Classification of Traffic Signs Using Transfer Learning Methods

Yıl 2024, Cilt: 24 Sayı: 4, 829 - 838, 20.08.2024

Ömer Aykılıç , Muhammet Sinan Başarslan , Fatih Bal

https://doi.org/10.35414/akufemubid.1420978

Öz

Transportation refers to a process based on the movement of people or vehicles from one place to another. Sea routes and roads have existed for centuries. They generally play a very important role in people's daily life, trade and industrial activities. Highway, a mode of transportation, is the first preferred mode of transportation worldwide. However, various signs and rules have been set by the authorities to prevent chaos on the highways. Traffic signs are the most important of these rules. In this study, transfer learning models (VGG16, VGG19, Xception and EfficientNet) are used to classify traffic signs using a state-of-art traffic signs dataset (German Traffic Sign Detection Benchmark-GTSDB). Accuracy was used as the classification evaluation criterion. The CNN model designed for the study gave the best result with an accuracy rate of 98% and a model competing with the literature was proposed.

Anahtar Kelimeler

Traffic sign images, image processing, classification, transfer learning

Transfer Öğrenme Yöntemleri Kullanılarak Trafik İşaretlerinin Sınıflandırılması

Öz

Ulaşım, insanların veya araçların bir yerden başka bir yere hareketine dayanan bir süreci ifade eder. Deniz yolları ve karayolları yüzyıllardır var olmuştur. Genellikle insanların günlük yaşamında, ticaretinde ve endüstriyel faaliyetlerinde çok önemli bir rol oynarlar. Bir ulaşım şekli olan karayolu, dünya genelinde ilk tercih edilen ulaşım şeklidir. Ancak karayollarında yaşanan kaosu önlemek için yetkililer tarafından çeşitli işaretler ve kurallar belirlenmiştir. Trafik işaretleri bu kuralların en önemlisidir. Bu çalışmada, transfer öğrenme modelleri (VGG16, VGG19, Xception ve EfficientNet) son teknoloji bir trafik işaretleri veri kümesi (German Traffic Sign Detection Benchmark-GTSDB) kullanılarak trafik işaretlerini sınıflandırmak için kullanılmıştır. Sınıflandırma değerlendirme kriteri olarak doğruluk kullanılmıştır. Çalışma için tasarlanan CNN modeli %98 doğruluk oranı ile en iyi sonucu vermiş ve literatürle yarışan bir model önerilmiştir.

Anahtar Kelimeler

Trafik işareti görüntüleri, görüntü işleme, sınıflandırma, transfer öğrenme

Kaynakça

• Barstuğan, M., & Osmanpaşaoğlu, Z. 2023. Deep Learniıng Based Human Robot Interactıon With 5g Communıcatıon. Konya Journal of Engineering Sciences, 11(2), 423–438. https://doi.org/10.36306/konjes.1228275
• Chen, Z., Yang, J., & Kong, B. 2011. A Robust Traffic Sign Recognition System for Intelligent Vehicles. 2011 Sixth International Conference on Image and Graphics, 975–980 https://doi.org/10.1109/ICIG.2011.58
• Cireşan, D., Meier, U., Masci, J., & Schmidhuber, J. 2012. Multi-column deep neural network for traffic sign classification. Neural Networks, 32, 333–338. https://doi.org/10.1016/j.neunet.2012.02.023
• Chollet, F., 2016. Xception: Deep Learning with Depthwise Separable Convolutions. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 1800-1807. https://doi.org/10.1109/CVPR.2017.195
• Ellahyani, A., Ansari, M. El, & Jaafari, I. El. 2016. Traffic sign detection and recognition based on random forests. Applied Soft Computing, 46, 805–815. https://doi.org/10.1016/j.asoc.2015.12.041
• Fleyeh, H., & Davami, E. 2011. Eigen-based traffic sign recognition. IET Intelligent Transport Systems, 5(3), 190-196. https://doi.org/10.1049/iet-its.2010.0159
• Hannan, M. A., Wali, S. B., Pin, T. J., Hussain, A., & Samad, S. A. 2014. Traffic sign classification based on neural network for advance driver assistance system. Przegląd Elektrotechniczny, 90(11), 169-172. https://doi.org/10.12915/pe.2014.11.44
• Houben, S., Stallkamp, J., Salmen, J., Schlipsing, M., & Igel, C. 2013. Detection of Traffic Signs in Real-World Images: The German Traffic Sign Detection Benchmark. International Joint Conference on Neural Networks, 1288. Küçük, Ö., Yavşan, E., & Gökçe, B. 2021. Otonom Tabanlı İşaret ve Şerit Tanımak Amacı ile Bir Öğrenme Sisteminin Geliştirilmesi. Uluslararası Mühendislik Arastirma ve Gelistirme Dergisi, 13(3), 19–25. https://doi.org/10.29137/umagd.1037237
• Çetinkaya, M., & Acarman, T. 2020. Trafik işaret levhası tespiti için derin öğrenme yöntemi. Akıllı Ulaşım Sistemleri ve Uygulamaları Dergisi, 3(2), 140-157.
• Kabakus, A. T., & Erdogmus, P., 2022. An experimental comparison of the widely used pre‐trained deep neural networks for image classification tasks towards revealing the promise of transfer‐learning. Concurrency and Computation: Practice and Experience. 34(24), e7216 https://doi.org/10.1002/cpe.7216
• Khaliki, M. Z., & Başarslan, M. S., 2024. Brain tumor detection from images and comparison with transfer learning methods and 3-layer CNN. Scientific Reports, 14(1), 2664. https://doi.org/10.1038/s41598-024-52823-9
• Maldonado-Bascon, S., Lafuente-Arroyo, S., Gil-Jimenez, P., Gomez-Moreno, H., & Lopez-Ferreras, F. 2007. Road-Sign Detection and Recognition Based on Support Vector Machines. IEEE Transactions on Intelligent Transportation Systems, 8(2), 264–278. https://doi.org/10.1109/TITS.2007.895311
• Mete, S., Çelik, E., & Gül, M., 2022. Predicting the Time of Bus Arrival for Public Transportation by Time Series Models. Journal of Transportation and Logistics, 7(2), 441–455. https://doi.org/10.26650/JTL.2022.953913 Orhan, H., & Yavşan, E., 2023. Artificial intelligence-assisted detection model for melanoma diagnosis using deep learning techniques. Mathematical Modelling and Numerical Simulation with Applications, 3(2), 159–169. https://doi.org/10.53391/mmnsa.1311943
• Ortataş, F. N., & Çetin, E. 2023. Solution of Real-Time Traffic Signs Detection Problem for Autonomous Vehicles by Using YOLOV4 And Haarcascade Algorithms. International Journal of Automotive Science and Technology, 7(2), 125–140. https://doi.org/10.30939/ijastech..1231646
• Palandız, T., Bayrakçı, H. C., & Özkahraman, M. 2021. Yapay Zekâ Kullanılarak Trafik İşaret Levhalarının Sınıflandırılması: Denizli İl Merkezi İçin Örnek Bir Uygulama. International Journal of 3D Printing Technologies and Digital Industry, 5(3), 645–653. https://doi.org/10.46519/ij3dptdi.1021837
• Ruta, A., Li, Y., & Liu, X. 2010. Real-time traffic sign recognition from video by class-specific discriminative features. Pattern Recognition, 43(1), 416–430. https://doi.org/10.1016/j.patcog.2009.05.018
• Hasçelik, S. 2021. Konvolüsyonel sinir ağı kullanılarak trafik işaretlerini gerçek zamanlı bulma ve tanıma (Master's thesis, Trakya Üniversitesi, Fen Bilimleri Enstitüsü), 47 Shustanov, A., & Yakimov, P., 2017. CNN design for real-time traffic sign recognition. Procedia engineering, 201, 718-725. https://doi.org/10.1016/j.proeng.2017.09.594
• Sermanet, P., & LeCun, Y. 2011. Traffic sign recognition with multi-scale Convolutional Networks. 2011 International Joint Conference on Neural Networks, 2809–2813. https://doi.org/10.1109/IJCNN.2011.6033589
• Tan, M., & Le, Q., 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. 2019 International conference on machine learning (ICML), 6105-6114. https://doi.org/10.48550/arXiv.1905.11946
• Torres, L. T., Paixao, T. M., Berriel, R. F., De Souza, A. F., Badue, C., Sebe, N., & Oliveira-Santos, T., 2019. Effortless Deep Training for Traffic Sign Detection Using Templates and Arbitrary Natural Images. 2019 International Joint Conference on Neural Networks (IJCNN), 1–7. https://doi.org/10.1109/IJCNN.2019.8852086
• Vicen-Bueno, R., García-González, A., Torijano-Gordo, E., Gil-Pita, R., & Rosa-Zurera, M. 2007. Traffic sign classification by image preprocessing and neural networks. In Computational and Ambient Intelligence: 9th International Work-Conference on Artificial Neural Networks, IWANN 2007, San Sebastián, Spain, 741-748. https://doi.org/10.1007/978-3-540-73007-1_89
• Yavsan, E., & Ucar, A., 2015. Teaching human gestures to humanoid robots by using Kinect sensor. 2015 23nd Signal Processing and Communications Applications Conference (SIU), 1208–1211. https://doi.org/10.1109/SIU.2015.7130053
• Yildiz, G., & Dizdaroglu, B. 2019. Traffic Sign Detection via Color And Shape-Based Approach. 2019 1st International Informatics and Software Engineering Conference (UBMYK), 1–5. https://doi.org/10.1109/UBMYK48245.2019.8965590
• Yuan, X., Guo, J., Hao, X., & Chen, H. 2015. Traffic Sign Detection via Graph-Based Ranking and Segmentation Algorithms. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 45(12), 1509–1521. https://doi.org/ 10.1109/TSMC.2015.2427771