Movatterモバイル変換

[0]ホーム
URL:

Skip to main content
Springer Nature Link
Log in

Edge computing for driving safety: evaluating deep learning models for cost-effective sound event detection

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

This paper addresses road safety concerns by investigating low-cost solutions for sound event detection (SED) tailored to driving scenarios. While advanced technologies like deep learning hold promise for improving road safety, their practical implementation often involves expensive sensors and hardware. Distractions, a major cause of accidents, require effective detection and mitigation. This study concentrates on auditory distractions and utilizes SED with low-cost edge devices to identify and timestamp relevant audio events, providing valuable insights into the driving environment. We evaluate state-of-the-art deep learning models on various edge devices, including the 2023 DCASE baseline with convolutional recurrent neural networks (CRNN) and an adapted YOLO vision model for audio spectrograms. Our analysis spans different hardware options, including single-board computers (SBCs) and desktop equipment, offering guidance on cost-effective hardware selection for in-vehicle SED applications. This research aims to contribute to affordable SED solutions in the context of driving safety, with the ultimate goal of advancing road safety efforts worldwide.

This is a preview of subscription content,log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Data availability

No datasets were generated or analyzed during the current study.

Notes

References

  1. The sustainable development goals report 2022, July 2022. [Online]. Available:https://unstats.un.org/sdgs/report/2022/

  2. Vicente F, Huang Z, Xiong X, la Torre F, Zhang W, Levi D (2015) Driver gaze tracking and eyes off the road detection system. IEEE Trans Intell Transp Syst 16:2014–2027

    Article  Google Scholar 

  3. Li W, Huang J, Xie G, Karray F, Li R (2021) A survey on vision-based driver distraction analysis. J Syst Architect 121:102319

    Article  Google Scholar 

  4. Li W, Gkritza K, Albrecht C (2014) The culture of distracted driving: evidence from a public opinion survey in IOWA. Transp Res F: Traffic Psychol Behav 26:337–347

    Article  Google Scholar 

  5. Prat F, Planes M, Gras ME, Sullman MJ (2015) An observational study of driving distractions on urban roads Spain. Accid Anal Prevent 74:8–16

    Article  Google Scholar 

  6. Prat F, Gras ME, Planes M, Font-Mayolas S, Sullman MJ (2017) Driving distractions: an insight gained from roadside interviews on their prevalence and factors associated with driver distraction. Transp Res F: Traffic Psychol Behav 45:194–207

    Article  Google Scholar 

  7. Farmer CM, Braitman KA, Lund AK (2010) Cell phone use while driving and attributable crash risk. Traffic Inj Prev 11(5):466–470

    Article  Google Scholar 

  8. Castorena C, Cobos M, Lopez-Ballester J, Ferri FJ (2024) A safety-oriented framework for sound event detection in driving scenarios. Appl Acoust 215:109719

    Article  Google Scholar 

  9. Edwards S, Wundersitz LN, Australia S (2019) Distracted driving: prevalence and motivations. Accid Anal Prevent 54:99–107

    Google Scholar 

  10. Koppel S, Charlton J, Kopinathan C, Taranto D (2011) Are child occupants a significant source of driving distraction? Accid Anal Prevent 43(3):1236–1244

    Article  Google Scholar 

  11. Regan MA, Oviedo-Trespalacios O (2022) Driver distraction: mechanisms, evidence, prevention, and mitigation. In: The Vision Zero Handbook: Theory, Technology and Management for a Zero Casualty Policy. (pp 995–1056). Springer International Publishing, Cham

  12. Zou T, Guo H, Khaloei M, MacKenzie D, Boyle LN (2023) Examining the relationships between multimodal environments and multitasking driving behaviors. Transp Res Rec 2677(2):944–957

    Article  Google Scholar 

  13. Nagahama A, Tanaka K, Feliciani C, Cui G, Wada T (2022) Effects of urban landscape and soundscape on driving behavior. In: 2022 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA). (pp 84–88). IEEE

  14. Prohn MJ, Herbig B (2023) Potentially critical driving situations during “Blue-light" driving: a video analysis. West J Emerg Med 24(2):348

    Article  Google Scholar 

  15. Turpault N, Serizel R, Shah AP, Salamon J (2019) Sound event detection in domestic environments with weakly labeled data and soundscape synthesis. In: Workshop on Detection and Classification of Acoustic Scenes and Events

  16. Tarvainen A, Valpola H (2017) Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems. 30

  17. Venkatesh S, Moffat D, Miranda ER (2022) You only hear once: a YOLO-like algorithm for audio segmentation and sound event detection. Appl Sci 12:3293

    Article  Google Scholar 

  18. Bai J, Lu, F and Zhang K. “ONNX: Open neural network exchange GitHub.” [Online]. Available:https://github.com/onnx/onnx

  19. Ahn H, Chen T, Alnaasan N, Shafi A, Abduljabbar M, Subramoni H, Panda DK (2023) Performance characterization of using quantization for dnn inference on edge devices. In2023 IEEE 7th International Conference on Fog and Edge Computing (ICFEC). (pp 1–6). IEEE

  20. Jin T, Bercea GT, Le TD, Chen T, Su G, Imai H, Negishi Y, Leu A, O’Brien K, Kawachiya K, Eichenberger AE (2020) Compiling ONNX neural network models using mlir. arXiv preprintarXiv:2008.08272.

  21. Han S, Mao H, Dally WJ (2015) Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprintarXiv:1510.00149.

  22. Cerutti G, Prasad R, Brutti A, Farella E (2020) Compact recurrent neural networks for acoustic event detection on low-energy low-complexity platforms. IEEE J Select Topics Signal Process 14(4):654–664

    Article  Google Scholar 

  23. Liang T, Glossner J, Wang L, Shi S, Zhang X (2021) Pruning and quantization for deep neural network acceleration: A survey. Neurocomputing 461:370–403

    Article  Google Scholar 

  24. Rokh B, Azarpeyvand A, Khanteymoori A (2023) A comprehensive survey on model quantization for deep neural networks in image classification. ACM Trans Intell Syst Technol 14(6):1–50

    Article  Google Scholar 

  25. Kuzmin A, Nagel M, Van Baalen M, Behboodi A, Blankevoort T (2023) Pruning vs quantization: Which is better? Adv Neural Inform Process Syst 36:62414–62427

    Google Scholar 

  26. Bilen Ç, Ferroni G, Tuveri F, Azcarreta J, Krstulović S (2020 ) A framework for the robust evaluation of sound event detection. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). (pp 61–65). IEEE

  27. Ebbers J, Haeb-Umbach R, Serizel R (2022) Threshold independent evaluation of sound event detection scores. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). (pp 1021–1025). IEEE

Download references

Acknowledgements

This work has been supported by Grant TED2021-131003B-C21 funded by MCIN/AEI/10.13039/501100011033 and by the “EU Union NextGenerationEU/PRTR”, as well as by Grant PID2022-137048OB-C41 funded by MICIU/AEI/10.13039/501100011033 and “ERDF A way of making Europe”. Authors would like also to thankGeneralitat Valenciana-Santiago Grisolía program for financing this work (GRISOLIAP/2021/060, CPI-21-232). Finally, the authors acknowledge as well the Artemisa computer resources funded by the EU ERDF and Comunitat Valenciana, and the technical support of IFIC (CSIC-UV).

Author information

Authors and Affiliations

  1. Computer Science Department, Universitat de València, Burjassot, Spain

    Carlos Castorena, Jesus Lopez-Ballester, Juan A. De Rus, Maximo Cobos & Francesc J. Ferri

Authors
  1. Carlos Castorena

    You can also search for this author inPubMed Google Scholar

  2. Jesus Lopez-Ballester

    You can also search for this author inPubMed Google Scholar

  3. Juan A. De Rus

    You can also search for this author inPubMed Google Scholar

  4. Maximo Cobos

    You can also search for this author inPubMed Google Scholar

  5. Francesc J. Ferri

    You can also search for this author inPubMed Google Scholar

Contributions

Carlos Castorena conceived the idea, conducted the experiments, and wrote the main manuscript. Jesus Lopez-Ballester provided technical and experimental assistance. Juan Antonio de Rus contributed to the planning and execution of the experiments. Maximo Cobos and Francesc J. Ferri provided technical supervision and assisted in the writing and analysis of the results. All authors reviewed and approved the final manuscript.

Corresponding author

Correspondence toMaximo Cobos.

Ethics declarations

Conflict of interests

The authors declare no competing interests.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Castorena, C., Lopez-Ballester, J., De Rus, J.A.et al. Edge computing for driving safety: evaluating deep learning models for cost-effective sound event detection.J Supercomput81, 288 (2025). https://doi.org/10.1007/s11227-024-06796-1

Download citation

Keywords

Associated Content

Part of a collection:

SI - Computational and Mathematical Methods – CMMSE 2024

Access this article

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Advertisement

[8]ページ先頭
©2009-2025 Movatter.jp