؤثر برای نظارت هوشمند بر ترافیک شهری و بهبود ایمنی جاده‌ها مورد استفاده قرار گیرد. با این‌حال، مقاله به چالش‌های موجود در تشخیص برخی از کلاس‌های علائم ترافیکی نیز اشاره دارد و پیشنهادهایی برای بهبود بیشتر مدل و توسعۀ روش‌های مؤثرتر در مدیریت هوشمند ترافیک ارائه می‌دهد. این پیشنهادها شامل استفاده از مدل‌های چندوجهی، افزایش تنوع داده‌های آموزشی و پیاده‌سازی مدل روی سخت‌افزارهای سبک است.
کلیدواژه‌ها
بینایی کامپیوتر
شهرهای هوشمند
مدیریت ترافیک
هوش مصنوعی
یادگیری عمیق
موضوعات

عنوان مقاله English

Performance Evaluation of the YOLOv8 Model in Traffic Sign Detection for Intelligent Transportation System

نویسندگان English

Sana Nazarinezhad 1
Elham Farahani 2
1 M.Sc. in Information Technology Engineering, Department of Information Technology, Faculty of Industrial Engineering, K.N.Toosi University of Technology, Tehran, Iran
2 Assistant Professor, Faculty of Computer Engineering, Iranian eUniversity, Tehran, Iran
چکیده English

The increasing urbanization and vehicle growth strain traditional transportation systems, necessitating data-driven intelligent solutions. This article explores the application of artificial intelligence, specifically computer vision, in urban traffic management. We employed YOLOv8, the latest YOLO model, for traffic sign detection. Its improved architecture offers enhanced speed and accuracy for real-time object detection. Trained and evaluated on the Self-Driving Cars dataset, YOLOv8 demonstrated acceptable performance in traffic sign detection, suggesting its potential for intelligent urban traffic monitoring and improved road safety. However, the study identifies challenges in detecting certain traffic sign classes and proposes future directions, including multimodal models, increased training data diversity, and lightweight hardware implementation.

کلیدواژه‌ها English

Artificial Intelligence
Computer Vision
Deep Learning
Smart Cities
Traffic Management
  1. Thapliyal N, Aeri M, Namdev D, Kukreja V, Sharma R. YOLOv8 Enhanced: Pioneering Accuracy in Traffic Sign Detection and Classification. In: 2024 IEEE 9th International Conference for Convergence in Technology (I2CT). IEEE; 2024. p. 1–4. Available from: https://doi.org/10.1109/i2ct61223.2024.10543354
  2. Belli L, Cilfone A, Davoli L, Ferrari G, Adorni P, Di Nocera F, et al. IoT-enabled smart sustainable cities: Challenges and approaches. Smart Cities. 2020;3(3):1039-71.
  3. Scuotto V, Ferraris A, Bresciani S. Internet of Things: Applications and challenges in smart cities: a case study of IBM smart city projects. Bus Process Manag J. 2016;22(2):357-67.
  4. Arasteh H, Hosseinnezhad V, Loia V, Tommasetti A, Troisi O, Shafie-Khah M, et al. IoT-based smart cities: A survey. In: 2016 IEEE 16th International Conference on Environment and Electrical Engineering (EEEIC). IEEE; 2016. p. 1-6.
  5. Tukker A. Product services for a resource-efficient and circular economy–a review. J Clean Prod. 2015;97:76-91.
  6. Gärling T, Schuitema G. Travel demand management targeting reduced private car use: effectiveness, public acceptability and political feasibility. J Soc Issues. 2007;63(1):139-53.
  7. Byttner S, Rögnvaldsson T, Svensson M. Consensus self-organized models for fault detection (COSMO). Eng Appl Artif Intell. 2011;24(5):833-9.
  8. Pillai AS. Traffic management: Implementing AI to optimize traffic flow and reduce congestion. J Emerg Technol Innov Res. 2024;11(7).
  9. Ban X, Wang H, Chen T, Wang Y, Xiao Y. Monocular visual odometry based on depth and optical flow using deep learning. IEEE Trans Instrum Meas. 2020;70:1-19.
  10. Wei L, Guo D, Chen Z, Yang J, Feng T. Forecasting short-term passenger flow of subway stations based on the temporal pattern attention mechanism and the long short-term memory network. ISPRS Int J Geo-Inf. 2023;12(1):25.
  11. Shedding Light on Energy in the EU-A Guided Tour of Energy Statistics; Technical Report; Eurostat: Luxembourg, 2020.
  12. Rahman R, Bin Azad Z, Bakhtiar Hasan M. Densely-populated traffic detection using YOLOv5 and non-maximum suppression ensembling. In: Proceedings of the International Conference on Big Data, IoT, and Machine Learning: BIM 2021. Singapore: Springer Singapore; 2021. p. 567-78.
  13. Chen L, Englund C. Cooperative intersection management: A survey. IEEE Trans Intell Transp Syst. 2015;17(2):570-86.
  14. Englund C, Chen L, Voronov A. Cooperative speed harmonization for efficient road utilization. In: 2014 7th International Workshop on Communication Technologies for Vehicles (Nets4Cars-Fall). IEEE; 2014. p. 19-23.
  15. European Environment Agency. Final Energy Consumption in Europe by Mode of Transport; Technical Report; Copenhagen, Denmark, 2019.
  16. Arora A, Jain A, Yadav D, Hassija V, Chamola V, Sikdar B. Next generation of multi-agent driven smart city applications and research paradigms. IEEE Open J Commun Soc. 2023;4:2104-21.
  17. Badidi E, Moumane K, El Ghazi F. Opportunities, applications, and challenges of edge-AI enabled video analytics in smart cities: a systematic review. IEEE Access. 2023;11:80543-72.
  18. Rizwan P, Suresh K, Babu MR. Real-time smart traffic management system for smart cities by using Internet of Things and big data. In: 2016 International Conference on Emerging Technological Trends (ICETT). IEEE; 2016. p. 1-7.
  19. Adewopo V, Elsayed N, ElSayed Z, Ozer M, Wangia-Anderson V, Abdelgawad A. AI on the Road: A Comprehensive Analysis of Traffic Accidents and Autonomous Accident Detection System in Smart Cities. In: 2023 IEEE 35th International Conference on Tools with Artificial Intelligence (ICTAI). IEEE; 2023. p. 501-6.
  20. Apolo-Apolo OE, Martínez-Guanter J, Egea G, Raja P, Pérez-Ruiz M. Deep learning techniques for estimation of the yield and size of citrus fruits using a UAV. Eur J Agron. 2020;115:126030.
  21. World Health Organization. Global status report on road safety 2018. World Health Organization; 2019.
  22. European Commission. State of the Union: Commission raises climate ambition; 2020.
  23. Zhao C, Wang X, Lv Y, Tian Y, Lin Y, Wang FY. Parallel transportation in TransVerse: From foundation models to DeCAST. IEEE Trans Intell Transp Syst. 2023;24(12):15310-27.
  24. Barrachina J, Garrido P, Fogue M, Martinez FJ, Cano JC, Calafate CT, et al. Reducing emergency services arrival time by using vehicular communications and Evolution Strategies. Expert Syst Appl. 2014;41(4):1206-17.
  25. Englund C, Chen L, Ploeg J, Semsar-Kazerooni E, Voronov A, Bengtsson HH, et al. The grand cooperative driving challenge 2016: boosting the introduction of cooperative automated vehicles. IEEE Wirel Commun. 2016;23(4):146-52.
  26. European Commission. EU Road Safety Policy Framework 2021–2030—Next Steps towards “Vision Zero”. 2019.
  27. Manika S. Mechanisms for Innovative-Driven Solutions in European Smart Cities. Smart cities. 2020, 3, 527–540
  28. Bešinović N, De Donato L, Flammini F, Goverde RM, Lin Z, Liu R, et al. Artificial intelligence in railway transport: Taxonomy, regulations, and applications. IEEE Trans Intell Transp Syst. 2021;23(9):14011-24.
  29. Cui Q, Wang Y, Chen KC, Ni W, Lin IC, Tao X, et al. Big data analytics and network calculus enabling intelligent management of autonomous vehicles in a smart city. IEEE Internet Things J. 2018;6(2):2021-34.
  30. Koshnicharova D, Mihovska A, Koleva P, Poulkov V. Data-driven interactive crowd management systems for Metaverse scenarios. In: 2022 25th International Symposium on Wireless Personal Multimedia Communications (WPMC). IEEE; 2022. p. 549-54.
  31. Englund C, Aksoy EE, Alonso-Fernandez F, Cooney MD, Pashami S, Åstrand B. AI perspectives in Smart Cities and Communities to enable road vehicle automation and smart traffic control. Smart Cities. 2021;4(2):783-802.
  32. Humayun M, Afsar S, Almufareh MF, Jhanjhi NZ, AlSuwailem M. Smart traffic management system for metropolitan cities of kingdom using cutting edge technologies. J Adv Transp. 2022;2022(1):4687319.
  33. Gharrawi HA, Yaghoub MB. Traffic Management in Smart Cities Using the Weighted Least Squares Method. arXiv preprint. 2022. Available from: https://arxiv.org/abs/2205.00346
  34. van der Meulen J, Mukhtar-Landgren D, Koglin T. Modernity, mobility, and acceleration: cycling as the blind spot in Swedish transport innovation. Urban, Planning and Transport Research. 2023;11(1):2261534.
  35. Singh S, Singh J, Goyal SB, Sehra SS, Ali F, Alkhafaji MA, et al. A novel framework to avoid traffic congestion and air pollution for sustainable development of smart cities. Sustainable Energy Technologies and Assessments. 2023;56:103125.
  36. Aramrattana M, Larsson T, Jansson J, Englund C. Dimensions of cooperative driving, ITS and automation. In: 2015 IEEE Intelligent Vehicles Symposium (IV). IEEE; 2015. p. 144-9.
  37. Gupta R, Verma A, Kukreja V, Sharma R. Enhancing Road Safety and ITS Efficiency: A Comprehensive Evaluation of Traffic Sign Detection using YOLOv8. In: 2024 International Conference on Emerging Technologies in Computer Science for Interdisciplinary Applications (ICETCS). IEEE; 2024. Available from: https://doi.org/10.1109/icetcs61022.2024.10543721
  38. Kaur A, Kukreja V, Thapliyal N, Aeri M, Sharma R, Hariharan S. An Improved YOLOv8 Model for Traffic Sign Detection and Classification. In: 2024 3rd International Conference for Innovation in Technology (INOCON). IEEE; 2024. Available from: https://doi.org/10.1109/inocon60754.2024.10511576
  39. Zhang Y, Liu H, Dong D, Duan X, Lin F, Liu Z. DPF-YOLOv8: Dual Path Feature Fusion Network for Traffic Sign Detection in Hazy Weather. Electronics. 2024;13:4016. Available from: https://doi.org/10.3390/electronics13204016
  40. Choudhary N, Sharma R, Upadhyay D, Verma A, Jain V. Enhanced Traffic Sign Recognition Using Advanced YOLOv8 Model. In: 2023 4th International Conference on Intelligent Technologies (CONIT). IEEE; 2024. Available from: https://doi.org/10.1109/conit61985.2024.10626450
  41. Sohan M, Sai Ram T, Rami Reddy CV. A review on YOLOv8 and its advancements. In: International Conference on Data Intelligence and Cognitive Informatics. Singapore: Springer Singapore; 2024. p. 529-45.
  42. Yang G, Wang J, Nie Z, Yang H, Yu S. A lightweight YOLOv8 tomato detection algorithm combining feature enhancement and attention. Agronomy. 2023;13(7):1824.
سیاست گذاری پیشرفت شهری
دوره 2، شماره 3
پاییز 1404
صفحه 277-296

  • تاریخ دریافت 28 اسفند 1403
  • تاریخ بازنگری 29 فروردین 1404
  • تاریخ پذیرش 25 اردیبهشت 1404
  • تاریخ انتشار 11 خرداد 1404