Research Article
BibTex RIS Cite

Otonom araçlar için evrişimsel sinir ağları kullanılarak trafik işareti sınıflandırması

Year 2025, Volume: 8 Issue: 2, 289 - 298, 25.10.2025
https://doi.org/10.51513/jitsa.1746494

Abstract

Trafik işaretlerinin tanınması, yollarda güvenli navigasyon için otonom araçların geliştirilmesinde temel faaliyetlerden biridir. Bu çalışma, ConvNet'in Türk trafik işaretlerini tehlike uyarı işaretleri ve düzenleyici işaretler olmak üzere iki sınıfa ayırma çalışmasını ele almaktadır. Model performansını artırmak için renk tonu titreme dönüşümleriyle zenginleştirilmiş 129 trafik işareti görüntüsünden oluşan bir veri kümesi kullanılmıştır. Üç evrişim katmanlı mimariye, dört ReLU katmanına ve iki tam bağlı katmana dayanan ConvNet, iki trafik işareti sınıfını sınıflandırmak üzere eğitilmiştir. Elde edilen ortalama doğruluk, eğitim setinde %97,7 ± %5,2, doğrulama setinde %88,8 ± %1,2 ve test setinde %96,9 ± %7,2 olmuştur. Bu sonuçlar, ConvNet'lerin trafik işaretlerini tanımlamada ve sınıflandırmada oldukça iyi çalıştığını ve dolayısıyla otonom araç teknolojilerinde uygulanabileceğini kanıtlamaktadır. Modelin uygulanabilirliğini test etmek için gelecekteki çalışmalarda trafik işaretlerinin çekilmiş gerçek fotoğrafları kullanılacaktır.

References

  • Abdelkhalek, A., & Mashaly, M. (2023). Addressing the class imbalance problem in network intrusion detection systems using data resampling and deep learning. The journal of Supercomputing, 79(10), 10611-10644.
  • Al-Ali, E. M., Hajji, Y., Said, Y., Hleili, M., Alanzi, A. M., Laatar, A. H., & Atri, M. (2023). Solar energy production forecasting based on a hybrid CNN-LSTM-transformer model. Mathematics, 11(3), 676.
  • Altuntaş, Y., Okumuş, F., & Kocamaz, F. (2022). Evrişimsel Sinir Ağları ve Transfer Öğrenme Yaklaşımı Kullanılarak Altın Fiyat Yönünün Tahmini. Computer Science, 7(2), 124-131.
  • Arora, V., Ng, E. Y.-K., & Singh, A. (2022). Machine learning and its applications. In Smart Electrical and Mechanical Systems (pp. 1-37). Elsevier.
  • Arslan, B., Büyükkaya, T., & Ilgın, H. A. (2016). Real time traffic sign detection and recognition. Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering, 58(2), 70-83.
  • Arul, V. (2021). Deep learning methods for data classification. In Artificial intelligence in data mining (pp. 87-108). Elsevier.
  • Avci, D., Sert, E., Dogantekin, E., Yildirim, O., Tadeusiewicz, R., & Plawiak, P. (2023). A new super resolution Faster R-CNN model based detection and classification of urine sediments. Biocybernetics and Biomedical Engineering, 43(1), 58-68.
  • Bartneck, C., Lütge, C., Wagner, A., & Welsh, S. (2020). Autonomous vehicles. In An introduction to ethics in robotics and AI (pp. 83-92). Springer.
  • Bucsuházy, K., Matuchová, E., Zůvala, R., Moravcová, P., Kostíková, M., & Mikulec, R. (2020). Human factors contributing to the road traffic accident occurrence. Transportation research procedia, 45, 555-561.
  • Çetin, E., & Ortataş, F. (2021). Elektrikli ve Otonom Araçlarda Makine Öğrenmesi Kullanarak Trafik Levhaları Tanıma ve Simülasyon Uygulaması. El-Cezeri, 8(3), 1081-1092.
  • Gezgin, H., & Alkan, R. M. (2024). Traffic sign detection and recognition based on MMS data using YOLOv4-Tiny algorithm. Neural Computing and Applications, 36(33), 20633-20651.
  • Gündüz, H., Kaplan, S., Günal, S., & Akınlar, C. (2013). Circular traffic sign recognition empowered by circle detection algorithm. 2013 21st Signal Processing and Communications Applications Conference (SIU),
  • Kilic, I., & Aydin, G. (2020). Traffic sign detection and recognition using tensorflow’s object detection API with a new benchmark dataset. 2020 international conference on electrical engineering (ICEE),
  • Kocakanat, K., & Serif, T. (2021). Turkish traffic sign recognition: comparison of training step numbers and lighting conditions. Avrupa Bilim ve Teknoloji Dergisi(28), 1469-1475.
  • Mahadik, S., Pawar, P. M., & Muthalagu, R. (2023). Efficient intelligent intrusion detection system for heterogeneous internet of things (HetIoT). Journal of Network and Systems Management, 31(1), 2.
  • Palandız, T., Bayrakçı, H. C., & Özkahraman, M. (2021). Yapay Zekâ Kullanilarak Trafik İşaret Levhalarinin Siniflandirilmasi: Denizli İl Merkezi İçin Örnek Bir Uygulama. International Journal of 3D Printing Technologies and Digital Industry, 5(3), 645-653.
  • Salman, E. H., Taher, M. A., Hammadi, Y. I., Mahmood, O. A., Muthanna, A., & Koucheryavy, A. (2022). An anomaly intrusion detection for high-density internet of things wireless communication network based deep learning algorithms. Sensors, 23(1), 206.
  • Salvador, J. (2016). Deep Learning. In Example-Based super resolution (pp. 113-127). Elsevier.
  • Teuwen, J., & Nikita, M. (2019). Convolutional Neural Networks. In Handbook of medical image computing and computer assisted intervention (pp. 481-501). Elsevier.
  • Uluskan, S. (2020). Automatic detection of regulatory traffic signs via circle detection by post edge detection applied to straight line Hough transform. International Journal of Automotive Science And Technology, 4(2), 49-58.
  • Vilchez, J. L. (2019). Mental representation of traffic signs and their classification: Warning signs. Transportation research part F: traffic psychology and behaviour, 64, 447-462.
  • Wang, J., Ma, Y., Zhang, L., Gao, R. X., & Wu, D. (2018). Deep learning for smart manufacturing: Methods and applications. Journal of manufacturing systems, 48, 144-156.
  • Waziry, S., Rasheed, J., Ghabban, F. M., Alsubai, S., Elkiran, H., & Alqahtani, A. (2024). Unveiling interpretability: analyzing transfer learning in deep learning models for traffic sign recognition. SN Computer Science, 5(6), 682.
  • Yaliç, H. Y., & Can, A. B. (2011). Automatic recognition of traffic signs in Turkey roads. 2011 IEEE 19th Signal Processing and Communications Applications Conference (SIU),
  • Yıldıran, O. (2019). Derin Öğrenme Yöntemleri Ile Trafik Işareti Tanıma Marmara Universitesi (Turkiye)].
  • Zou, L. (2022). Meta-learning for computer vision. In Meta-learning: theory, algorithms and applications (pp. 91-208). Elsevier.

Traffic sign classification for autonomous vehicles using convolutional neural networks

Year 2025, Volume: 8 Issue: 2, 289 - 298, 25.10.2025
https://doi.org/10.51513/jitsa.1746494

Abstract

Recognition of traffic signs is one of the key activities in the development of autonomous vehicles for safe navigation on the roads. This work addresses the study of ConvNet in classifying Turkish traffic signs into two classes: hazard-warning signs and regulatory signs. A dataset of 129 traffic sign images was utilized, augmented through hue jitter transformations to enhance model performance. The ConvNet, based on a three-convolution-layer architecture, four ReLU layers, and two fully connected layers, is trained to classify the two classes of traffic signs. The attained average accuracy was 97.7% ± 5.2% on the training set, 88.8% ± 1.2% on the validation set, and 96.9% ± 7.2% on the test set. These results really prove that ConvNets work quite well in identifying and classifying traffic signs, thus proving that they can be applied in autonomous vehicle technologies. Real-world photos of traffic signs will be used in future studies to test the model's applicability.

References

  • Abdelkhalek, A., & Mashaly, M. (2023). Addressing the class imbalance problem in network intrusion detection systems using data resampling and deep learning. The journal of Supercomputing, 79(10), 10611-10644.
  • Al-Ali, E. M., Hajji, Y., Said, Y., Hleili, M., Alanzi, A. M., Laatar, A. H., & Atri, M. (2023). Solar energy production forecasting based on a hybrid CNN-LSTM-transformer model. Mathematics, 11(3), 676.
  • Altuntaş, Y., Okumuş, F., & Kocamaz, F. (2022). Evrişimsel Sinir Ağları ve Transfer Öğrenme Yaklaşımı Kullanılarak Altın Fiyat Yönünün Tahmini. Computer Science, 7(2), 124-131.
  • Arora, V., Ng, E. Y.-K., & Singh, A. (2022). Machine learning and its applications. In Smart Electrical and Mechanical Systems (pp. 1-37). Elsevier.
  • Arslan, B., Büyükkaya, T., & Ilgın, H. A. (2016). Real time traffic sign detection and recognition. Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering, 58(2), 70-83.
  • Arul, V. (2021). Deep learning methods for data classification. In Artificial intelligence in data mining (pp. 87-108). Elsevier.
  • Avci, D., Sert, E., Dogantekin, E., Yildirim, O., Tadeusiewicz, R., & Plawiak, P. (2023). A new super resolution Faster R-CNN model based detection and classification of urine sediments. Biocybernetics and Biomedical Engineering, 43(1), 58-68.
  • Bartneck, C., Lütge, C., Wagner, A., & Welsh, S. (2020). Autonomous vehicles. In An introduction to ethics in robotics and AI (pp. 83-92). Springer.
  • Bucsuházy, K., Matuchová, E., Zůvala, R., Moravcová, P., Kostíková, M., & Mikulec, R. (2020). Human factors contributing to the road traffic accident occurrence. Transportation research procedia, 45, 555-561.
  • Çetin, E., & Ortataş, F. (2021). Elektrikli ve Otonom Araçlarda Makine Öğrenmesi Kullanarak Trafik Levhaları Tanıma ve Simülasyon Uygulaması. El-Cezeri, 8(3), 1081-1092.
  • Gezgin, H., & Alkan, R. M. (2024). Traffic sign detection and recognition based on MMS data using YOLOv4-Tiny algorithm. Neural Computing and Applications, 36(33), 20633-20651.
  • Gündüz, H., Kaplan, S., Günal, S., & Akınlar, C. (2013). Circular traffic sign recognition empowered by circle detection algorithm. 2013 21st Signal Processing and Communications Applications Conference (SIU),
  • Kilic, I., & Aydin, G. (2020). Traffic sign detection and recognition using tensorflow’s object detection API with a new benchmark dataset. 2020 international conference on electrical engineering (ICEE),
  • Kocakanat, K., & Serif, T. (2021). Turkish traffic sign recognition: comparison of training step numbers and lighting conditions. Avrupa Bilim ve Teknoloji Dergisi(28), 1469-1475.
  • Mahadik, S., Pawar, P. M., & Muthalagu, R. (2023). Efficient intelligent intrusion detection system for heterogeneous internet of things (HetIoT). Journal of Network and Systems Management, 31(1), 2.
  • Palandız, T., Bayrakçı, H. C., & Özkahraman, M. (2021). Yapay Zekâ Kullanilarak Trafik İşaret Levhalarinin Siniflandirilmasi: Denizli İl Merkezi İçin Örnek Bir Uygulama. International Journal of 3D Printing Technologies and Digital Industry, 5(3), 645-653.
  • Salman, E. H., Taher, M. A., Hammadi, Y. I., Mahmood, O. A., Muthanna, A., & Koucheryavy, A. (2022). An anomaly intrusion detection for high-density internet of things wireless communication network based deep learning algorithms. Sensors, 23(1), 206.
  • Salvador, J. (2016). Deep Learning. In Example-Based super resolution (pp. 113-127). Elsevier.
  • Teuwen, J., & Nikita, M. (2019). Convolutional Neural Networks. In Handbook of medical image computing and computer assisted intervention (pp. 481-501). Elsevier.
  • Uluskan, S. (2020). Automatic detection of regulatory traffic signs via circle detection by post edge detection applied to straight line Hough transform. International Journal of Automotive Science And Technology, 4(2), 49-58.
  • Vilchez, J. L. (2019). Mental representation of traffic signs and their classification: Warning signs. Transportation research part F: traffic psychology and behaviour, 64, 447-462.
  • Wang, J., Ma, Y., Zhang, L., Gao, R. X., & Wu, D. (2018). Deep learning for smart manufacturing: Methods and applications. Journal of manufacturing systems, 48, 144-156.
  • Waziry, S., Rasheed, J., Ghabban, F. M., Alsubai, S., Elkiran, H., & Alqahtani, A. (2024). Unveiling interpretability: analyzing transfer learning in deep learning models for traffic sign recognition. SN Computer Science, 5(6), 682.
  • Yaliç, H. Y., & Can, A. B. (2011). Automatic recognition of traffic signs in Turkey roads. 2011 IEEE 19th Signal Processing and Communications Applications Conference (SIU),
  • Yıldıran, O. (2019). Derin Öğrenme Yöntemleri Ile Trafik Işareti Tanıma Marmara Universitesi (Turkiye)].
  • Zou, L. (2022). Meta-learning for computer vision. In Meta-learning: theory, algorithms and applications (pp. 91-208). Elsevier.
There are 26 citations in total.

Details

Primary Language English
Subjects Artificial Intelligence (Other)
Journal Section Articles
Authors

Mehmet Özcan 0000-0001-8250-3143

Abdurrahim Hüseyin Ezirmik 0000-0002-1154-1537

Early Pub Date October 22, 2025
Publication Date October 25, 2025
Submission Date July 20, 2025
Acceptance Date October 14, 2025
Published in Issue Year 2025 Volume: 8 Issue: 2

Cite

APA Özcan, M., & Ezirmik, A. H. (2025). Traffic sign classification for autonomous vehicles using convolutional neural networks. Akıllı Ulaşım Sistemleri Ve Uygulamaları Dergisi, 8(2), 289-298. https://doi.org/10.51513/jitsa.1746494