AKUSTİK TEMELLİ ARAÇ TRAFİK YOĞUNLUĞU KESTİRİMİ

Year 2019, Volume: 24 Issue: 1, 429 - 440, 30.04.2019

Fikret Öztürk Ali Köksal Hocaoğlu

https://doi.org/10.17482/uumfd.454100

Abstract

Bu çalışmada, araçların oluşturduğu akustik gürültü sinyalinden trafik yoğunluğunun kestirimi yapılmıştır. Akustik gürültü sinyali, motor, hava türbülans, tekerlek, egzoz ve korna gürültü bileşenlerinden oluşmaktadır. Trafik yoğunluk durumuna göre bu bileşenlerin bulunma ağırlıkları değişmektedir. Örneğin trafiğin yoğun olduğu zaman motor ve korna gürültüsü yoğun, trafiğin akışkan olduğu zaman hava türbülansı ve tekerlek gürültüsü daha yoğundur. Akustik gürültü sinyalindeki bu farklılıktan faydalanılarak trafik yoğunluğu yoğun, orta ve serbest akış olmak üzere üç sınıfa ayrılmıştır. Önerilen yöntem Mel-frekans kepstrum katsayıları (MFCC) (Mel-Frequency Cepstral Coefficients) özniteliklerini ve sınıflandırıcı olarak k-en yakın komşu yöntemini kullanmaktadır. E5 karayolunda özgün bir veri seti üretilmiş ve önerilen yöntem bu veri seti kullanılarak test edilmiştir. MFCC özniteliklerine ilişkin parametrelerin trafik yoğunluğu tespitine etkisi incelenmiştir ve en önemli iki parametrenin kepstrum katsayı sayısı ve pencere süresi olduğu görülmüştür. Hava durumunu dikkate alarak sınıflandırıcı eğitmenin performansı iyileştirdiği gösterilmiştir. Bu iyileştirmenin sebebi irdelenmiş ve iki boyutlu öznitelik uzayında gösterilmiştir. E5 karayolunda trafik yoğunluğu yağışlı havalarda %90, yağış olmayan durumlarda ise %82 doğrulukla tespit edilmiştir.

Keywords

Trafik yoğunluk kestirimi, karayolu araçları, akustik sinyal işleme, örüntü tanıma

Acoustic Based Vehicular Traffic Density Estimation

Abstract

In this study, traffic density is estimated using
acoustic noise signals formed by the land vehicles. The acoustic noise signals
formed by the vehicles consist of engine noise, air turbulence, the noise of
the wheels touching the floor, exhaust noise and the horn noise. The contributions
of these different types of noise change according to the traffic density. For
example, engine noise and horn noise are dense when the traffic is busy and
when the traffic is free-flow, air turbulence and wheel noise are more dense.
By taking advantage of this change in the acoustic noise signal, the traffic
density is categorized into three classes; busy, normal and free-flow. The
proposed method use Mel-Frequency Cepstral Coefficients (MFCC) to extract
features and the k-Nearest Neighbor Rule to classify. A data set was formed on
E5 roadway and it was used to evaluate the proposed method. The effect of MFCC attributes
on the traffic density estimation was investigated and the number of cepstral
coefficients and the duration of windows are found to be the most important
ones. It is shown that the performance of the traffic density estimation is
increased if the weather conditions are considered when training the
classifiers. The reason behind this improvement is investigated and shown on a
two dimensional feature space. The traffic density in the E5 roadway is
determined by %90 and %82 accuracies when raining and not raining,
respectively. 

Keywords

Traffic density estimation, land vehicles, acoustic signal processing, pattern recognition

References

• 1. Aras, S. ve Gangal, A. (2017), Comparison of different features derived from mel frequency cepstrum coefficients for classification of single channel lung sounds, 40th International Conference on Telecommunications and Signal Processing Barcelona, 2017, pp. 346-349. doi: 10.1109/TSP.2017.8076002
• 2. Beymer, D., Mclauchlan, P., Coifman, B., ve Malik J., (1997), A real-time computer vision system for measuring traffic parameters, IEEE Conference on Computer Vision and Pattern Recognition, San Juan, Puerto Rico, USA, pp. 495–501. doi: 10.1109/CVPR.1997.609371
• 3. Bolat, B., Küçük, Ü. Yıldırım, T. (2004), Aktif Öğrenen PNN ile Konuşma/Müzik Sınıflandırma, Akıllı Sistemlerde Yenilikler ve Uygulamaları Sempozyumu, İstanbul, 187-189.
• 4. Borkar, P. Malik, L. G. (2013a), Cumulative Acoustic Signal Based Traffic Density State Estimation, Third International Conference on Advances in Computing and Communications, Cochin, India, 2013, pp. 169-172. doi: 10.1109/ICACC.2013.40
• 5. Borkar P., Malik L., (2013b), “Review on vehicular speed, density estimation and classification using acoustic signal”, International Journal for Traffic and Transport Engineering, 3 (3), 331-343. doi: 10.7708/ijtte.2013.3(3).08
• 6. Durukal, M. ve Hocaoğlu, A. K. (2015), Performance optimization on emotion recognition from speech, 23nd Signal Processing and Communications Applications Conference, Malatya, pp. 308-311. doi: 10.1109/SIU.2015.7129820
• 7. Eskidere, Ö., Ertaş, F. (2009), Mel Frekansı Kepstrum Katsayılarındaki Değişimlerin Konuşmacı Tanımaya Etkisi,Uludağ Üniversitesi Mühendislik-Mimarlık Fakültesi Dergisi, Cilt 14, sayı 2. doi: 10.17482/uujfe.11784
• 8. Eskridge R., Hunt J., (1979), “Highway modeling.Part I: Prediction of velocity and turbulence fields in the wake of vehicles”, Journal of Applied Meteorology, 18 (4), 387-400. doi: 10.1175/1520-0450(1979)018<0387:HMPIPO>2.0.CO;2
• 9. Gtü (2018), http://goo.gl/QFwkWY, Erişim Tarihi: 01.07.2018, Konu: GTU Traffic Density Data Set
• 10. Hanilçi, Ç. (2007), Konuşmacı Tanıma Yöntemlerinin Karşılaştırmalı Analizi, Yüksek lisans tezi, Uludağ Üniversitesi - Elektronik Mühendisliği Anabilim Dalı, BURSA.
• 11. Koch W., Koller J., Ulmke M., (2006), Ground target tracking and road map extraction, Transportation ISPRS Journal of Photogrammetry and Remote Sensing, 61 (3), 197-208. doi: 10.1016/j.isprsjprs.2006.09.013
• 12. Li, X., Porikli, F.M., (2004), A hidden markov model framework for traffic event detection using video features, in Int’l Conference on Image Processing, Singapore, vol. 5, pp. 2901–2904. doi: 10.1109/ICIP.2004.1421719
• 13. Sandberg U., (2001), “Tyre/road noise - myths and realities”, The International Congress and Exhibition on Noise Control Engineering, Hague, Netherlands, 35-56, 27-30 August
• 14. Sumithra, M.G., Devika, A.K. (2012), A Study on Feature Extraction Techniques for Text Independent Speaker Identification, International Conference on Computer Communication and Informatics, Coimbatore, India, 10-12, January. doi: 10.1109/ICCCI.2012.6158791
• 15. Tan, E. ve Chen, J., (2007), Vehicular traffic density estimation via statistical methods with automated state learning, Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, pp. 164–169, IEEE, London. doi: 10.1109/AVSS.2007.4425304
• 16. Tyagi, V., Kalyanaraman, S. ve Krishnapuram, R, (2012) Vehicular Traffic Density State Estimation Based on Cumulative Road Acoustics, IEEE Transactions on Intelligent Transportation Systems, vol. 13, no. 3, pp. 1156-1166. doi: 10.1109/TITS.2012.2190509
• 17. Vijay, R., Sharma, R., Chakrabarti, T. ve Gupta, R. (2015), Assessment of honking impact on traffic noise in urban traffic environment of Nagpur, India, Journal of Environmental Health Science and Engineering. doi:10.1186/s40201-015-0164-4
• 18. Wang, Q, Zheng, J, Xu, H., Xu,B. ve Chen, R. (2018), Roadside Magnetic Sensor System for Vehicle Detection in Urban Environments, IEEE Transactions on Intelligent Transportation Systems, vol. 19, no. 5, pp. 1365-1374. doi: 10.1109/TITS.2017.2723908
• 19. Xia, Y., Shi, X., Song, G. Geng, Q., Liu (2016), Towards improving quality of video-based vehicle counting method for traffic flow estimation, Signal Processing, vol. 120, pp. 672-681. doi: 10.1016/j.sigpro.2014.10.035.
• 20. Yang B., ve Lei, Y. (2015), Vehicle Detection and Classification for Low-Speed Congested Traffic With Anisotropic Magnetoresistive Sensor, IEEE Sensors Journal, vol. 15, no. 2, pp. 1132-1138. doi: 10.1109/JSEN.2014.2359014
• 21. Zhao, H, Liu, H., Zhao, K., Yang, Y. (2011), Robust Speech Feature Extraction Using the Hilbert Transform Spectrum Estimation Method, International Journal of Digital Content Technology and its Applications, Volume 5, Number 12. doi:10.4156/jdcta.vol5.issue12.11