Recognition of Brazilian vertical traffic signs and lights from a car using Single Shot Multi box Detector
DOI:
https://doi.org/10.5753/jbcs.2024.3678Keywords:
Artificial Intelligence, MobileNet, SSD, Traffic Signs, Traffic LightsAbstract
This work presents an automated system for recognizing Brazilian vertical traffic signs and lights using artificial intelligence. The main objective of the system is to contribute to road safety by alerting drivers to potential risks such as speeding, alcohol consumption, and cell phone use, which could lead to severe accidents. The system’s core contribution lies in its ability to accurately recognize various traffic signs and lights, providing crucial warnings to drivers. To achieve this, the system utilizes a light version of the single shot multi box detector as its detection algorithm and experiments with three Mobilenet versions as base networks. The optimal Mobilenet version is selected based on a mean average precision higher than 80%, which guarantees reliable detection results. The dataset used for training and evaluation comprises images extracted from YouTube traffic videos, each annotated to create the necessary labels for training. Through this extensive experimentation, the system demonstrates its efficacy in achieving accurate and efficient detection. The results of the experiments are compared with other existing approaches and our work significantly advances the field by providing a tailored dataset, an optimized model, and also valuable insights into traffic sign and light recognition, collectively contributing to the improvement of road safety.
Downloads
References
Alghmgham, D. A., Latif, G., Alghazo, J., and Alzubaidi, L. (2019). Autonomous traffic sign (ATSR) detection and recognition using deep CNN. Procedia Computer Science, 163:266-274. DOI: 10.1016/j.procs.2019.12.108.
Bhatt, N., Laldas, P., and Lobo, V. B. (2022). A real-time traffic sign detection and recognition system on hybrid dataset using cnn. In 2022 7th International Conference on Communication and Electronics Systems (ICCES). IEEE. DOI: 10.1109/icces54183.2022.9835954.
Choudhary, A. S. (2023). ONNX Model | Open Neural Network Exchange. Available online [link]. Accessed 27-11-2023.
Dalborgo, V., Murari, T. B., Madureira, V. S., Moraes, J. G. L., Bezerra, V. M. O. S., Santos, F. Q., Silva, A., and Monteiro, R. L. S. (2023). Traffic sign recognition with deep learning: Vegetation occlusion detection in brazilian environments. Sensors, 23(13):5919. DOI: 10.3390/s23135919.
DeLuca, L. (2021). Black Inventor Garrett Morgan Saved Countless Lives with Gas Mask and Improved Traffic Lights -- scientificamerican.com. Available online [link]. Accessed 11-04-2024.
Dong, X. (2018). Research on Road Transportation Safety Management, page 160–166. Springer International Publishing. DOI: 10.1007/978-3-030-00214-5_21.
Hoelscher, I. G. (2017). Detecção e classificação de sinalização vertical de trânsito em cenários complexos. Master's thesis, Universidade Federal do Rio Grande do Sul. Available online [link].
JDV (2023). O que significa as cores do semáforo. Available at: [link]. Accessed on: 16 July 2024.
Jee, G., Gm, H., Gourisaria, M. K., Singh, V., Rautaray, S. S., and Pandey, M. (2021). Efficacy determination of various base networks in single shot detector for automatic mask localisation in a post covid setup. Journal of Experimental & Theoretical Artificial Intelligence, 35(3):345–364. DOI: 10.1080/0952813x.2021.1960638.
Padilla, R., Netto, S. L., and da Silva, E. A. B. (2020). A survey on performance metrics for object-detection algorithms. In 2020 International Conference on Systems, Signals and Image Processing (IWSSIP). IEEE. DOI: 10.1109/iwssip48289.2020.9145130.
Palmieri, N. (2021). Sinais de Trânsito que todo motorista precisa conhecer. Available online [link]. Accessed 31-01-2023.
Pierre, M. M. and Fernandes, H. C. (2023). Recognition of Brazilian vertical traffic signs and lights using Single Shot Multi box Detector. Master's thesis, Universidade Federal de Uberlândia. Available online [link].
Pon, A., Adrienko, O., Harakeh, A., and Waslander, S. L. (2018). A hierarchical deep architecture and mini-batch selection method for joint traffic sign and light detection. In 2018 15th Conference on Computer and Robot Vision (CRV). IEEE. DOI: 10.1109/crv.2018.00024.
Santos, D. C., Silva, F. A. d., Pereira, D. R., Almeida, L. L. d., Artero, A. O., Piteri, M. A., and Albuquerque, V. H. (2020). Real-time traffic sign detection and recognition using cnn. IEEE Latin America Transactions, 18(03):522–529. DOI: 10.1109/tla.2020.9082723.
Souza, S. S., Santos, M. F., and Souza, G. M. S. (2023). Incapacidade em motociclistas envolvidos em acidente de trânsito. Research, Society and Development, 12(4):e12112441047. DOI: 10.33448/rsd-v12i4.41047.
Story, E. (2021). Road building in brazil. Oxford Research Encyclopedia of Latin American History. DOI: 10.1093/acrefore/9780199366439.013.992.
William, M. M., Zaki, P. S., Soliman, B. K., Alexsan, K. G., Mansour, M., El-Moursy, M., and Khalil, K. (2019). Traffic signs detection and recognition system using deep learning. In 2019 Ninth International Conference on Intelligent Computing and Information Systems (ICICIS). IEEE. DOI: 10.1109/icicis46948.2019.9014763.
World Health Organization (2022). Road traffic injuries. Available online [link]. Accessed 31-03-2023.
Yoneda, K., Kuramoto, A., Suganuma, N., Asaka, T., Aldibaja, M., and Yanase, R. (2020). Robust traffic light and arrow detection using digital map with spatial prior information for automated driving. Sensors, 20(4):1181. DOI: 10.3390/s20041181.
Zhang, J., Wang, W., Lu, C., Wang, J., and Sangaiah, A. K. (2019). Lightweight deep network for traffic sign classification. Annals of Telecommunications, 75(7–8):369–379. DOI: 10.1007/s12243-019-00731-9.
Zhu, Y. and Yan, W. Q. (2022). Traffic sign recognition based on deep learning. Multimedia Tools and Applications, 81(13):17779–17791. DOI: 10.1007/s11042-022-12163-0.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Monhel Maudoony Pierre, Henrique Fernandes
![Creative Commons License](http://i.creativecommons.org/l/by/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution 4.0 International License.