Road Type Identification Ahead of the Tire Using D-CNN and Reflected Ultrasonic Signals


Every land moving object accelerates or decelerates based on the fictional coefficient of the road surface. It has been known that this coefficient on the road is determined by the type of road surface. In this work, we propose a simplistic, machine-learning based solution to estimate the road type using the reflected ultrasonic signals paired with ultrasonic transmitter and receiver. Since the reflected signal contains the material information of the surface due to the difference in the surface roughness and acoustic impedance, different characteristics can be observed for each frequency of the reflected signal. To exploit such characteristics, the signals are transformed into the frequency domain using short-time Fourier transform. In addition, a deep convolutional neural network is applied as the road identifier due to its well-known representational power. In order to verify the aforementioned ideas, the ample database consisting of eight types of road surfaces are obtained with the ultrasonic sensors. And then, the database is used to train the model, as well as to evaluate the accuracy of the trained model. It can be seen that the proposed method makes it easier and more accurate to identify the type of road surface than the conventional methods.

This is a preview of subscription content, access via your institution.


F l :

feature of l-th layer

b :

bias of convolutional layer

w :

weight of convolutional layer

B :

bias of classifier layer

W :

weight of classifier layer

C in :

number of input channel


  1. Alonso, J., Lopez, J. M., Pavón, I., Recuero, M., Asensio, C., Arcas, G. and Bravo, A. (2014). On-board wet road surface identification using tyre/road noise and support vector machines. Applied Acoustics, 76, 407–415.

    Article  Google Scholar 

  2. Arandjelovic, R. and Zisserman, A. (2017). Look, listen and learn. Proc. IEEE Int. Conf. Computer Vision. Venice, Italy.

  3. Breiman, L. (2017). Classification and regression trees. Routledge. London, UK.

  4. Burckhardt, M. (1993). Fahrwerktechnik: Radschlupf-Regelsysteme: Reifenverhalten, Zeitablaeufe, Messung des Drehzustands der Raeder, Anti-Blockier-System (ABS), Theorie Hydraulikkreislaeufe, Antriebs-Schlupf-Regelung (ASR), Theorie Hydraulikkreislaeufe, elektronische Regeleinheiten, Leistungsgrenzen, ausgefuehrte Anti-Blockier-Systeme und Antriebs-Schlupf-Regelungen. Vogel.

  5. Carullo, A. and Parvis, M. (2001). An ultrasonic sensor for distance measurement in automotive applications. IEEE Sensors J. 1,2, 143.

    Article  Google Scholar 

  6. Cristianini, N. and Shawe-Taylor, J. (2000). An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press. Cambridge, UK.

    Google Scholar 

  7. Dahiya, R.S., Metta, G., Valle, M. and Sandini, G., 2010. Tactile sensing—from humans to humanoids. IEEE Trans. Robotics 26,1, 1–20.

    Article  Google Scholar 

  8. Elunai, R., Chandran, V. and Gallagher, E. (2011). Asphalt concrete surfaces macrotexture determination from still images. IEEE Trans. Intelligent Transportation Systems, 12,3, 857–869.

    Article  Google Scholar 

  9. Farnioli, E., Gabiccini, M. and Bicchi, A. (2016). Toward whole-body loco-manipulation: Experimental results on multi-contact interaction with the Walk-Man robot. 2016 IEEE/RSJ Int. Conf., Intelligent Robots and Systems (IROS). Daejeon, Korea.

  10. Gailius, D. and Jačėnas, S. (2007). Ice detection on a road by analyzing tire to road friction ultrasonic noise. Ultragarsas” Ultrasound” 62,2, 17–20.

    Google Scholar 

  11. Goodfellow, I., Bengio, Y., Courville, A. and Bengio, Y. (2016). Deep learning (1st ed.). MIT press. Cambridge, UK.

    Google Scholar 

  12. Han, K., Hwang, Y., Lee, E. and Choi, S. (2016). Robust estimation of maximum tire-road friction coefficient considering road surface irregularity. Int. J. Automotive Technology 17,3, 415–425.

    Article  Google Scholar 

  13. Ioffe, S. and Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv: 1502.03167.

  14. Kim, M. H. and Choi, S. B. (2016). Road surface height estimation for preview system using ultrasonic sensor array. FISITA World Automotive Cong. Busan, Korea.

  15. Kinsler, L. E., Frey, A. R., Coppens, A. B., and Sanders, J. V. (1999). Fundamentals of acoustics, 4th edn, 560. ISBN 2510-471-84789-5. Wiley-VCH.

  16. Kongrattanaprasert, W., Nomura, H., Kamakura, T., and Ueda, K. (2009). Detection of road surface conditions using tire noise from vehicles. IEEJ Trans. Industry Applications, 129, 761–767.

    Article  Google Scholar 

  17. Krizhevsky, A., Sutskever, I. and Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 1097–1105.

  18. LeCun, Y., Bengio, Y. and Hinton, G. (2015). Deep learning. nature 521,7553, 436–444.

    Article  Google Scholar 

  19. Li, X., Izawa, D., Minami, M., Matsuno, T. and Yanou, A. (2016). Dynamical model of humanoid considering slipping with nonlinear floor friction and internal force during freefall motion. 2016 IEEE/SICE Int. Symp. System Integration (SII). Sapporo, Japan.

  20. Masino, J., Pinay, J., Reischl, M. and Gauterin, F. (2017). Road surface prediction from acoustical measurements in the tire cavity using support vector machine. Applied Acoustics, 125, 41–48.

    Article  Google Scholar 

  21. Nakashima, S., Aramaki, S., Kitazono, Y., Mu, S., Tanaka, K., and Serikawa, S. (2016). Application of ultrasonic sensors in road surface condition distinction methods. Sensors 16,10, 1678.

    Article  Google Scholar 

  22. Nyquist, H. (1928). Certain topics in telegraph transmission theory. Trans. American Institute of Electrical Engineers, 47,2, 617–644.

    Article  Google Scholar 

  23. Omer, R. and Fu, L. (2010). An automatic image recognition system for winter road surface condition classification. 13th Int. IEEE Conf. Intelligent Transportation Systems (ITSC). Funchal, Madeira Island, Portugal.

  24. Persson, B. N. (2013). Sliding friction: physical principles and applications. Springer Science & Business Media.

  25. Raj, A., Krishna, D. and Shantanu, K. (2012). Vision based road surface detection for automotive systems. 2012 Int. Conf. Applied Electronics (AE). Pilsen, Czech Republic.

  26. Rajamani, R., Phanomchoeng, G., Piyabongkarn, D. and Lew, J. Y. (2012). Algorithms for real-time estimation of individual wheel tire-road friction coefficients. IEEE/ASME Trans. Mechatronics, 17,6, 1183–1195.

    Article  Google Scholar 

  27. Rajamani, R., Piyabongkarn, N., Lew, J., Yi, K. and Phanomchoeng, G. (2010). Tire-road friction-coefficient estimation. IEEE Control Systems Magazine 30,4, 54–69.

    MathSciNet  Article  Google Scholar 

  28. Xu, B., Wang, N., Chen, T., and Li, M. (2015). Empirical evaluation of rectified activations in convolutional network. arXiv:1505.00853.

Download references


This research was supported by the grant (20TLRP-C152478-02) from Transportation & Logistics Research Program funded by Ministry of Land, Infrastructure and Transport (MOLIT) of Korea government and Korea Agency for Infrastructure Technology Advancement(KAIA); and the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIP) (No. 2020R1A2B5B01001531).

Author information



Corresponding author

Correspondence to Seibum Choi.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Kim, MH., Park, J. & Choi, S. Road Type Identification Ahead of the Tire Using D-CNN and Reflected Ultrasonic Signals. Int.J Automot. Technol. 22, 47–54 (2021).

Download citation

Key Words

  • Ultrasonic sensor
  • Road type identification
  • Friction coefficient
  • Short-time Fourier transform
  • Machine-learning
  • Deep convolutional neural network