UPM Institutional Repository

Acoustic feature analysis for wet and dry road surface classification using two-stream CNN


Citation

Bahrami, Siavash and Doraisamy, Shyamala and Azman, Azreen and Nasharuddin, Nurul Amelina and Shigang, Yue (2020) Acoustic feature analysis for wet and dry road surface classification using two-stream CNN. In: CSAI 2020: 2020 4th International Conference on Computer Science and Artificial Intelligence, 11-13 Dec. 2020, Zhuhai China. (pp. 194-200).

Abstract

Road surface wetness affects road safety and is one of the main reasons for weather-related accidents. Study on road surface classification is not only vital for future driverless vehicles but also important to the development of current vehicle active safety systems. In recent years, studies on road surface wetness classification using acoustic signals have been on the rise. Detection of road surface wetness from acoustic signals involve analysis of signal changes over time and frequency-domain caused by interaction of the tyre and the wet road surface to determine the suitable features. In this paper, two single stream CNN architectures have been investigated. The first architecture uses MFCCs and the other uses temporal and spectral features as the input for road surface wetness detection. A two-stream CNN architecture that merges the MFCCs and spectral feature sets by concatenating the outputs of the two streams is proposed for further improving classification performance of road surface wetness detection. Acoustic signals of wet and dry road surface conditions were recorded with two microphones instrumented on two different cars in a controlled environment. Experimentation and comparative performance evaluations against single stream architectures and the two-stream architecture were performed. Results shows that the accuracy performance of the proposed two-stream CNN architecture is significantly higher compared to single stream CNN for road surface wetness detection.


Download File

[img] Text
Acoustic Feature Analysis for Wet and Dry Road Surface.pdf

Download (3MB)

Additional Metadata

Item Type: Conference or Workshop Item (Paper)
Divisions: Faculty of Computer Science and Information Technology
DOI Number: https://doi.org/10.1145/3445815.3445847
Publisher: Association for Computing Machinery
Keywords: Acoustic signal processing; Artificial neural networks; Feature selection; Intelligent transportation systems; Vehicle safety
Depositing User: Nurul Ainie Mokhtar
Date Deposited: 18 Apr 2021 07:34
Last Modified: 21 Apr 2021 02:33
Altmetrics: http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.1145/3445815.3445847
URI: http://psasir.upm.edu.my/id/eprint/85375
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item