DEEP LEARNING-BASED VEHICLE BRAND AND MODEL RECOGNITION FOR MARKET ANALYSIS USING YOLOV8 AND YOLOV11 ON REAL-WORLD TRAFFIC DATA

Abstract

The ability to analyze vehicle brand distribution from real-world traffic data has significant implications for market research and trend analysis. This study presents a deep learning-based approach for automated vehicle brand and model recognition using the YOLOv8 and YOLOv11 object detection architectures. The proposed system was trained and evaluated on a dataset of 5,213 labeled vehicle images, collected from actual road traffic footage to ensure real-world applicability. Performance assessments were conducted using mean Average Precision (mAP), precision, recall, and inference speed, demonstrating that YOLOv11 outperforms YOLOv8 in precision and object localization accuracy, achieving a mAP of 88.6%. However, YOLOv8 achieved a higher recall, detecting a broader range of vehicles, albeit with an increased false positive rate. In addition to model performance analysis, this study examines the distribution of different automobile brands in traffic, providing valuable insights for data-driven market analysis. The findings highlight the potential of deep learning-based vehicle detection as a tool for understanding brand presence and consumer trends in the automotive market.

Keywords

• Deep Learning
• Market Analysis
• Object Detection
• Vehicle Brand Recognition
• YOLOv8 Algorithm
• YOLOv11 Algorithm

Ethical Statement

This study is derived from the Master’s Thesis named "Brand Model Detection of Automobiles used on Highways with lmage Processing Techniques and Related commercial Market Research" in the Department of Mechatronics Engineering, Institute of Graduate Education, Isparta University of Applied Sciences.

DERİN ÖĞRENME TABANLI YOLOV8 VE YOLOV11 YAKLAŞIMLARI KULLANILARAK GERÇEK TRAFİK VERİLERİ ÜZERİNDE PİYASA ANALİZİ İÇİN ARAÇ MARKA VE MODEL TANIMA

Abstract

Gerçek dünya trafik verilerinden araç marka dağılımını analiz edebilme yeteneği, pazar araştırması ve eğilim analizi için önemli etkiler taşımaktadır. Bu çalışma, YOLOv8 ve YOLOv11 nesne tespit mimarilerini kullanarak otomatik araç marka ve model tanıma için derin öğrenme tabanlı bir yaklaşım sunmaktadır. Önerilen sistem, gerçek dünya uygulanabilirliğini sağlamak amacıyla gerçek yol trafiği görüntülerinden toplanmış 5.213 etiketli araç görüntüsünden oluşan bir veri kümesi üzerinde eğitilmiş ve değerlendirilmiştir. Performans değerlendirmeleri, Ortalama Doğruluk (mAP), kesinlik, duyarlılık ve çıkarım hızı kullanılarak gerçekleştirilmiş olup, YOLOv11’in kesinlik ve nesne konumlandırma doğruluğunda YOLOv8’i geride bıraktığı ve %88,6 Ortalama Doğruluk (mAP) elde ettiği gösterilmiştir. Ancak YOLOv8, daha geniş bir araç aralığını tespit ederek daha yüksek duyarlılık elde etmiş, bununla birlikte artmış bir yanlış pozitif oranına neden olmuştur. Model performans analizine ek olarak, bu çalışma trafikteki farklı otomobil markalarının dağılımını inceleyerek veri odaklı pazar analizi için değerli içgörüler sağlamaktadır. Bulgular, derin öğrenme tabanlı araç tespitinin otomotiv pazarında marka varlığını ve tüketici eğilimlerini anlamada bir araç olarak potansiyelini vurgulamaktadır.

Keywords

• Derin Öğrenme
• Piyasa Analizi
• Nesne Tespiti
• Araç Marka Tanıma
• YOLOv8 Algoritması
• YOLOv11 Algoritması

References

1. Adu-Gyamfi, Y.O., Asare, S.K., Sharma, A., Titus, T., 2017. Automated vehicle recognition with deep convolutional neural networks. Transportation Research Record, 2645 (1), 113-122.
2. Alamgir, R.M., Shuvro, A.A., Al Mushabbir, M., Raiyan, M.A., Rani, N.J., Rahman, M.M., Kabir, M.H., Ahmed, S., 2022. Performance analysis of YOLO-based architectures for vehicle detection from traffic images in Bangladesh. 25th International Conference on Computer and Information Technology (ICCIT), IEEE, 982-987.
3. Alif, M.A.R., 2024. YOLOv11 for vehicle detection: Advancements, performance, and applications in intelligent transportation systems. arXiv preprint arXiv:2410.22898.
4. Alin, A.Y., Yuana, K.A., 2023. Data augmentation method on drone object detection with YOLOv5 algorithm. Eighth International Conference on Informatics and Computing (ICIC), IEEE, 1-6.
5. Alruwaili, M., Atta, M.N., Siddiqi, M.H., Khan, A., Khan, A., Alhwaiti, Y., Alanazi, S., 2023. Deep learning-based YOLO models for the detection of people with disabilities. IEEE Access, 12, 2543-2566.
6. Atkočiūnas, E., Blake, R., Juozapavičius, A., Kazimianec, M., 2005. Image processing in road traffic analysis. Nonlinear Analysis: Modelling and Control, 10 (4), 315-332.
7. Bitwire, G.A., Han, D.S., 2024. YOLOv11: Revolutionizing object detection with focus on tiny objects in complex settings. Korean Institute of Communication Sciences Fall Conference Proceedings.
8. Chen, Y.-H., Kara, L.B., Cagan, J., 2023. Automating style analysis and visualization with explainable AI-case studies on brand recognition. International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, American Society of Mechanical Engineers, V03AT03A006.

9. Fathy, M., Siyal, M., 1995. Real-time image processing approach to measure traffic queue parameters. IEEE Proceedings-Vision, Image and Signal Processing, 142 (5), 297-303.
10. Gilmore, J.F., Elibiary, K.J., 1993. AI in advanced traffic management systems. Association for the Advancement of Artificial Intelligence (AAAI) Technical Report, WS-93-04.
11. Gulati, R., Srinivasan, R., 2019. Image processing in intelligent traffic management. International Journal of Recent Technology and Engineering, 8 (2S4), 213-218.
12. Hidayatullah, P., Syakrani, N., Sholahuddin, M.R., Gelar, T., Tubagus, R., 2025. YOLOv8 to YOLO11: A comprehensive architecture in-depth comparative review. arXiv preprint arXiv:2501.13400.
13. Hu, C., Bai, X., Qi, L., Wang, X., Xue, G., Mei, L., 2015. Learning discriminative pattern for real-time car brand recognition. IEEE Transactions on Intelligent Transportation Systems, 16 (6), 3170-3181.
14. Hussain, M., 2024. YOLOv1 to v8: Unveiling each variant-a comprehensive review of YOLO. IEEE Access, 12, 42816-42833.
15. Jegham, N., Koh, C.Y., Abdelatti, M., Hendawi, A., 2024. Evaluating the evolution of YOLO (you only look once) models: A comprehensive benchmark study of YOLO11 and its predecessors. arXiv preprint arXiv:2411.00201.
16. Jiang, T., Zhong, Y., 2025. ODVerse33: Is the new YOLO version always better? A multi-domain benchmark from YOLO v5 to v11. arXiv preprint arXiv:2502.14314.
17. Jiang, X., Sun, K., Ma, L., Qu, Z., Ren, C., 2022. Vehicle logo detection method based on improved YOLOv4. Electronics, 11 (20), 3400.
18. Kaur, P., Khehra, B.S., Mavi, E.B.S., 2021. Data augmentation for object detection: A review. IEEE International Midwest Symposium on Circuits and Systems (MWSCAS), IEEE, 537-543.
19. Lee, Y.-H., Kim, H.-J., 2024. Comparative analysis of YOLO series (from V1 to V11) and their application in computer vision. Journal of the Semiconductor & Display Technology, 23 (4), 190-198.
20. Lu, P., Wu, F., Hsiao, S.-W., Tang, J., 2025. A feature curve-based method for balancing brand identity and emotional imagery in automobile frontal form design. Advanced Engineering Informatics, 65.
21. Ma, X., Boukerche, A., 2020. An AI-based visual attention model for vehicle make and model recognition. IEEE Symposium on Computers and Communications (ISCC), IEEE, 1-6.
22. Ma, Y., Chowdhury, M., Sadek, A., Jeihani, M., 2009. Real-time highway traffic condition assessment framework using vehicle-infrastructure integration (VII) with artificial intelligence (AI). IEEE Transactions on Intelligent Transportation Systems, 10 (4), 615-627.
23. Montserrat, D.M., Lin, Q., Allebach, J., Delp, E.J., 2017. Training object detection and recognition CNN models using data augmentation. Electronic Imaging, 29, 27-36.
24. Murendeni, R., Mwanza, A., Obagbuwa, I.C., 2024. Using a YOLO deep learning algorithm to improve the accuracy of 3D object detection by autonomous vehicles. World Electric Vehicle Journal, 16 (1), 9.
25. Naftali, M.G., Sulistyawan, J.S., Julian, K., 2022. Comparison of object detection algorithms for street-level objects. arXiv preprint arXiv:2208.11315.
26. Rahman, R., Bin Azad, Z., Hasan, M.B., 2022. Densely-populated traffic detection using YOLOv5 and non-maximum suppression ensembling. Proceedings of the International Conference on Big Data, IoT, and Machine Learning: BIM 2021, Springer, 567-578.
27. Shandilya, S.K., Srivastav, A., Yemets, K., Datta, A., Nagar, A.K., 2023. YOLO-based segmented dataset for drone vs. bird detection for deep and machine learning algorithms. Data in Brief, 50, 109355.
28. Swathi, Y., Challa, M., 2024. YOLOv8: Advancements and innovations in object detection. International Conference on Smart Computing and Communication, Springer, 1-13.
29. Usama, M., Anwar, H., Anwar, S., 2025. Vehicle and license plate recognition with novel dataset for toll collection. Pattern Analysis and Applications, 28 (2), 57.
30. Varghese, R., Sambath, M., 2024. YOLOv8: A novel object detection algorithm with enhanced performance and robustness. 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS), IEEE, 1-6.
31. Yang, B., 2023. Research on vehicle detection and recognition technology based on artificial intelligence. Microprocessors and Microsystems, 104937.
32. Zhang, Y., Guo, Z., Wu, J., Tian, Y., Tang, H., Guo, X., 2022. Real-time vehicle detection based on improved YOLO v5. Sustainability, 14 (19), 12274.