Abstract
The performance of emergency vehicle prioritization system is determined by its efficiency in reducing the response time of the vehicles detected. Emergency vehicle (EV) detection is possible through various methods, but the use of the acoustic signal in detection method is found to have an edge over the others. The present study reviewed various acoustic-based EV detection systems and their merits, which would provide a better understanding of techniques to be used for IoT system design with limited power and computational resources. It is found that EV siren detection accuracy decreases in low SNR conditions and is affected by the choice of features used in neural network (NN). It is observed that neural network-based system performance is better compared to other methods. Also, it is observed that network parameters of long short-term memory recurrent NN architecture are almost 150 time less as compared to other NN for similar detection accuracy. More research on acoustic-based systems is required to be done, for achieving high detection accuracy of 99% in low SNR condition of − 15 dB or below. Developing a universally deployable generalized model of a neural network in detecting EV siren and designing a system of low power with low computation requirements are the main goals which are analyzed in the present study. In detecting EV by acoustic-based method, the effects of noise, various signal domain features, environment, relative movement of source and detector, etc. have been studied here. The physical characteristics of the siren signal are analyzed and how these can be used in emergency vehicle detection systems are discussed. The present study analyzes the acoustic-based EV detection system into three major categories, namely digital signal processing-based systems, neural network-based systems, and statistical methods-based systems. For all the methods discussed in these categories, the research gaps are identified to indicate future research directions. Further, major challenges and future scope in the acoustic-based EV detection system are presented. Also, the new direction to increase the accuracy and decrease the latency of the EV detection system is discussed.
Similar content being viewed by others
Availability of Data and Materials
The datasets, figure used during and/or analyzed during the current study are available from the open source research paper of author available.
Abbreviations
- ASR:
-
Automatic speech recognition
- PCEN:
-
Per-channel energy normalization
- MAP:
-
Maximum a posteriori
- CNN:
-
Convolutional neural networks
- K-NN:
-
K-nearest neighbor
- ANN:
-
Artificial neural network
- BRANN:
-
Bayesian regularized artificial neural network.
- GMM:
-
Gaussian mixture models
- SVM:
-
Support vector machine
- NN:
-
Neural network
- FFT:
-
Fast Fourier transform
- MDF:
-
Module difference function
- ADSR:
-
Attack–decay–sustain–release
- µPa:
-
Micro-Pascal
- SED:
-
Sound event detection
- ILD:
-
Interaural level difference
- ITD:
-
Interaural time difference
- EVP:
-
Emergency vehicle priority
- AV:
-
Autonomous vehicle
- EV:
-
Emergency vehicle
- LCS:
-
Longest common subsequence
- LSTM-RNN:
-
Long short-term memory recurrent neural network
- MFCC:
-
Mel-frequency cepstral coefficients
References
Angela DP (2013) Emergency vehicle siren noise effectiveness. Master Thesis. University of Windsor Ontario, Canada.
Angione F, Novak C, Imeson C, Lehman A, Merwin B, Pagliarella T, Samardzic N, D’Angela P, Ule H (2016) Study of a low-frequency emergency siren in comparison to traditional siren technology. Proc Mtgs Acoust 29(1):030008
Aviva Atkins February (2020) Speech enhancement based on adaptive line enhancer. Master Thesis. Israel Institute of Technology
Bubar A, Eckstein B, Ell A, Hilts E, Martin S, Powell T, Miguel Cruz A, Rios Rincon A (2020) Emergency siren detection technology and hearing impairment: a systematized literature review. Disabil Rehabil 18:295
Carmel D, Yeshurun A, Moshe Y (2017) Detection of alarm sounds in noisy environments. In: IEEE 25th European Signal Processing Conference (EUSIPCO), pp 1839–1843
Chavdar M, Gerazov B, Ivanovski Z, Kartalov T (2020) Towards a system for automatic traffic sound event detection. In: IEEE 28th Telecommunications Forum (TELFOR), pp 1–4
De Lorenzo RA, Eilers MA (1991) Lights and siren: a review of emergency vehicle warning systems. Ann Emerg Med 20(12):1331–1335
Dobre RA, Negrescu C, Stanomir D (2017) Improved low computational method for siren detection. In: IEEE 23rd International Symposium for Design and Technology in Electronic Packaging (SIITME), pp 318–323
Dubin S, Zietz S (2004) Personal alerting technology for people with hearing difficulty: pilot study. In: IEEE Proceedings of the 30th Annual Northeast Bioengineering Conference, pp 202–203
Ebizuka Y, Kato S, Itami M 2019 Detecting approach of emergency vehicles using siren sound processing. In: IEEE Intelligent Transportation Systems Conference (ITSC), pp 4431–4436
Fatimah, B, Preethi A, Hrushikesh V, Singh A and Kotion H.R 2020 An automatic siren detection algorithm using Fourier decomposition method and MFCC. In: IEEE 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT), pp 1–6
Howard CQ, Maddern AJ, Privopoulos EP (2011) Acoustic characteristics for effective ambulance sirens. Acoust Aust 39(2):43–53
Ick C, McFee B 2021 June. Sound event detection in urban audio with single and multi-rate PCEN. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 880–884
Jonnadula EP, Khilar PM (2021) Comparison of various techniques for emergency vehicle detection using audio processing. In: Gupta BB (ed) Cloud security. CRC Press, Boca Raton, pp 64–75
Kiran SL, Supriya M (2017) Siren detection and driver assistance using modified minimum mean square error method. In: IEEE International Conference on Smart Technologies for Smart Nation (SmartTechCon), pp 127–131
Lilja AP, Raboshchuk G, Nadeu C (2017) A neural network approach for automatic detection of acoustic alarms. In: Biosignals, pp 84–91
Marchegiani L, Posner I (2017) Leveraging the urban soundscape: Auditory perception for smart vehicles. In: IEEE International Conference on Robotics and Automation (ICRA), pp 6547–6554
Marchegiani L, Newman P (2022) listening for sirens: Locating and classifying acoustic alarms in city scenes. IEEE Trans Intell Transp Syst 23(10):17087–17096
Mehendale N, Patel R, Mange S, Mulik S (2021) Review of emergency vehicle priority systems. SSRN. https://doi.org/10.2139/ssrn.3859424
Mesaros A, Heittola T, Virtanen T, Plumbley MD (2021) Sound event detection: a tutorial. IEEE Signal Process Mag 38(5):67–83
Meucci F, Pierucci L, Del Re E. Lastrucci L and Desii P (2008) A real-time siren detector to improve safety of guide in traffic environment. In: IEEE 16th European Signal Processing Conference, pp 1–5
Miyazakia T, Kitazonoa Y, Shimakawab M (2013) Ambulance siren detector using FFT on dsPIC. In: Proceedings of the 1st IEEE/IIAE International Conference on Intelligent Systems and Image Processing, pp 266–269
Montoro L, Drastrup JK, Johan M (2017) Automatic detection of emergency cars. Master Thesis, Aalborg University.
Müller M (2015) Music Representations, Fundamentals of music processing: Audio, analysis, algorithms, applications. Springer (Audio Representation)
Padhy S, Tiwari J, Rathore S, Kumar N (2019) Emergency signal classification for the hearing impaired using multi-channel convolutional neural network architecture. In: IEEE Conference on Information and Communication Technology, pp 1–6
Palecek J, Cerny M (2016) Emergency horn detection using embedded systems. In: IEEE 14th International Symposium on Applied Machine Intelligence and Informatics (SAMI), pp 257–261
Park SW, Trevino J (2013) Automatic detection of emergency vehicles for hearing impaired drivers. Texas a&m Univ-Kingsv EE/CS Dep MSC 192:637–665
Rane D, Shirodkar P, Panigrahi T, Mini S (2019) Detection of ambulance siren in traffic. In: IEEE International Conference on Wireless Communications Signal Processing and Networking (WiSPNET), pp 401–405
Raval P, Christopher J (2021) Parameter tuning for wavelet-based sound event detection using neural networks. International conference on computational intelligence in music, sound, art and design (Part of EvoStar). Springer, Cham, pp 235–247
Rudzyn B, Kadous W, Sammut C (2007) Real time robot audition system incorporating both 3D sound source localization and voice characterization. In: Proceedings of IEEE International Conference on Robotics and Automation, pp 4733–4738
Schröder J, Goetze S, Grützmacher V, Anemüller J (2013) Automatic acoustic siren detection in traffic noise by part-based models. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp 493–497
Scola CF, Ortega MDB (2010) Direction of arrival estimation: a two microphones approach. Master Thesis. Blekinge Institute of Technology.
Shabtai NR, Tzirke E (2019) Detecting the direction of emergency vehicle sirens with microphones. In: EAA Spatial Audio Signal Processing Symposium, pp 137–142
Srinivasamurthy KM, Angadi VJ, Kubrin SP, Matteppanavar S, Kumar PM, Rudraswamy B (2018) Evidence of enhanced ferromagnetic nature and hyperfine interaction studies of Ce-Sm doped Co-Ni ferrite nanoparticles for microphone applications. Ceram Int 44(15):18878–18885
Sun H, Liu X, Xu K, Miao J, Luo Q (2021) Emergency vehicles audio detection and localization in autonomous driving. arXiv preprint arXiv:2109.14797
Supreeth H V, Rao S, Chethan KS, Purushotham U (2020) Identification of Ambulance Siren sound and Analysis of the signal using statistical method. In: IEEE International Conference on Intelligent Engineering and Management (ICIEM), pp 198–202
The Goertzel Algorithm (2022). https://courses.cs.washington.edu/courses/cse466/12au/calendar/Goertzel-EETimes.pdf. Accessed 06 Jan 2022
The Human Ear Hearing, Sound Intensity and Loudness Levels (2022). https://courses.physics.illinois.edu/phys406/sp2017/Lecture_Notes/P406POM_Lecture_Notes/P406POM_Lect5.pdf. Accessed 03 March 2022
TranYVT, Tsai YC, Ho W (2018) Detection of ambulance and fire truck siren sounds using neural networks. In: Proceedings of 51st Research World International Conference, pp 9–14
Tran VT, Tsai WH (2020) Acoustic-based emergency vehicle detection using convolutional neural networks. IEEE Access 8:75702–75713
Wang Y, Getreuer P, Hughes T, Lyon RF, Saurous RA (2017) Trainable frontend for robust and far-field keyword spotting. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 5670–5674
‘What are the Different Sounds a Police Siren Makes (2022). https://www.extremetacticaldynamics.com/blog/what-are-the-different-sounds-a-policesiren-makes/. Accessed 10 April 2022
When to Use the Goertzel Algorithm Instead of the FFT? (2022).https://medium.com/geekculture/the-great-unknown-the-goertzel-algorithm-492681f30866. Accessed 02 Feb 2022
Funding
No funding received.
Author information
Authors and Affiliations
Contributions
Conceptualization and writing original draft: KC; Supervision, review and editing: DN. Authors reviewed the final manuscript. The author(s) read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of Interest
The authors declare that they have no competing interests.
Ethical Approval and Consent to Participate
Not applicable.
Consent for Publication
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Choudhury, K., Nandi, D. Review of Emergency Vehicle Detection Techniques by Acoustic Signals. Trans Indian Natl. Acad. Eng. 8, 535–550 (2023). https://doi.org/10.1007/s41403-023-00424-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41403-023-00424-9