Yapay Sinir Ağları, Destek Vektör Makineleri ve AdaBoost Algoritması ile Araç Sınıflandırmasının Değerlendirilmesi

Öz

Trafik yönetimi ve bilgi sistemlerinin trafik akışını doğru sağlayabilmesi için çeşitli sensörler ve kameralar kullanarak trafik hakkında bilgi edinmesi hayati önem taşımaktadır. Bu bağlamda video kameralar son yıllarda trafik gözetim ve kontrolünde yaygın ve aktif olarak kullanılmaya başlanmıştır. Bu çalışmada araçlar boyutlarına göre üç kategoriye ayrılarak sınıflandırılmıştır. Oluşturduğumuz trafik video görüntüleri üzerinde Yapay Sinir Ağları, Destek Vektör Makineleri ve Adaboost sınıflandırıcıları ile eğitim gerçekleştirilmiş ve performansları karşılaştırılmıştır.

Anahtar Kelimeler

• Araç sınıflandırma
• Akıllı trafik yönetimi
• Yapay Sinir Ağları
• Destek Vektör Makineleri ve Adaboost
• İkili imge bölge özellikleri.

Evaluation of Vehicle Classification with Artificial Neural Networks, Support Vector Machines, and AdaBoost Algorithm

Abstract

It is vital for traffic management and information systems to obtain information about the traffic using various sensors and cameras in order to provide the traffic flow correctly. In this context, video cameras have been widely and actively used in traffic surveillance and control in recent years. In this study, vehicles were classified into three categories according to their sizes. Training was carried out with Artificial Neural Networks, Support Vector Machines and Adaboost classifiers on the traffic video images we created and their performances were compared.

Keywords

• Vehicle classification
• Intelligent traffic management
• Neural Networks
• Support Vector Machines and Adaboost
• Binary image region properties

References

1. Kul, S., Eken, S., & Sayar, A. (2017). Distributed and collaborative real-time vehicle detection and classification over the video streams. International Journal of Advanced Robotic Systems. https://doi.org/10.1177/1729881417720782.
2. Şentaş, A., Tashiev, İ., Küçükayvaz, F. et al. Performance evaluation of support vector machine and convolutional neural network algorithms in real-time vehicle type and color classification. Evol. Intel. 13, 83–91 (2020). https://doi.org/10.1007/s12065-018-0167-z.
3. C. Gou, K. Wang, Y. Yao, Z. Li, “Vehicle License Plate Recognition Based on Extremal Regions and Restricted Boltzmann Machines,” IEEE Transactions on Intelligent Transportation Systems, 17(4): 1096-1107, 2016.
4. N. Miller, M. A. Thomas, J. A. Eichel, A. Mishra, “A Hidden Markov Model for Vehicle Detection and Counting,” IEEE 12th Conference on Computer and Robot Vision 269 – 276, 2015.
5. Shrikant Fulari, Ajitha Thankappan, Lelitha Vanajakshi & Shankar Subramanian (2019) Traffic flow estimation at error prone locations using dynamic traffic flow modeling, Transportation Letters, 11:1, 43-53, DOI: 10.1080/19427867.2016.1271761S. C. Subramanian, M. Panda, “Performance Comparison of Filtering Techniques for Real Time Traffic Density Estimation under Indian Urban Traffic Scenario,” IEEE 18th International Conference on Intelligent Transportation Systems, pp. 1442-1447, 2015.
6. H. Im, B.Hong, S. Jeon, J. Hong, “Bigdata analytics on CCTV images for collecting traffic information,” 2016 International Conference on Big Data and Smart Computing, pp. 525-528, 2016.
7. R. Marikhu, J. Moonrinta, M. Ekpanyapong, M. Dailey, S. Siddhichai, “Police Eyes: Real world automated detection of traffic violations,” 10th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, pp. 1-6, 2013.
8. H.C. Karaimer, I. Cinaroglu, Y. Bastanlar, “Combining Shape-Based and Gradient-Based Classifiers for Vehicle Classification,” IEEE 18th International Conference on Intelligent Transportation Systems, pp. 800-805, 2015.

9. S. Messelodi, C.M. Modena, M. Zanin, “A computer vision system for the detection and classification of vehicles at urban road intersections”, Pattern Analysis & Applications, 8(1-2):17-31, 2005.
10. N. Buch, J. Orwell, S.A. Velastin, “Detection and classification of vehicles for urban traffic scenes”, 5th International Conference on Visual Information Engineering, pp.182-187, 2008.
11. B. Morris, M. Trivedi, “Robust classification and tracking of vehicles in traffic video streams”, In Intelligent Transportation Systems Conference. ITSC '06. IEEE, pp.1078-1083, 2006.
12. B. Morris, M. Trivedi, “Improved vehicle classification in long traffic video by cooperating tracker and classifier modules”, In AVSS '06: Proceedings of the IEEE International Conference on Video and Signal Based Surveillance, page 9, Washington, DC, USA. IEEE Computer Society, 2006.
13. T. Gandhi, M.M. Trivedi, “Video based surround vehicle detection, classification and logging from moving platforms: Issues and approaches”, In Intelligent Vehicles Symposium, pp. 1067-1071, 2007.
14. D. Demet, B.A. Gözde, “Hareket Halindeki Araçların Sınıflandırılması”, 21st Signal Processing and Communications Applications Conference (SIU), pp. 1-4, 2013.
15. S.M. Ghada, “Vehicle Type Classification with Geometric and Appearance Attributes”, World Academy of Science, Engineering and Technology International Journal of Civil, Structural, Construction and Architectural Engineering 8(3): 273-278, 2014.
16. Z. Dong, Y. Wu, M. Pei, Y. Jia, “Vehicle Type Classification Using Semi-Supervised Convolutional Neural Network”, IEEE Transactions on Intelligent Transportation Systems, 16(4): 2247 – 2256, 2015.
17. S. Kul, S. Eken, A Sayar, “Video Gözetleme Sistemlerinde Terk Edilmiş Nesne Saptamak için Servis Odaklı Uyarı Sistemi,” 23nd Signal Processing and Communications Applications Conference, 911-914, 2015.
18. A. Sobral, A. Vacavant “A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos,” ComputerVision and Image Understanding ELSEVIER, vol. 122, pp. 4–21, May 2014.
19. BMC veri seti, http://bmc.iut-auvergne.com/?page_id=24 Changedetection veri setleri, http://changedetection.net/
20. S. Kul, S. Eken, A. Sayar, “"Evaluation of Real-time Performance for BGSLibrary Algorithms: A Case Study on Traffic Surveillance Video,” IEEE 6th International Conference on IT Convergence and Security, 2016.
21. Z. Zivkovic, “Improved Adaptive Gaussian Mixture Model for Background Subtraction”, Proceedings of the 17th International Conference on (ICPR'04), pp. 28-31, 2004.
22. D.G. Lowe, “Distinctive image features from scale-invariant keypoints,” International journal of computer vision, 60, 91-110, 2004.
23. H. Bay, T. Tuytelaars, L. Van Gool, “Surf: Speeded up robust features”, ECCV, Springer, 404-417, 2006.