JBT Journal
Advanced

Raqamli Transformatsiya va Sun’iy Intellekt

SUN’IY INTELLEKT YORDAMIDA VIDEOTASVIRLARDA AVARIYA HOLATINI ANIQLASH ALGORITMINI ISHLAB CHIQISH

Abduvaliyev Asror Abdusoliyevich1

1 Qarshi davlat texnika universiteti

Keywords

kompyuter koʻrish LSTM diqqat (attention) mexanizmi chuqur oʻrganish avariya holatini aniqlash konvolyutsion neyron tarmoq sun’iy intellekt videotasvirni tahlil qilish obyektni aniqlash CNN

Abstract

Ushbu maqolada avtomobil yoʻllarida yuzaga keladigan avariya (baxtsiz hodisa) holatlarini videokuzatuv kameralari orqali real vaqt rejimida aniqlash uchun sun’iy intellektga asoslangan algoritm taklif etilgan. Taklif etilgan yechim konvolyutsion neyron tarmoq (CNN) asosidagi fazoviy xususiyatlarni ajratish moduli, uzoq qisqa muddatli xotira (LSTM) tarmogʻi asosidagi vaqtinchalik ketma-ketlik tahlili hamda diqqat (attention) mexanizmini oʻzida birlashtirgan gibrid arxitekturaga asoslangan.

Views: 99 Published: 2026-10-28 Pages: 356-361 Volume: 4 Issue: 5

References

  1. Hochreiter S., Schmidhuber J. Long Short-Term Memory // Neural Computation. 1997. Vol. 9, No. 8. P. 1735–1780.
  2. Chan F.-H., Chen Y.-T., Xiang Y., Sun M. Anticipating Accidents in Dashcam Videos // Proceedings of the Asian Conference on Computer Vision (ACCV), 2020. P. 136–153.
  3. Kim H., Lee J., Park S. ConvLSTM-Based Spatiotemporal Feature Learning for Traffic Accident Detection // Applied Sciences. 2022. Vol. 12, No. 14. P. 7112.
  4. Jocher G. et al. Ultralytics YOLOv8 Documentation. 2023. URL: https://docs.ultralytics.com
  5. Redmon J., Farhadi A. YOLOv3: An Incremental Improvement // arXiv preprint arXiv:1804.02767. 2018.
  6. Singh D., Mohan C.K. Deep Spatio-Temporal Representation for Detection of Road Accidents Using Stacked Autoencoder // IEEE Transactions on Intelligent Transportation Systems. 2019. Vol. 20, No. 3. P. 879–887.
  7. Wang T., Qiao M., Zhu A. et al. Real-Time Traffic Accident Detection Using YOLOv5 and DeepSORT // Sensors. 2021. Vol. 21, No. 19. P. 6668.
  8. Carreira J., Zisserman A. Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset // IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017. P. 6299–6308.
  9. He K., Zhang X., Ren S., Sun J. Deep Residual Learning for Image Recognition // Proceedings of CVPR. 2016. P. 770–778.
  10. A. Abduvaliyev Transport oqimlarini tahlil qilishda geoaxborot tizimlarining (GAT) qo‘llanilishi // Journal of Transport // Volume:2|Issue:4|2025 b. 55-57.