YO‘L BELGILARINI GRAFIK PROTSESSORLAR YORDAMIDA DINAMIK TASVIRLARDAN TANIB OLISH ALGORITMI

Ushbu maqolada zamonaviy sun’iy intellekt texnologiyalaridan foydalangan holda, "You Only Look Once" algoritmi asosida yo‘l belgilarini aniqlash va tasniflash masalasi o‘rganilgan. Dasturiy majmua O‘zbekiston hududida ko‘p qatnovli avtomobil yo‘llaridagi yo‘l harakati hodisalarini kamaytirish, haydovchilarga yo‘l infratuzilmasi haqida ma’lumotlarni vizual yetkazishga ko‘maklashish va yo‘l belgilari ma’lumotlar bazasini yaratish uchun xizmat qiladi. Mazkur dasturiy majmua videokuzatuv kamerasidan olingan tasvirlar orqali Nvidia Jetson Nano grafik protsessorlari va mobil qurilmalarida real vaqt rejimida amalga oshirildi. Sunʼiy intellekt texnologiyalaridan foydalangan holda, tasvirlardagi yo‘l belgilarini aniqlash, ajratish va tanib olish usullari, algoritmlari va dasturiy majmuasi ishlab chiqildi. Ushbu dasturiy majmua avtomobilga o‘rnatilgan kuzatuv kameralari yordamida real vaqt rejimida yo‘l belgilarini tanish orqali haydovchilarni ogohlantirish va yo‘l transport hodisalarining oldini olishda yuqori samaradorlik ko‘rsatadi. Dunyodagi turli davlatlarda yo‘l transport hodisalarining oldini olish bo‘yicha maʼlum texnologi-yalar va dasturiy vositalar ishlab chiqilgan, ammo bu tizimlar tegishli davlatning yo‘l harakati qoidalariga ixtisoslashgan. Shuningdek, O‘zbekiston Respublikasi hududidagi yo‘l transport hodisalarining oldini olish va ogohlantirish bo‘yicha texnologiyalar ishlab chiqil-magan.

Jurnal nomiИЛМ-ФАН ВА ИННОВАЦИОН РИВОЖЛАНИШ
Nashr soniИлм-фан ва инновацион ривожланиш илмий журнали 2022 йил 3-сон
Ko'rishlar soni37

Internet havola https://ilm.mininnovation.uz/index.php/journal/article/view/296

DOIhttps://dx.doi.org/10.36522/2181-9637-2022-3-8

UzSCI tizimida yaratilgan sana10-02-2023

O'qishlar soni11

Nashr sanasi24-06-2022

Asosiy tilO'zbek

Sahifalar71-80

Kalit so'z

model

klassifikatsiya

ma’lumotlar bazasi

dinamik tasvir

YOLO

sunʼiy intellekt

yo‘l belgilari

grafik protsessor

Ўзбек

Ushbu maqolada zamonaviy sun’iy intellekt texnologiyalaridan foydalangan holda, "You Only Look Once" algoritmi asosida yo‘l belgilarini aniqlash va tasniflash masalasi o‘rganilgan. Dasturiy majmua O‘zbekiston hududida ko‘p qatnovli avtomobil yo‘llaridagi yo‘l harakati hodisalarini kamaytirish, haydovchilarga yo‘l infratuzilmasi haqida ma’lumotlarni vizual yetkazishga ko‘maklashish va yo‘l belgilari ma’lumotlar bazasini yaratish uchun xizmat qiladi. Mazkur dasturiy majmua videokuzatuv kamerasidan olingan tasvirlar orqali Nvidia Jetson Nano grafik protsessorlari va mobil qurilmalarida real vaqt rejimida amalga oshirildi. Sunʼiy intellekt texnologiyalaridan foydalangan holda, tasvirlardagi yo‘l belgilarini aniqlash, ajratish va tanib olish usullari, algoritmlari va dasturiy majmuasi ishlab chiqildi. Ushbu dasturiy majmua avtomobilga o‘rnatilgan kuzatuv kameralari yordamida real vaqt rejimida yo‘l belgilarini tanish orqali haydovchilarni ogohlantirish va yo‘l transport hodisalarining oldini olishda yuqori samaradorlik ko‘rsatadi. Dunyodagi turli davlatlarda yo‘l transport hodisalarining oldini olish bo‘yicha maʼlum texnologi-yalar va dasturiy vositalar ishlab chiqilgan, ammo bu tizimlar tegishli davlatning yo‘l harakati qoidalariga ixtisoslashgan. Shuningdek, O‘zbekiston Respublikasi hududidagi yo‘l transport hodisalarining oldini olish va ogohlantirish bo‘yicha texnologiyalar ishlab chiqil-magan.

Kalit so'z

model

klassifikatsiya

ma’lumotlar bazasi

dinamik tasvir

YOLO

sunʼiy intellekt

yo‘l belgilari

grafik protsessor

Русский

В данной статье рассматривается проблема идентификации и классификации дорожных знаков на основе алгоритма You Only Look Once с использованием современных технологий искусственного интеллекта. Программный комплекс поможет снизить количество аварий на автомобильных дорогах Узбекистана, предоставить водителям наглядную информацию о дорожной инфраструктуре, создать базу данных дорожных знаков. Этот программный комплекс был реализован в режиме реального времени на графических процессорах Nvidia Jetson Nano и мобильных устройствах посредством изображений, снятых с камеры видеонаблюдения. Разработан комплекс методов, алгоритмов и программного обеспечения для обнаружения, выделения и распознавания дорожных знаков на изображениях с использованием технологий искусственного интеллекта. Этот программный комплекс очень эффективен для предупреждения водителей и предотвращения дорожно-транспортных происшествий путем распознавания дорожных знаков в режиме реального времени с помощью камер наблюдения, установленных в автомобиле. В разных странах мира разработаны определенные технологии и программное обеспечение для предотвращения дорожно-транспортных происшествий, но эти системы специализируются на правилах дорожного движения. Однако в Республике Узбекистан не разработаны технологии предупреждения и предотвращения дорожно-транспортных происшествий.

Kalit so'z

модель

классификация

база данных

дорожные знаки

искусственный интеллект

YOLO

динамическое изображение

графический процессор

English

This article discusses the problem of identifying and classifying road signs based on the You Only Look Once algorithm using modern artificial intelligence technologies. The software package will help to reduce traffic accidents on the territory of Uzbekistan, to provide drivers with visual information about the road infrastructure, to create a database of road signs. This software package was implemented in real time on Nvidia Jetson Nano graphics processors and mobile devices through images taken from a video surveillance camera. A set of methods, algorithms and software for the detection, separation and recognition of road signs in images using artificial intelligence technology has been developed. This software package is highly effective in warning drivers and preventing traffic accidents by real-time recognition of road signs with the help of surveillance cameras installed in the car. Certain technologies and software have been developed in various countries around the world to prevent traffic accidents, but these systems specialize in the rules of the road. Also, technologies for the prevention and prevention of road accidents in the territory of the Republic of Uzbekistan have not been developed.

Kalit so'z

classification

model

database

road signs

YOLO

dynamic image

artificial intelligence

graphics processor

№ Muallifning F.I.Sh. Lavozimi Tashkilot nomi

1 Umarov M.A. “Dasturiy injiniring” kafedrasi assistenti Muhammad al-Xorazmiy nomidagi Toshkent axborot texnologiyalari universiteti Samarqand filiali

№ Havola nomi

1 Zeng Y., Xu X., Fang Y., Zhao K. Traffic sign recognition using extreme learning classifier with deep convolutional features. Proceedings of the 2015 international conference on intelligence science and big data engineering (IScIDE 2015), Suzhou, China, 2015, June, vol. 9242, pp. 272-280.

2 Khamdamov U., Zaynidinov H. Parallel Algorithms for Bitmap Image Proceedings of 2018 10th International Conference on Communication Software and Networks (ICCSN), 2018, pp. 537-541. DOI: 10.1109/ICCSN.2018.8488270/.

3 Goodfellow I.J., Warde-Farley D., Mirza M., Courville A., Bengio Y. Maxout networks, in ICML’13, ed. S. Dasgupta, D. McAllester. 2013, pp. 1319-1327.

4 Lin G., Shen W. Research on convolutional neural network based on improved Relu piecewise activation function. Procedia Computer Science, 2018, vol. 131, pp. 977–984. DOI: 10.1016/j. procs.2018.04.239/.

5 Krizhevsky I. Sutskever G.E. Hinton, ImageNet classification with deep convolutional neural networks. NIPS’, 2012.

6 Calin O. Deep Learning Architectures. Springer Series in the Data Sciences 2020. ISBN 978-3-030-36720-6, ISBN 978-3-030-36721-3 (eBook). DOI: 10.1007/978-3-030-36721-3/.

7 Eckle K., Schmidt-Hieber J. A comparison of deep networks with ReLU activation function and linear spline-type methods. Neural Networks, 2019, vol. 110, pp. 232-242. DOI: 10.1016/j. neunet.2018.11.005/.

8 Khamdamov R., Rakhmanov K., Saliev E., Karshiyev Z. Advantages using of the contour analysis method for detecting fire from video images. Proceedings of the 2021 International Conference on Information Science and Communications Technologies (ICISCT), 2021, pp. 1-4.

9 Chen Y., Zheng B., Zhang Z., Wang Q., Shen C., Zhang Q. Deep learning on mobile and embedded devices: State-of-the-art, challenges, and future directions. ACM Comput. Surveys, 2020, September, vol. 53, no. 4, pp. 1-37. DOI: 10.1145/3398209/.

10 Redmon J., Divvala S., Girshick R., Farhadi A. 2015 You Only Look Once: Unified, Real-Time Object Detection You Look Only Once, p. 10.

11 Umarov M., Muradov F., Azamov T. Traffic Sign Recognition Method Based on Simplified Gabor Wavelets and CNNs. Proceedings of the 2021 International Conference on Information Science and Communications Technologies (ICISCT), 2021, pp. 1-5. DOI: 10.1109/ICISCT52966.2021.9670118/.

12 Ren S., He K., Girshick R., Sun J. 2016 Faster R-CNN. Towards Real-Time Object Detection with Region Proposal Networks, p. 14.

13 Liu C., Li S., Chang F., Wang Y. Machine vision based traffic sign detection methods: Review, analyses and perspectives. IEEE Access, 2019, vol. 7, pp. 865-879.

14 Redmon J., Divvala S., Girshick R., Farhadi A. You only look once: Unified, real-time object detection. Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779-788.

15 Stallkamp J., Schlipsing M., Salmen J., Igel C. Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition. Neural Networks, no. 10.

16 Shao F.M., Wang X.Q., Meng F.J., Rui T., Wang D., Tang J. Real-Time Traffic Sign Detection and Recognition Method Based on Simplified Gabor Wavelets and CNNs. Sensors-Basel, 2018, no. 18 (10).

17 Zhang J., Huang M., Jin X., Li X. A Real-Time Chinese Traffic Sign Detection Algorithm Based on Modified YOLOv2. Algorithms. 2017, no. 10 (4).

18 Li J.A., Liang X.D., Wei Y., Xu T.F., Feng J.S., Yan S.C. Perceptual Generative Adversarial Networks for Small Object Detection. Proceedings of the Cvpr Ieee. 2017, pp. 1951-9.

19 Yang Y., Luo H., Xu H., Wu F. Towards real-time traffic sign detection and classification. IEEE Transactions on Intelligent Transportation Systems, 2015, no. 17 (7), pp. 2022-2031.

20 Sutskever I., Hinton G.E., Krizhevsky A. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 2012, pp. 1097-1105.

21 Liu Z.W, Shen C., Qi M.Y., Fan X. SADANet: Integrating Scale-Aware and Domain Adaptive for Traffic Sign Detection. Ieee Access, 2020, no. 8, p. 77920.

22 Chen Y.Y.L., Kong T., Qi L., Chu R,. Li L., Jia J. Scale-aware Automatic Augmentation for Object Detection. arXiv, 2021, p. 210317220.

23 Tan M.R.P., Le Q.V. EfficientDet: Scalable and Efficient Object Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 10781-90.

24 Qi W.T., Qi Y., Liu J. YOLO5Face: Why Reinventing a Face Detector. 2021.

25 Zhang Q.T.S., Wang Y., Tang Z., Chen Y., Cai L., Ling H. M2Det A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, no. 33, pp. 9259-66.

Kutilmoqda

№	Havola nomi
1	Zeng Y., Xu X., Fang Y., Zhao K. Traffic sign recognition using extreme learning classifier with deep convolutional features. Proceedings of the 2015 international conference on intelligence science and big data engineering (IScIDE 2015), Suzhou, China, 2015, June, vol. 9242, pp. 272-280.
2	Khamdamov U., Zaynidinov H. Parallel Algorithms for Bitmap Image Proceedings of 2018 10th International Conference on Communication Software and Networks (ICCSN), 2018, pp. 537-541. DOI: 10.1109/ICCSN.2018.8488270/.
3	Goodfellow I.J., Warde-Farley D., Mirza M., Courville A., Bengio Y. Maxout networks, in ICML’13, ed. S. Dasgupta, D. McAllester. 2013, pp. 1319-1327.
4	Lin G., Shen W. Research on convolutional neural network based on improved Relu piecewise activation function. Procedia Computer Science, 2018, vol. 131, pp. 977–984. DOI: 10.1016/j. procs.2018.04.239/.
5	Krizhevsky I. Sutskever G.E. Hinton, ImageNet classification with deep convolutional neural networks. NIPS’, 2012.
6	Calin O. Deep Learning Architectures. Springer Series in the Data Sciences 2020. ISBN 978-3-030-36720-6, ISBN 978-3-030-36721-3 (eBook). DOI: 10.1007/978-3-030-36721-3/.
7	Eckle K., Schmidt-Hieber J. A comparison of deep networks with ReLU activation function and linear spline-type methods. Neural Networks, 2019, vol. 110, pp. 232-242. DOI: 10.1016/j. neunet.2018.11.005/.
8	Khamdamov R., Rakhmanov K., Saliev E., Karshiyev Z. Advantages using of the contour analysis method for detecting fire from video images. Proceedings of the 2021 International Conference on Information Science and Communications Technologies (ICISCT), 2021, pp. 1-4.
9	Chen Y., Zheng B., Zhang Z., Wang Q., Shen C., Zhang Q. Deep learning on mobile and embedded devices: State-of-the-art, challenges, and future directions. ACM Comput. Surveys, 2020, September, vol. 53, no. 4, pp. 1-37. DOI: 10.1145/3398209/.
10	Redmon J., Divvala S., Girshick R., Farhadi A. 2015 You Only Look Once: Unified, Real-Time Object Detection You Look Only Once, p. 10.
11	Umarov M., Muradov F., Azamov T. Traffic Sign Recognition Method Based on Simplified Gabor Wavelets and CNNs. Proceedings of the 2021 International Conference on Information Science and Communications Technologies (ICISCT), 2021, pp. 1-5. DOI: 10.1109/ICISCT52966.2021.9670118/.
12	Ren S., He K., Girshick R., Sun J. 2016 Faster R-CNN. Towards Real-Time Object Detection with Region Proposal Networks, p. 14.
13	Liu C., Li S., Chang F., Wang Y. Machine vision based traffic sign detection methods: Review, analyses and perspectives. IEEE Access, 2019, vol. 7, pp. 865-879.
14	Redmon J., Divvala S., Girshick R., Farhadi A. You only look once: Unified, real-time object detection. Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779-788.
15	Stallkamp J., Schlipsing M., Salmen J., Igel C. Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition. Neural Networks, no. 10.
16	Shao F.M., Wang X.Q., Meng F.J., Rui T., Wang D., Tang J. Real-Time Traffic Sign Detection and Recognition Method Based on Simplified Gabor Wavelets and CNNs. Sensors-Basel, 2018, no. 18 (10).
17	Zhang J., Huang M., Jin X., Li X. A Real-Time Chinese Traffic Sign Detection Algorithm Based on Modified YOLOv2. Algorithms. 2017, no. 10 (4).
18	Li J.A., Liang X.D., Wei Y., Xu T.F., Feng J.S., Yan S.C. Perceptual Generative Adversarial Networks for Small Object Detection. Proceedings of the Cvpr Ieee. 2017, pp. 1951-9.
19	Yang Y., Luo H., Xu H., Wu F. Towards real-time traffic sign detection and classification. IEEE Transactions on Intelligent Transportation Systems, 2015, no. 17 (7), pp. 2022-2031.
20	Sutskever I., Hinton G.E., Krizhevsky A. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 2012, pp. 1097-1105.
21	Liu Z.W, Shen C., Qi M.Y., Fan X. SADANet: Integrating Scale-Aware and Domain Adaptive for Traffic Sign Detection. Ieee Access, 2020, no. 8, p. 77920.
22	Chen Y.Y.L., Kong T., Qi L., Chu R,. Li L., Jia J. Scale-aware Automatic Augmentation for Object Detection. arXiv, 2021, p. 210317220.
23	Tan M.R.P., Le Q.V. EfficientDet: Scalable and Efficient Object Detection. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 10781-90.
24	Qi W.T., Qi Y., Liu J. YOLO5Face: Why Reinventing a Face Detector. 2021.
25	Zhang Q.T.S., Wang Y., Tang Z., Chen Y., Cai L., Ling H. M2Det A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, no. 33, pp. 9259-66.