NaijaTrafficNet: A Custom CNN for Robust Sign Classification under Nigerian Road Conditions
Article Sidebar
Main Article Content
Abstract
In this study, we propose NaijaTrafficNet, a novel custom Convolutional Neural Network (CNN) architecture designed for robust traffic sign classification under challenging Nigerian road conditions, characterised by poor lighting, occlusion, and non-standard signage. To address data scarcity, we merged two public datasets the Kaggle Traffic Sign Dataset Classification and the German Traffic Sign Recognition Benchmark (GTSRB) resulting in a unified dataset of 12,472 images across 43 classes. Extensive preprocessing, including resizing, grayscale conversion, histogram equalization, and data augmentation, was applied to enhance generalizability. The model was trained from scratch using the Adam optimizer and evaluated on a held-out test set of 795 images. NaijaTrafficNet achieved a test accuracy of 94.72% and a weighted F1-score of 94.48%, demonstrating high performance, particularly for regulatory signs (e.g., stop and speed limits). The architecture is lightweight, enabling real-time inference suitable for deployment in resource-constrained environments. Limitations include misclassification of visually similar signs (e.g., 50 km/h vs. 60 km/h). This work contributes (1) an open-source preprocessing pipeline for African traffic sign data, (2) a novel CNN architecture, and (3) empirical validation of deep learning for non-standard signage. Future work includes comparative benchmarking and synthetic data generation.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
Krizhevsky, A., Sutskever, I., & Hinton, G.E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84 - 90.
Khalaf, O.I., & Abdulsahib, G.M. (2021). Optimised dynamic storage of data (ODSD) in IoT based on blockchain for wireless sensor networks. PeerJ Computer Science, 7, e476.
Szegedy, C., et al. (2015). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1 - 9.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436 - 444.
Redmon, J., & Farhadi, A. (2018). YOLOv3: An incremental improvement. arXiv:1804.02767.
Khan, M., et al. (2020). Deep learning for safe autonomous driving: Current challenges and future directions. IEEE Transactions on Intelligent Transportation Systems, 22(7), 4316 - 4336.
Alawaji, K., Hedjar, R., & Zuair, M. (2024). Traffic sign recognition using multi-task deep learning for self-driving vehicles. Sensors, 24(11), 3282.
Girish Kumar, N.G., Kishore, A., & Krishna, A.J. (2025). Real-time traffic sign recognition and autonomous vehicle control system using convolutional neural networks. Multimedia Tools and Applications, 1 - 36.
Houben, S., et al. (2013). Detection of traffic signs in real-world images: The German Traffic Sign Detection Benchmark. Proceedings of the International Joint Conference on Neural Networks (IJCNN), 1 - 8.
Mathur, M., Singh, A.K., & Mohapatra, S.K. (2019). Traffic sign detection and recognition using deep learning. Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW), 278 - 284.
Yu, F., & Koltun, V. (2015). Multiscale context aggregation by dilated convolutions. arXiv:1511.07122.
Raza, M., et al. (2025). An edge-deployed real-time adaptive traffic light control system using YOLO-based vehicle detection and PCE-aware density estimation. IEEE Access.
Zhang, X. (2025). Artificial intelligence in intelligent traffic signal control. Applied and Computational Engineering, 118, 113 - 120.
Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 886 - 893.
He, K., et al. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770 - 778.
Ugboko, E.T., & Jo, S.B. (2025). Adapting AI-based speed violation detection systems for Africa: A case study with Nigeria. African Transport Studies, 3, 100035.
Huang, G., et al. (2017). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 4700 - 4708.
Ahmed, S.F., et al. (2023). Deep learning modelling techniques: Current progress, applications, advantages, and challenges. Artificial Intelligence Review, 56(11), 13521 - 13617.
Hussain, M., et al. (2024). A comprehensive review on deep learning-based data fusion. IEEE Access.
Nasser, M., & Yusof, U.K. (2023). Deep learning based methods for breast cancer diagnosis: A systematic review and future direction. Diagnostics, 13(1), 161.
Tan, M., & Le, Q. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning (ICML), 6105 - 6114.
Dosovitskiy, A., et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929.
Li, Z., et al. (2018). Improving traffic sign recognition by active search. Proceedings of the IEEE Intelligent Vehicles Symposium (IV), 1 - 6.
Lin, T.Y., et al. (2017). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2980 - 2988.
Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3431 - 3440.
Russakovsky, O., et al. (2015). ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 115(3), 211 - 252.
Ren, S., et al. (2017). Faster R-CNN: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6), 1137 - 1149.
Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556.
Lin, L.J., et al. (2014). Microsoft COCO: Common objects in context. Proceedings of the European Conference on Computer Vision (ECCV), 740 - 755.
Szegedy, C., et al. (2016). Rethinking the inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2818 - 2826.
Howard, A., et al. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861.
Sandler, M., et al. (2018). MobileNetV2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 4510 - 4520.
Shustanov, A., & Yakimov, P. (2017). CNN design for real-time traffic sign recognition. Procedia Engineering, 201, 718 - 725.
Singh, K., & Malik, N. (2022). CNN based approach for traffic sign recognition system. Advanced Journal of Graduate Research, 11(1), 23 - 33.
Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1251 - 1258.
Hemateja, A. (2023). Traffic sign dataset classification. Kaggle. Available at: https://www.kaggle.com/datasets/ahemateja19bec1025/traffic-sign-dataset-classification (Accessed: 1 April 2025).
Stallkamp, J., et al. (2011). The German Traffic Sign Recognition Benchmark: A multiclass classification competition. Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN), 1453 - 1460.
DeVries, T., & Taylor, G.W. (2017). Improved regularisation of convolutional neural networks with cutout. arXiv:1708.04552.
Cubuk, E.D., et al. (2018). AutoAugment: Learning augmentation policies from data. arXiv:1805.09501.
Narejo, S., et al. (2020). An automated system for traffic sign recognition using convolutional neural network. 3C Tecnología: Glosas de innovación aplicadas a la pyme, 9(1), 119 - 135.
Sreya, S.K.V.N. (2021). Traffic sign classification using CNN. International Journal of Research in Applied Science and Engineering Technology, 9, 1952 - 1956.
Kingma, D.P., & Ba, J. (2014). Adam: A method for stochastic optimisation. arXiv:1412.6980.
Goodfellow, I., et al. (2014). Generative adversarial nets. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), 2672 - 2680.
Ghouse, M., Farag, S., & Butt, U. (2025). Traffic sign recognition based on CNN vs different transfer learning techniques. Fifth Symposium on Pattern Recognition and Applications (SPRA 2024), 13540, 18 - 25, SPIE.
Vaswani, A., et al. (2017). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), 5998 - 6008.
Alghmgham, D.A., et al. (2019). Autonomous traffic sign (ATSR) detection and recognition using deep CNN. Procedia Computer Science, 163, 266 - 274.
De Guia, J.M., & Deveraj, M. (2024). Development of traffic light and road sign detection and recognition using deep learning. Development, 15(10).
Wali, S.B., et al. (2019). Vision-based traffic sign detection and recognition systems: Current trends and challenges. Sensors, 19(9), 2093.
Bichkar, M., Bobhate, S., & Chaudhari, S. (2021). Traffic sign classification and detection of Indian traffic signs using deep learning. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 7(3), 215 - 219.
Shrivastava, A., et al. (2017). Learning from simulated and unsupervised images through adversarial training. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2107-2116.
Bulla, P. (2022). Traffic sign detection and recognition based on convolutional neural network. International Journal on Recent and Innovation Trends in Computing and Communication, 10(4), 43 - 53.
Gollapudi, S.J., Singathala, H., & Kata, H. (2023). Traffic sign recognition and detection using SVM and CNN. International Research Journal of Engineering and Technology (IRJET), 10(7), 117 - 125.