CONDUCTING ANALYSIS OF DEEP LEARNING ALGORITHMS USED IN ROAD SIGN DETECTION

Abstract

Abstract. This article analyzes convolutional neural network (CNN) algorithms and studies their application in computer vision, in particular, in automated road recognition systems. The main focus is on the structure of the CNN architecture, its operating principles and its capabilities in image segmentation. As a result of this work, theoretical and practical aspects of developing a road sign recognition system based on artificial intelligence technologies will be considered, and proposals will be made for creating a system capable of operating in real time.

Keywords

References

1. Szeliski, R. (2022). Computer Vision: Algorithms and Applications. Springer. ISSN - 1868 - 0941. https://doi.org/10.1007/978 - 3 - 030 - 34372 - 9
2. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. The MIT Press, 2016, 800 pp, ISBN: 0262035618. DOI:10.1007/s10710 - 017 - 9314 - z
3. Russell, S., & Norvig, P. (2020). Artificial Intelligence: A Modern Approach (4th ed.). Pearson.
4. Athanasios Voulodimos, Nikolaos Doulamis, Anastasios Doulamis, and Eftychios Protopapadakis. Deep Learning for Computer Vision: A Brief Review. Volume 2018, Article ID 7068349, 13 pages, https://doi.org/10.1155/2018/7068349.
5. Redmon, J., & Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv preprint arXiv:1804.02767.
6. He, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017). Mask R - CNN. In Proceedings of the IEEE ICCV.
7. R. Sharma, R. B. Pachori, and P. Sircar, (2020). “Automated emotion recognition based on higher - order statistics and deep learning algorithm,” Biomedical Signal Processing and Control, vol. 58, p. 101867.
8. Zhongqin Bi,·Ling Yu, Honghao Gao, Ping Zhou, Hongyang Yao. (2021) Improved VGG model‑based e ffi cient tra ffi c sign recognition for safe driving in 5G scenarios. International Journal of Machine Learning and Cybernetics 12(3). DOI:10.1007/s13042 - 020 - 01185 - 5
9. A. Almalaq and G. Edwards. (2017). “A review of deep learning methods applied on load forecasting,” in Proceedings - 16th IEEE International Conference on Machine Learning and Applications, ICMLA 2017, pp. 511 – 516. doi: 10.1109/ICMLA.2017.0 - 110
10. K. Simonyan and A. Zisserman, (2014) “Very deep convolutional networks for large - scale image recognition,” Computer Science, arXiv preprint arXiv:1409.1556.
11. Alexander Wong, Mohammad Javad Sha fi ee, Michael St. Jules. (2018) MicronNet: A Highly Compact Deep Convolutional Neural Network Architecture for Real - Time Embedded Traffic Sign Classification. DOI:10.1109/ACCESS.2018.2873948