Deep Learning Based Traffic Sign Recognition Using YOLO Algorithm

Year 2024, , 219 - 229, 26.01.2024

Gökalp Çınarer

https://doi.org/10.29130/dubited.1214901

Abstract

Traffic sign detection has attracted a lot of attention in recent years among object recognition applications. Accurate and fast detection of traffic signs will also eliminate an important technical problem in autonomous vehicles. With the developing artificial intelligency technology, deep learning applications can distinguish objects with high perception and accurate detection. New applications are being tested in this area for the detection of traffic signs using artificial intelligence technology. In this context, this article has an important place in correctly detecting traffic signs with deep learning algorithms. In this study, three model of (You Only Look Once) YOLOv5, an up-to-date algorithm for detecting traffic signs, were used. A system that uses deep learning models to detect traffic signs is proposed. In the proposed study, real-time plate detection was also performed. When the precision, recall and mAP50 values of the models were compared, the highest results were obtained as 99.3, 95% and 98.1%, respectively. Experimental results have supported that YOLOv5 architectures are an accurate method for object detection with both image and video. It has been seen that YOLOv5 algorithms are quite successful in detecting traffic signs and average precession.

Keywords

Deep learning, traffic sign recognition, Yolo

Yolo Algoritması Kullanarak Derin Öğrenme Tabanlı Trafik İşareti Tanıma

Abstract

Trafik işaretleri tespiti nesne tanıma uygulamaları arasında son yıllarda oldukça fazla ilgi görmektedir. Trafik işaretlerinin doğru ve hızlı şekilde algılanması otonom araçlarda önemli bir teknik sorunu da ortadan kaldıracaktır. Gelişen yapay zeka teknolojiyle beraber derin öğrenme uygulamaları yüksek algılama ve doğru tespitle objeleri ayırt edebilmektedir. Yapay zeka teknolojisi kullanarak trafik levhalarının tespiti için bu alanda yeni uygulamalar test edilmektedir. Bu kapsamda bu makale trafik işaretlerini derin öğrenme algoritmalarıyla doğru tespit etmek için önemli bir yere sahiptir. Bu çalışmada trafik işaretlerinin tespiti için güncel bir algoritma olan YOLOv5’in en yeni üç modeli kullanılmıştır. Derin öğrenme algoritmalarını temel alan bir trafik işaret algılama ve tanıma sistemi önerilmiştir. Önerilen çalışmada aynı zamanda gerçek zamanlı levha tespiti de gerçekleştirilmiştir. Modellerin precision, recall ve mAP50 değerleri karşılaştırıldığında en yüksek sonuçlar sırasıyla %99.3, %95 ve %98.1 olarak elde edilmiştir. Deneysel sonuçlar YOLOv5 mimarilerinin hem görüntü hem de video ile nesne tespiti için doğru bir yöntem olduğunu desteklemektedir. YOLOv5 algoritmalarının trafik işaretlerini ve ortalama hassasiyeti (mAP) algılamada oldukça başarılı olduğu görülmüştür.

Keywords

Derin öğrenme, Trafik işareti tanıma, Yolo, Deep learning, traffic sign recognition

References

• [1] R. Timofte, K. Zimmermann, and L. Van Gool, “Multi-view traffic sign detection, recognition, and 3D localisation,” Machine vision and applications, vol. 25 no. 3, pp. 633-647, 2014.
• [2] P. S. Zaki, M. M. William, B. K. Soliman, K. G. Alexsan, K. Khalil, and M. El-Moursy, “Traffic signs detection and recognition system using deep learning,” arXiv Prepr. arXiv2003.03256, 2020.
• [3] C. Dewi, R.C. Chen, Y.T. Liu, X. Jiang, and K. D. Hartomo, “Yolov4 for advanced traffic sign recognition with synthetic training data generated by various GAN,” IEEE Access, vol. 9, pp. 97228-97242, 2021.
• [4] S. You, Q. Bi, Y. Ji, S. Liu, Y. Feng, and F. Wu, “Traffic sign detection method based on improved SSD,” Information, vol. 11, no. 10, pp. 475, 2020.
• [5] A. Shustanov, and P. Yakimov, “CNN design for real-time traffic sign recognition,” Procedia Engineering, vol. 201, pp. 718-725, 2017.
• [6] Z. Liu, Y. Musha, and H. Wu, “Detection of traffic sign based on improved Yolov4,” In 2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP), 2022, IEEE, pp. 444-448.
• [7] Y. Zhu, and . Q. W. Yan, “Traffic sign recognition based on deep learning,” Multimedia Tools and Applications, vol. 81, no. 13, pp. 17779-17791, 2022.
• [8] H. Wan, L. Gao, M. Su, Q. You, H. Qu, and Q. Sun, “A novel neural network model for traffic sign detection and recognition under extreme conditions,” Journal of Sensors, 2021.
• [9] E. H. C. Lu, M. Gozdzikiewicz, K. H. Chang, and J. M. Ciou, “A hierarchical approach for traffic sign recognition based on shape detection and image classification,” Sensors, vol. 22, no 13, pp. 4768, 2022.
• [10] L. Yi, L. Jinguo, Z. Yongjie, and M. Ping, “Detection of self-explosive insulators in aerial images based on improved Yolov4,” In Journal of Physics: Conference Series vol. 2320, no. 1, pp. 012025, IOP Publishing, 2022.
• [11] L. Jiang, H. Liu, H. Zhu, and G. Zhang, “Improved Yolov5 with balanced feature pyramid and attention module for traffic sign detection,” In MATEC Web of Conferences vol. 355, EDP Sciences, 2022.
• [12] A. Aggar, and M. Zaiter, “Iraqi traffic signs detection based on Yolov5,” In 2021 International Conference on Advanced Computer Applications, 2021, IEEE, pp. 5-9.
• [13] F. Shao, X. Wang, F. Meng, J. Zhu, D. Wang, and J. Dai, “Improved faster R-CNN traffic sign detection based on a second region of interest and highly possible regions proposal network,” Sensors, vol. 19, no. 10, pp. 2288, 2019.
• [14] Z. Liu, M. Qi, C. Shen, Y. Fang, X. Zhao, “Cascade saccade machine learning network with hierarchical classes for traffic sign detection,” Sustainable Cities and Society, 67, 102700, 2021.
• [15] L. Zeng, B. Sun, D. Zhu, “Underwater target detection based on Faster R-CNN and adversarial occlusion network,” Engineering Applications of Artificial Intelligence, vol. 100, 104190, 2021.
• [16] J. Zhang, M. Huang, X. Jin , and X. Li , “A real-time Chinese traffic sign detection algorithm based on modified Yolov2,” Algorithms, vol. 10, no. 4, pp. 127, 2017.
• [17] O. Belghaouti, W. Handouzi, and M. Tabaa, “Improved traffic sign recognition using deep ConvNet architecture,” Procedia Computer Science, vol. 177, pp. 468–473, 2020.
• [18] D. Tabernik, and D. Skočaj, “Deep learning for large-scale traffic-sign detection and recognition,” IEEE transactions on intelligent transportation systems, vol. 21, no. 4, pp. 1427-1440, 2019.
• [19] V. Sichkar. (2020). Traffic Signs Dataset in Yolo Format [Online]. Available: https://www.kaggle.com/datasets/valentynsichkar/traffic-signs-dataset-in-yolo-format
• [20] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: unified, real-time object detection,” In Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 779-788.
• [21] M. Sozzi, A. Kayad, D. Tomasi, L. Lovat, F. Marinello, and L. Sartori, “Assessment of grapevine yield and quality using a canopy spectral index in white grape variety,” In Precision agriculture 19, pp. 111-129, Wageningen Academic Publishers, 2019.
• [22] W. Lan, J. Dang, Y. Wang, and S. Wang, “Pedestrian detection based on Yolo network model,” In 2018 IEEE international conference on mechatronics and automation (ICMA), 2018, IEEE, pp. 1547-1551.
• [23] Y. Tian, G. Yang, Z. Wang, H. Wang, E. Li, and Z. Liang, “Apple detection during different growth stages in orchards using the improved Yolo-v3 model,” Computers and Electronics in Agriculture, vol. 157, pp. 417-426, 2019.
• [24] R. N. Babu, V. Sowmya, and K. P. Soman, “Indian car number plate recognition using deep learning,” 2nd international conference on intelligent computing, instrumentation and control technologies, 2019, IEEE, pp. 1269-1272.
• [25] J. Liu, and X. Wang, “Tomato diseases and pests detection based on improved Yolov3 convolutional neural network,” Frontiers in Plant Science, vol. 11, pp. 898, 2020.
• [26] J. Yu, and W. Zhang, “Face mask wearing detection algorithm based on improved Yolo-v4,” Sensors, vol. 21, no. 9, pp. 3263, 2021.
• [27] S. Tan, G. Lu, Z. Jiang, and L. Huang, “Improved Yolov5 network model and application in safety helmet detection,” 2021 IEEE International Conference on Intelligence and Safety for Robotics, 2021, IEEE, pp. 330-333.
• [28] J. Wan, B. Chen, and Y. Yu, “Polyp detection from colorectum images by using attentive Yolov5,” Diagnostics, vol. 11, no. 12, pp. 2264, 2021.
• [29] F. Zhou, H. Zhao, and Z. Nie, “Safety helmet detection based on Yolov5,” In 2021 IEEE International Conference on Power Electronics, Computer Applications, 2021, IEEE, pp. 6-11.
• [30] S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, “Path aggregation network for instance segmentation,” Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 8759-8768.
• [31] H. Rezatofighi, N. Tsoi, J. Gwak, A. Sadeghian, I. Reid, S. Savarese, “Generalized intersection over union: a metric and a loss for bounding box regression,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 658-666.