Raqamli Transformatsiya va Sun’iy Intellekt
REAL VAQTDA AVTOTRANSPORT VOSITALARINI ANIQLASHNING ZAMONAVIY MODELLAR TAHLILI
1 Nukus davlat texnika universiteti
2 Toshkent davlat iqtisodiyot universiteti
Keywords
Abstract
Ushbu tadqiqotda real vaqt rejimi video oqimida avtotransport vositalarini aniqlashga mo‘ljallangan YOLO26n, YOLOv11n va RT-DETR arxitekturalarining qiyosiy hamda eksperimental tahlili taqdim etilgan. Tadqiqot O‘zbekiston Respublikasi sharoitida yo‘l monitoringi vazifalariga nisbatan zamonaviy detektorlarning qiyosiy samaradorligi yetarli darajada o‘rganilmaganligi bilan bog‘liq dolzarb ilmiy bo‘shliqni bartaraf etishga qaratilgan. Eksperimentni o‘tkazish uchun O‘zbekiston yo‘l harakati qoidabuzarliklarini video qayd etish kameralaridan olingan yo‘l sahnalarining 1475 ta annotatsiyalangan tasvirlarini o‘z ichiga olgan original Uzcardet ma’lumotlar to‘plami shakllantirildi. Uchta modelni o‘qitish yagona eksperimental muhitda, birlashtirilgan giperparametrlar asosida, Google Colaboratory platformasida NVIDIA Tesla T4 GPU yordamida amalga oshirildi. Aniqlik ko‘rsatkichlari bo‘yicha RT-DETR modeli eng yaxshi natijalarni ko‘rsatdi (mAP50-95 = 0.634, F1 = 0.719), YOLO26n va YOLOv11n esa nisbatan muvozanatli ko‘rsatkichlarni ta’minladi. CPU qurilmasida (Intel Core i3-1115G4) o‘tkazilgan inference-eksperiment tezlik tavsiflarida prinsipial farq mavjudligini ko‘rsatdi: YOLO26n va YOLOv11n mos ravishda 35.2 va 35.7 FPS ga erishgan bo‘lsa, RT-DETR atigi 2.7 FPS ni ko‘rsatdi, bu esa YOLO modellaridan 13 barobar pastdir. Aniqlik va tezlik mezonlari yig‘indisiga ko‘ra, GPU-tezlatgichsiz yo‘l kuzatuvi uchun Edge-qurilmalarda joriy etish nuqtai nazaridan eng maqbul arxitektura sifatida YOLOv11n modeli e’tirof etildi.
References
- Wang, C.-Y., Liao, H.-Y. M., Wu, Y.-H., Chen, P.-Y., Hsieh, J.-W., and Yeh, I.-H., “CSPNet: A new backbone that can enhance learning capability of CNN”, in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), Seattle, WA, USA, 2020, pp. 390–391, doi: 10.1109/CVPRW50498.2020.00203.
- Wen, L. et al., “UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking”, Comput. Vis. Image Underst., vol. 193, p. 102907, Apr. 2020, doi: 10.1016/j.cviu.2020.102907.
- Tan, M., Pang, R., and Le, Q. V., “EfficientDet: Scalable and efficient object detection” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Seattle, WA, USA, 2020, pp. 10781–10790, arXiv:1911.09070.
- Jocher, G., Chaurasia, A., and Qiu, J., “Ultralytics YOLO”, Version 8.0.0, GitHub, 2023. [Online]. Available: https://github.com/ultralytics/ultralytics.
- Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Dollár, P., “Focal loss for dense object detection”, in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Venice, Italy, 2017, pp. 2980–2988, doi: 10.1109/ICCV.2017.324.
- Redmon, J. and Farhadi, A., “YOLOv3: An incremental improvement”, arXiv:1804.02767, Apr. 2018.
- Janai, J., Güney, F., Behl, A., and Geiger, A., “Computer vision for autonomous vehicles: Problems, datasets and state of the art”, Found. Trends Comput. Graph. Vis., vol. 12, no. 1–3, pp. 1–308, 2020, doi: 10.1561/0600000079.
- He, K., Zhang, X., Ren, S., and Sun, J., “Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification”, in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Santiago, Chile, 2015, pp. 1026–1034, doi: 10.1109/ICCV.2015.123.
- Ren, S., He, K., Girshick, R., and Sun, J., “Faster R-CNN: Towards real-time object detection with region proposal networks”, IEEE Trans. Pattern Anal. Mach. Intell., vol. 39, no. 6, pp. 1137–1149, Jun. 2017, doi: 10.1109/TPAMI.2016.2577031.
- He, K., Gkioxari, G., Dollár, P., and Girshick, R., “Mask R-CNN”, in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), Venice, Italy, 2017, pp. 2961–2969, doi: 10.1109/ICCV.2017.322.
- Wang, A. et al., “YOLOv10: Real-time end-to-end object detection”, in Adv. Neural Inf. Process. Syst. (NeurIPS), 2024, vol. 37, arXiv:2405.14458.
- Lin, T.-Y. et al., “Microsoft COCO: Common objects in context” in Proc. Eur. Conf. Comput. Vis. (ECCV), Zurich, Switzerland, 2014, pp. 740–755, doi: 10.1007/978-3-319-10602-1_48.
- Deli Group Co., Ltd., “Deli ES106 Security Camera User Manual”, 2023. [Online]. Available: https://my.deliworld.com/uploads/file/deli-es106-security-camera-manual.pdf [Accessed: Feb. 11, 2026].
- Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B., and Belongie, S., “Feature pyramid networks for object detection”, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Honolulu, HI, USA, 2017, pp. 2117–2125, doi: 10.1109/CVPR.2017.106.
- Liu, W. et al., “SSD: Single shot multibox detector”, in Proc. Eur. Conf. Comput. Vis. (ECCV), Amsterdam, Netherlands, 2016, pp. 21–37, doi: 10.1007/978-3-319-46448-0_2.
- Redmon, J., Divvala, S., Girshick, R., and Farhadi, A., “You only look once: Unified, real-time object detection”, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Las Vegas, NV, USA, 2016, pp. 779–788, doi: 10.1109/CVPR.2016.91.
- Dalal, N. and Triggs, B., “Histograms of oriented gradients for human detection”, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), San Diego, CA, USA, 2005, pp. 886–893, doi: 10.1109/CVPR.2005.177.
- Zhao, Y. et al., “DETRs beat YOLOs on real-time object detection”, in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Seattle, WA, USA, 2024, pp. 16965–16974, arXiv:2304.08069.
- Kirillov, A. et al., “Segment anything” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), Paris, France, 2023, pp. 4015–4026, arXiv:2304.02643.
- A.К. Makhаmatdinov, “Uzcardet: Road Scene Dataset of Uzbekistan”, Ultralytics Platform, 2024. [Online]. Available: https://platform.ultralytics.com/albatross-penguin/datasets/uzcardet [Accessed: Apr. 01, 2026].
- Khanam, R. and Hussain, M., “YOLOv11: An overview of the key architectural enhancements”, arXiv:2410.17725, Oct. 2024.
- Tricco, A. C. et al., “PRISMA extension for scoping reviews (PRISMA-ScR): Checklist and explanation” Ann. Intern. Med., vol. 169, no. 7, pp. 467–473, Oct. 2018, doi: 10.7326/M18-0850.
- Ultralytics, “YOLO26 Model Documentation”, 2025. [Online]. Available: https://docs.ultralytics.com/ru/models/yolo26/ [Accessed: Feb. 06, 2026].
- Zheng, Z. et al., “Distance-IoU loss: Faster and better learning for bounding box regression”, in Proc. AAAI Conf. Artif. Intell., New York, NY, USA, 2020, vol. 34, no. 7, pp. 12993–13000, arXiv:1911.08287.
- Girshick, R., Donahue, J., Darrell, T., and Malik, J., “Rich feature hierarchies for accurate object detection and semantic segmentation”, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Columbus, OH, USA, 2014, pp. 580–587, doi: 10.1109/CVPR.2014.81.
- Peters, M. D. J. et al., “Chapter 11: Scoping reviews”, in JBI Manual for Evidence Synthesis, JBI, Adelaide, Australia, 2020, doi: 10.46658/JBIMES-20-12.
- Liu, S., Qi, L., Qin, H., Shi, J., and Jia, J., “Path aggregation network for instance segmentation”, in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Salt Lake City, UT, USA, 2018, pp. 8759–8768, doi: 10.1109/CVPR.2018.00913.
- Vaswani, A. et al., “Attention is all you need”, in Adv. Neural Inf. Process. Syst. (NeurIPS), Long Beach, CA, USA, 2017, vol. 30, arXiv:1706.03762.
- Ioffe, S. and Szegedy, C., “Batch normalization: Accelerating deep network training by reducing internal covariate shift”, in Proc. Int. Conf. Mach. Learn. (ICML), Lille, France, 2015, pp. 448–456, arXiv:1502.03167.
- Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S., “End-to-end object detection with transformers”, in Proc. Eur. Conf. Comput. Vis. (ECCV), Glasgow, UK, 2020, pp. 213–229, doi: 10.1007/978-3-030-58452-8_13.