Traffic Sign Recognition for Advanced Driver Assistance Systems: A Neural Network and Computer Vision Approach
DOI:
https://doi.org/10.47839/ijc.24.1.3877Keywords:
artificial intelligence, computer vision, machine learning, neural networks, pattern recognitionAbstract
This paper presents a comprehensive traffic sign recognition system designed to enhance advanced driver assistance systems (ADAS) and autonomous vehicles. The system employs a three-step algorithm comprising color segmentation, shape recognition, and a neural network-based classification to detect and identify various traffic signs in real time. Leveraging the advantages of color-based segmentation for rapid processing and combining it with sophisticated shape detection methods, our approach ensures high accuracy and precision even under challenging conditions such as varying illumination and occlusions. The integration of neural networks allows for effective classification across a broad range of sign types, addressing limitations seen in traditional methods. Our system’s ability to operate with standard onboard cameras, combined with its resilience to lighting variations, marks a significant advancement in traffic sign recognition technology. Extensive testing demonstrates its efficacy in real-world scenarios, highlighting its potential to enhance road safety and support autonomous driving technologies.
References
F. Hu et al., “A comprehensive survey on traffic sign recognition systems,” IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 7, pp. 4745–4762, 2022.
R. C. Gonzalez and R. E. Woods, Digital Image Processing, 4th ed., Upper Saddle River, NJ, USA: Pearson, 2018.
W. Zhang et al., “YOLO-TS: Real-time traffic sign detection with enhanced accuracy using optimized receptive fields,” in Proceedings of the IEEE International Conference on Intelligent Transportation Systems (ITSC), 2021.
A. Zaid et al., “Traffic sign detection and recognition in adverse weather conditions,” IEEE Transactions on Image Processing, vol. 32, no. 1, pp. 567–579, 2023.
M. Komar, V. Golovko, A. Sachenko and S. Bezobrazov, “Development of neural network immune detectors for computer attacks recognition and classification,” in Proceedings of the 2013 IEEE 7th International Conference on Intelligent Data Acquisition and Advanced Computing Systems (IDAACS), Berlin, Germany, 2013, pp. 665-668. https://doi.org/10.1109/IDAACS.2013.6663008
Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, 2015. https://doi.org/10.1038/nature14539
M. Ahmed et al., “A real-time traffic sign detection and recognition system using optimized CNN architectures,” IEEE Transactions on Intelligent Vehicles, vol. 9, no. 4, pp. 1387–1398, 2023.
Z. Gao et al., “Adaptive fusion and dictionary learning models for traffic sign recognition,” IEEE Transactions on Intelligent Transportation Systems, vol. 20, no. 12, pp. 4724–4735, 2019.
K. Ishii et al., “Deep neural networks for traffic sign recognition systems,” IEEE Transactions on Intelligent Vehicles, vol. 4, no. 3, pp. 231–241, 2023.
J. Al-Salameh et al., “Real-time traffic sign recognition and detection using deep learning techniques,” IEEE Access, vol. 8, pp. 57690–57700, 2020.
D. Yu et al., “Real-time traffic sign detection and recognition on low-power embedded devices,” in Proceedings of the IEEE Embedded Systems Symposium, 2022.
H. Li et al., “Towards real-time traffic sign and traffic light detection on embedded systems,” in Proceedings of the IEEE Embedded Systems Conference, 2022.
A. Y. Rodrigues, J. S. Marques, and P. L. Correia, “Context-aware adaptive systems for real-time traffic sign detection,” Research Report, Univ. of Lisbon, Lisbon, Portugal, 2020.
X. Wang et al., “Neural-network-based traffic sign detection and recognition in high-definition images,” Journal of Transportation Engineering, vol. 146, no. 2, pp. 1–12, 2020.
R. Chen et al., “Improved YOLOv5 for real-time multi-scale traffic sign detection,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 6, pp. 5783–5795, 2022.
J. Stallkamp et al., “The German traffic sign recognition benchmark,” [Online]. Available at: https://benchmark.ini.rub.de/gtsrb_news.html
T. Timofte, V. Van Gool, and L. Van Gool, BelgiumTS Dataset, KU Leuven, 2012. [Online]. Available at: https://btsd.ethz.ch.
M. Alhamadi et al., “Real-time road traffic sign detection and recognition for intelligent transportation systems,” Applied Intelligence, vol. 50, no. 1, pp. 163–177, 2021.
X. Zhang et al., “Traffic sign detection and classification using deep learning,” IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 9, pp. 1–10, 2020.
F. Chen et al., “Deep learning techniques for traffic sign recognition,” IEEE Transactions on Intelligent Vehicles, vol. 6, no. 1, pp. 1–10, 2021.
T. Kim et al., “Traffic sign recognition using CNNs and advanced preprocessing techniques,” Proceedings of the International Conference on Computer Vision (ICCV), 2021.
A. Rahman et al., “TRD-YOLO: A real-time, high-performance small traffic sign detection method,” Sensors, vol. 22, no. 8, 2022.
P. V. K. Borges and E. Aldon, “Line detection with Hough transform and line segment clustering,” Pattern Recognition Letters, vol. 32, no. 13, 2011.
C. M. Bishop, Pattern Recognition and Machine Learning, New York, NY, USA: Springer, 2006.
A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in Advances in Neural Information Processing Systems (NIPS), vol. 25, 2012
A. Ishaq et al., “Real-time traffic sign recognition using YOLOv5,” IEEE Access, vol. 9, pp. 1–10, 2021.
J. Lee et al., “Enhanced traffic sign detection using context-aware algorithms,” Pattern Recognition Letters, vol. 130, pp. 321–327, 2023.
S. Zhou et al., “Efficient federated learning with spike neural networks for traffic sign recognition,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 10, pp. 4254–4265, 2022.
H. Li et al., “Deep learning-based traffic sign recognition for autonomous driving,” IEEE Transactions on Intelligent Vehicles, vol. 5, no. 2, pp. 1–10, 2020.
Downloads
Published
How to Cite
Issue
Section
License
International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:• Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
• Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
• Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
