تشخیص نوع خودرو به‌منظور کنترل هوشمند عبور و مرور خودروها توسط یادگیری عمیق

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد رشته مهندسی برق، واحد اصفهان (خوراسگان)، دانشگاه آزاد اسلامی، اصفهان، ایران

2 استادیار رشته مهندسی برق، واحد اصفهان (خوراسگان)، دانشگاه آزاد اسلامی، اصفهان، ایران

3 دانشیار رشته مهندسی برق، واحد اصفهان (خوراسگان)، دانشگاه آزاد اسلامی، اصفهان، ایران

10.22034/abmir.2025.22898.1112

چکیده

با افزایش خودروها در سراسر جهان و توسعه فناوری، سیستم‌های حمل‌ونقل هوشمند به‌عنوان یکی از راه‌حل‌های کلیدی برای کنترل ترافیک و افزایش ایمنی راه‌ها مطرح‌شده‌اند. یکی از بخش‌های مهم این سیستم‌ها، تشخیص نوع خودرو است. در این مقاله از ترکیب مدل‌های EfficientNet-B0 و YOLO-V11 جهت تشخیص نوع خودرو استفاده‌شده است. در این مدل، EfficientNet-B0 به‌عنوان ستون فقرات مدل YOLO-V11 به‌کاررفته است. این مدل، ویژگی‌های تصاویر را استخراج کرده و آن‌ها را به مدل YOLO اعمال می‌کند تا مکان و نوع خودرو را به‌طور دقیق تشخیص دهد. برای ارزیابی عملکرد مدل پیشنهادی از مجموعه داده تصویری BVMMR که شامل بیش از 5000 تصویر از انواع خودروهای ایرانی است، استفاده‌شده است. مدل مورداستفاده با زبان برنامه‌نویسی پایتون نوشته‌شده و در محیط کولی (Colab) اجراشده است. نتایج اجرای کدها نشان می‌دهد که مدل پیشنهادی دارای مقدار میانگین دقت در هم‌پوشانی پنجاه‌درصد (mAP50) برابر با 3/99% و میانگین دقت در هم‌پوشانی بیشتر از پنجاه‌درصد (mAP50-95) برابر با 3/98% است. این مدل، ازنظر سرعت پردازش نیز توانسته است با میانگین زمان 2/0 میلی‌ثانیه برای پیش‌پردازش، 8/2 میلی‌ثانیه برای استنتاج و 5/2 میلی‌ثانیه برای پس‌پردازش در هر تصویر، عملکرد مطلوبی را ارائه دهد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Vehicle Models Recognition for Intelligent Control of Vehicle Traffic by Deep Learning

نویسندگان [English]

  • Morteza Ehsandoust 1
  • Atefeh Salimi Shahraki 2
  • Mohammad Rohollah Yazdani 3
  • Mohammad Lali Dastjerdi 1
1 MSc. student Department of Electrical Engineering, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran
2 Assistant Professor Department of Electrical Engineering, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran
3 Associate Professor Department of Electrical Engineering, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran
چکیده [English]

With the increasing number of vehicles worldwide and the advancement of technology, intelligent transportation systems have emerged as a key solution for traffic control and road safety enhancement. One of the crucial components of these systems is vehicle type recognition. In this paper, a combination of EfficientNet-B0 and YOLO-V11 models is used for vehicle type classification. In this model, EfficientNet-B0 serves as the backbone of YOLO-V11, extracting image features and feeding them into the YOLO model to accurately determine the location and type of vehicles. To evaluate the performance of the proposed model, the BVMMR image dataset—containing over 5,000 of various Iranian vehicles—was utilized. The model was implemented using Python and executed in the Colab online environment. The results demonstrate that the proposed model achieves a mean Average Precision at 50% IoU (mAP50) of 99.3% and a mean Average Precision across IoU thresholds from 50% to 95% (mAP50-95) of 98.3%. Additionally, in terms of processing speed, the model delivers an efficient performance with an images average preprocessing time of 0.2 milliseconds, inference time of 2.8 milliseconds, and post-processing time of 2.5 milliseconds per image.

کلیدواژه‌ها [English]

  • Computer Vision
  • Intelligent Transportation System
  • Deep Learning
  • YOLO
  • Efficient Net

مراجع

[1]     M. A. R. Alif, "Yolov11 for vehicle detection: Advancements, performance, and applications in intelligent transportation systems," arXiv preprint arXiv:2410.22898, 2024, doi: 10.48550/arXiv.2410.22898.
[2]     X. Yi, Q. Wang, Q. Liu, Y. Rui, and B. Ran, "Advances in vehicle re-identification techniques: A survey," Neurocomputing, vol. 614, p. 128745, 2025, doi: 10.1016/j.neucom.2024.128745.
[3]     M. Ashkanani, A. AlAjmi, A. Alhayyan, Z. Esmael, M. AlBedaiwi, and M. Nadeem, "A Self-Adaptive Traffic Signal System Integrating Real-Time Vehicle Detection and License Plate Recognition for Enhanced Traffic Management," Inventions, vol. 10, no. 1, p. 14, 2025, doi: 10.3390/inventions10010014.
[4]     J. Zheng and J. Ren, "Multi Self-Supervised Pre-Finetuned Transformer Fusion for Better Vehicle Detection," IEEE Transactions on Automation Science and Engineering, 2024, doi: 10.1109/TASE.2024.3374759.
[5]     J. Karangwa, J. Liu, and Z. Zeng, "Vehicle detection for autonomous driving: A review of algorithms and datasets," IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 11, pp. 11568-11594, 2023, doi: 10.1109/TITS.2023.3292278.
[6]     M. Bakirci, "Enhancing vehicle detection in intelligent transportation systems via autonomous UAV platform and YOLOv8 integration," Applied Soft Computing, vol. 164, p. 112015, 2024, doi: 10.1016/j.asoc.2024.112015.
[7]     M. O. Yusuf et al., "Enhancing vehicle detection and tracking in UAV imagery: a pixel Labeling and particle filter approach," IEEE Access, 2024, doi: 10.1109/ACCESS.2024.3401253.
[8]     "Dataset for car detection on aerial photos applications." https://github.com/jekhor/aerial-cars-dataset (accessed 2018).
[9]     I. Bozcan and E. Kayacan, "Au-air: A multi-modal unmanned aerial vehicle dataset for low altitude traffic surveillance," in 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020: IEEE, pp. 8504-8510, doi: 10.1109/ICRA40945.2020.9196845.
[10] M. Zohaib, M. Asim, and M. ELAffendi, "Enhancing emergency vehicle detection: a deep learning approach with multimodal fusion," Mathematics, vol. 12, no. 10, p. 1514, 2024, doi: 10.3390/math12101514.
[11] Z. Song, Y. Wang, S. Xu, P. Wang, and L. Liu, "Lightweight Vehicle Detection Based on Mamba_ViT," Sensors, vol. 24, no. 22, p. 7138, 2024, doi: 10.3390/s24227138.
[12] Z. Wang and C. Ma, "Weak-mamba-unet: Visual mamba makes cnn and vit work better for scribble-based medical image segmentation," arXiv preprint arXiv:2402.10887, 2024, doi: 10.48550/arXiv.2402.10887.
[13] L. Wen et al., "UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking," Computer Vision and Image Understanding, vol. 193, p. 102907, 2020, doi: 10.1016/j.cviu.2020.102907.
[14] Y. Zhang, W. Wang, M. Ye, J. Yan, and R. Yang, "LGA-YOLO for Vehicle Detection in Remote Sensing Images," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025, doi: 10.1109/JSTARS.2025.3535090.
[15] "data-unicorn-2008." https://github.com/AFRL-RY/data-unicorn-2008 (accessed 2019).
[16] S. Razakarivony and F. Jurie, "Vehicle detection in aerial imagery: A small target detection benchmark," Journal of Visual Communication and Image Representation, vol. 34, pp. 187-203, 2016, doi: 10.1016/j.jvcir.2015.11.002.
[17] G.-S. Xia et al., "DOTA: A large-scale dataset for object detection in aerial images," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 3974-3983, doi: 10.1109/cvpr.2018.00418
[18] H. Park, K. Kim, I. Jeong, J. Jung, and J. Cho, "Special Vehicle Classification Algorithm-Based System for Dedicated Parking Zone Violation Detection in South Korea," IEEE Access, 2025, doi: 10.1109/ACCESS.2025.3526862.
[19] M. Tan and Q. Le, "Efficientnet: Rethinking model scaling for convolutional neural networks," in International conference on machine learning, 2019: PMLR, pp. 6105-6114, doi: 10.48550/arXiv.1905.11946.
[20] R. Khanam and M. Hussain, "Yolov11: An overview of the key architectural enhancements," arXiv preprint arXiv:2410.17725, 2024, doi: 10.48550/arXiv.2410.17725.
[21] "YOLO11_EfficientNet." https://github.com/JYe9/YOLO11_EfficientNet/tree/main (accessed 2025).
[22] N. Jegham, C. Y. Koh, M. Abdelatti, and A. Hendawi, "Evaluating the evolution of yolo (you only look once) models: A comprehensive benchmark study of yolo11 and its predecessors," arXiv preprint arXiv:2411.00201, 2024, doi: 10.48550/arXiv.2411.00201.
[23] J. Huang, K. Wang, Y. Hou, and J. Wang, "LW-YOLO11: A Lightweight Arbitrary-Oriented Ship Detection Method Based on Improved YOLO11," Sensors, vol. 25, no. 1, p. 65, 2024, doi: 10.3390/s25010065.
[24] S. U. Amin, M. S. Abbas, B. Kim, Y. Jung, and S. Seo, "Enhanced anomaly detection in pandemic surveillance videos: An attention approach with EfficientNet-B0 and CBAM integration," IEEE Access, 2024, doi: 10.1109/ACCESS.2024.3488797.
[25] M. Biglari, A. Soleimani, and H. Hassanpour, "Part‐based recognition of vehicle make and model," IET image processing, vol. 11, no. 7, pp. 483-491, 2017, doi: 10.1049/iet-ipr.2016.0969.
[26] M. Y. Shams et al., "Automated On-site Broiler Live Weight Estimation Through YOLO-Based Segmentation," Smart Agricultural Technology, p. 100828, 2025, doi: 10.1016/j.atech.2025.100828.
[27] Y. Gao, Y. Xin, H. Yang, and Y. Wang, "A Lightweight Anti-Unmanned Aerial Vehicle Detection Method Based on Improved YOLOv11," Drones, vol. 9, no. 1, p. 11, 2024, doi: 10.3390/drones9010011.
[28] S. A. Fahim, "Finetuning YOLOv9 for Vehicle Detection: Deep Learning for Intelligent Transportation Systems in Dhaka, Bangladesh," arXiv preprint arXiv:2410.08230, 2024, doi: 10.48550/arXiv.2410.08230.
[29] S. Soudeep, M. Mridha, M. A. Jahin, and N. Dey, "DGNN-YOLO: Dynamic Graph Neural Networks with YOLO11 for Small Object Detection and Tracking in Traffic Surveillance," arXiv preprint arXiv:2411.17251, 2024, doi: 10.48550/arXiv.2411.17251.
[30] E. Arthur, A. Aboah, and Y. Huang, "A Novel FHWA-Compliant Dataset for Granular Vehicle Detection and Classification," IEEE Access, 2024, doi: 10.1109/ACCESS.2024.3486603.
[31] Q.-A. N. Duc et al., "Optimizing Traffic Light Control using YOLOv8 for Real-Time Vehicle Detection and Traffic Density," in 2024 9th International Conference on Integrated Circuits, Design, and Verification (ICDV), 2024: IEEE, pp. 119-124, doi: 10.1109/ICDV61346.2024.10616901.
[32] J. Su, F. Wang, and W. Zhuang, "An Improved YOLOv7 Tiny Algorithm for Vehicle and Pedestrian Detection with Occlusion in Autonomous Driving," Chinese Journal of Electronics, vol. 34, no. 1, pp. 282-294, 2025, doi: 10.23919/cje.2023.00.256.
[33] Y. Zhang, Y. Sun, Z. Wang, and Y. Jiang, "YOLOv7-RAR for urban vehicle detection," Sensors, vol. 23, no. 4, p. 1801, 2023, doi: 10.3390/s23041801.
[34] X. Liu, Y. Wang, D. Yu, and Z. Yuan, "YOLOv8-FDD: A real-time vehicle detection method based on improved YOLOv8," IEEE Access, 2024, doi: 10.1109/ACCESS.2024.3453298
پژوهش های نظری و کاربردی هوش ماشینی
دوره 2، شماره 2
اسفند 1403
صفحه 111-124

فایل ها

هم رسانی

ارجاع به این مقاله

آمار