Abstract
In this paper, we study the traffic event detection from audio signals. Real-life data are collected in a long tunnel, and audio samples are labeled in accordance with traffic events including tire friction sound, vehicle percussion sound and other background sounds. Efficient spectral features are proposed for the fast classification of audio events. In order to model the acoustic characters, deep neural network approach is adopted. Several state-of-the-art algorithms are used for comparison, including LSTM neural network and Gaussian mixture models with Mel frequency cepstral coefficients. A novel convolutional neural network architecture which processes the input audio data in an end-to-end fashion is adopted for our traffic event detection application. Furthermore, we use time delay estimation algorithms to locate the sound location when the incident happens in the long tunnel. By comparison with the state-of-the-art audio detection methods, our proposed efficient spectral features are proved to be more accurate and more efficient in the detection of audio events related to traffic incidents.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
E.M. Brockmann, B.W. Kwan, L.J. Tung, Audio detection of moving vehicles, in IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation (1997), vol. 4, pp. 1–4
Y. Bengio, Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157–166 (2002)
B.R. Chang, H.F. Tsai, C. Young, Intelligent data fusion system for predicting vehicle collision warning using vision/GPS sensing. Expert Syst. Appl. 37, 2439–2450 (2010)
S. Chu, W. Ding, P. Gao, C. Wang, The application of video traffic-incident detecting technology in highway tunnel safety monitoring, in International Conference on Electronic Information and Electrical Engineering, Changsha, Hunan, China (2012), pp. 1–4
A. Ewald, V. Willhoe, Laser scanners for obstacle detection in automotive applications, in Proceedings of the IEEE Intelligent Vehicles Symposium, Dearborn (MI), USA (2000), pp. 682–687
B. Feiten, S. Gunzel, Automatic indexing of a sound database using self-organizing neural nets. Comput. Music J. 18, 53–65 (1994)
X.S. Fu, J. Zhu, Video-based automatic incident detection of highway network monitoring system. Adv. Mater. Res. 181–182, 776–781 (2011)
M.C. Green, D. Murphy, Acoustic scene classification using spatial features, in Proceedings of the Detection and Classification of Acoustic Scenes and Events, Munich, Germany (2017), pp. 16–17
Y.C. Guo, K. Gong, N. Zhang, Sound source localization algorithm based on seven-microphone array and PHAT-GCC method, in International Conference on Advanced Control, Automation and Robotoics (2015), pp. 568–575
C. Harlow, Y. Wang, Automated accident detection system, in Proceedings of the Transportation Research Board 80th Annual Meeting (2001), pp. 90–93
H. Jallet, E. Cakir, T. Virtanen, Acoustic scene classification using convolutional recurrent neural networks, in The Detection and Classification of Acoustic Scenes and Events (DCASE) (2017), pp. 1–5
Y. Li, Research on the smoke characteristics of a fire in a long highway tunnel. Mod. Tunn. Technol. 4, 10–14 (2007)
A. Mittal, A. Jain, G.K. Agarwal, Audio-video based people counting and security framework for traffic crossings. J. VLSI Signal Process. 49, 377–391 (2007)
Y. Nooralahiyan, H.R. Kirby, D. McKeown, Vehicle classification by acoustic signature. Math. Comput. Model. 27(9–11), 205–14 (1998)
B. Song, H. Jiang, L. Zhao et al., A bimodal biometric verification system based on deep learning, in ACM Proceedings of the International Conference on Video and Image Processing (2017), pp. 89–93
B. Wei, J. Yue, Y. Rao et al., A deep learning framework for financial time series using stacked autoencoders and long-short term memory. PLoS ONE 12(7), e0180944 (2017)
Y. Xu, Q. Kong, W. Wang et al., Large-scale weakly supervised audio classification using gated convolutional neural network, in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2018), pp. 1–4
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This work was supported by National Key R&D Program of China (2017YFC0840200) and Science and Technology Innovation Project of Research Institute of Highway, Ministry of Transport (2018-E0021).
Rights and permissions
About this article
Cite this article
Zhang, X., Chen, Y., Liu, M. et al. Acoustic Traffic Event Detection in Long Tunnels Using Fast Binary Spectral Features. Circuits Syst Signal Process 39, 2994–3006 (2020). https://doi.org/10.1007/s00034-019-01294-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-019-01294-9