Advertisement

Cepstrum-Based Road Surface Recognition Using Long-Range Automotive Radar

  • Sudeepini DarapuEmail author
  • S. M. Renuka Devi
  • Srinivasarao Katuri
Conference paper
Part of the Lecture Notes on Data Engineering and Communications Technologies book series (LNDECT, volume 28)

Abstract

During driving, a sudden change in the road surface results in imbalance of vehicle due to wheel slip which leads to accidents. Thus, a need arises for an automotive system to recognize the type of road surface ahead and alert the driver to accordingly change the speed of the vehicle. This paper proposes a technique for road surface recognition using 77 GHz frequency-modulating continuous wave (FMCW) long-range automotive radar. The cepstral coefficients calculated from the backscattered signal are analyzed, using classifiers like decision tree and SVM. This technique recognizes five different road surfaces, i.e., dry concrete, dry asphalt, slush, sand, and bushes. To validate the accuracy and classification rate, field testing is conducted at Kondapur (Telangana) and the system has achieved prediction percentage of above 90%.

Keywords

Automotive systems Radar backscattering Signal processing Cepstral coefficients Machine learning Road surface detection 

Notes

Acknowledgements

I sincerely thank INEDA SYSTEMS Pvt. Ltd (www.inedasystems.com) and express my gratitude to the officials for their guidance and encouragement in carrying out this project.

References

  1. 1.
    Alessandretti G, Broggi A, Cerri P (2007) Vehicle and guard detection using radar and vision data fusion. IEEE Trans Intell Transp Syst 8(1):95–105CrossRefGoogle Scholar
  2. 2.
    Eidehall A, Pohl J, Gustafsson F, Ekmark J (2007) Toward autonomous collision avoidance by steering. IEEE Trans Intell Transp Syst 8(1):84–94CrossRefGoogle Scholar
  3. 3.
    Ma B, Lakshmanan S, Hero AO III (2000) Simultaneous detection of lane and pavement boundaries using model-based multisensor fusion. IEEE Trans Intell Transp Syst 1(3):135–147CrossRefGoogle Scholar
  4. 4.
    Abou-Jaoude R (2003) ACC radar sensor technology, test requirements, andtestsolutions. IEEE Trans Intell Transp Syst 4(3):115–122CrossRefGoogle Scholar
  5. 5.
    Andersson M, Bruzelius F, Casselgren J, Gafvert M, Hjort M, Hultén J, Habring F, Klomp M, Olsson G, Sjodahl M, Svendenius J, Woxneryd S, Walivaara B (2007) Road friction estimation. IVSS project report. Saab Automobile AB, Trollhattan, SwedenGoogle Scholar
  6. 6.
    Bystrov A, Abbas M, Hoare E, Tran T-Y, Clarke N, Gashinova M, Cherniakov M (2014) Remote road surface identification using radar and ultrasonic sensors. In: Proceedings IEEE European radar conference, pp 185–188Google Scholar
  7. 7.
    Hakli J, Saily J, Koivisto P, Huhtinen I, Dufva T, Rautiainen A, Toivanen H, Nummila K (2013) Road surface condition detection using 24 GHz automotive radar technology, radar symposium (IRS). In: Proceedings IEEE applied electronics conference, vol 2, no 19–21, pp 702–707Google Scholar
  8. 8.
    Viikari V, Varpula T, Kantanen M (2009) Road-condition recognition using 24-GHz automotive radar. IEEE Trans Intell Transp Syst 10(4):639–648CrossRefGoogle Scholar
  9. 9.
    Raj A, Krishna D, Hari Priya R, Kumar S, Niranjani Devi S (2012) Vision based road surface detection for automotive systems. In: Proceedings IEEE applied electronics conference, pp 223–228Google Scholar
  10. 10.
    Kees R, Detlefsen J (1994) Road surface classification by using a polarimetric coherent radar module at millimetre waves. In: Proceedings. IEEE national telesystems conference, pp 95–98Google Scholar
  11. 11.
    Kim HS (2001) Road surface sensing device. Korean patent KR 2001:047234Google Scholar
  12. 12.
    Childers Donald G, Skinner David P, Kemerait RC (1977) Cepstrum: a guide to processing. Proc IEEE 65(10):1–16CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Sudeepini Darapu
    • 1
    Email author
  • S. M. Renuka Devi
    • 1
  • Srinivasarao Katuri
    • 2
  1. 1.G Narayanamma Institute of Technology and ScienceHyderabadIndia
  2. 2.Ineda Systems Pvt. Ltd.KothagudaIndia

Personalised recommendations