Acoustic-Based Drone Detection Using Neural Networks – A Comprehensive Analysis

• Autorzy: Paszkowski Waldemar , Gola Arkadiusz , Świć Antoni

Identyfikatory

DOI

10.12913/22998624/17586

• Języki publikacji: EN

Abstrakty

EN

The article presents and describes the implementation of research on the detection of a drone in an urban environment using of the sound features. The methods of drone detection were recognized on the basis of modeling and evaluation of the features of the audio and acoustic signal. The authors proposed the use of a neural network model for the needs of drone detection taking into account acoustic measurements in an anechoic chamber and in an urban environment. The final part presents the obtained results of the drone detection. For the purposes of detection, a neural network model was used in order to recognize the obtained images of the spectograms of sound sources.

Słowa kluczowe

EN

drone detection; acoustic measurements; signal; spectrogram; neural network

• Wydawca: Lublin University of Technology ; Polish Society of Ecological Engineering (PTIE), Branch of PTIE in Lublin
• Czasopismo: Advances in Science and Technology. Research Journal
• Rocznik: 2024
• Tom: Vol. 18, no 1
• Strony: 36--47
• Opis fizyczny: Bibliogr. 22 poz., fig., tab.

Twórcy

autor

Paszkowski Waldemar

• Silesian University of Technology, Faculty of Organization and Management

• https://orcid.org/0000-0001-5739-7449

autor

Gola Arkadiusz

• Lublin University of Technology, Faculty of Mechanical Engineering

• https://orcid.org/0000-0002-2935-5003

autor

Świć Antoni

• Lublin University of Technology, Faculty of Mechanical Engineering

• https://orcid.org/0000-0003-2553-7042

Bibliografia

• 1. Birch G.C., Griffin J.C., M.K. Erdman: UAS detection, classification, and neutralization: Market survey, prepared by Sandia Nat’l. Labs, 2015.
• 2. Busset J. et al. Detection and tracking of drones using advanced acoustic cameras. Proc. SPIE Security Defence, vol. 9647, Toulouse, France, Oct. 2015, 1–8.
• 3. Benyamin M., Goldman G.H. Acoustic detection and tracking of a Class I UAS with a small tetrahedral microphone array. Army Research Lab. tech. rep. (ARLTR-7086), DTIC Doc., Sept. 2014.
• 4. Thibbotuwawa A., Nielsen P., Zbigniew B., Bocewicz G. Factors affecting energy consumption of unmanned aerial vehicles: an analysis of how energy consumption changes in relation to UAV routing. Advances in Intelligent Systems and Computing 2019; 853, 228-238, doi: 10.1007/978-3-319-99996-8_21.
• 5. Thibbotuwawa A., Bocewicz G., Nielsen P., Banaszak Z. UAV mission planning subject to weather forecast constraints. Advances in Intelligent Systems and Computing, 2020; 1004, 65-76, doi: 10.1007/978-3-030-23946-6_8.
• 6. Rabiner L.R., Schafer R.W. Digital processing of speech signals. Prentice Hall, 1978.
• 7. Shea K.O., Nash R.: An introduction to convolutional neural networks. arXiv preprint arXiv:1511.08458, 2015.
• 8. Matviykiv O., Klymkovych T., Bokla N., Lobur M., Melnyk M., Timofiejczuk A.: Simulation of acoustophoretic separation of microplastic particles in mkFluidic Lab-chip. 2020 IEEE XVITH International Conference on the Perspective Technologies and Methods in Mems Design. Book Series: International Conference on Perspective Technologies and
• Methods in MEMS Design MEMSTECH, 123-126.
• 9. Shin J.-W., Lee Y.-J., Kim W.-H., Kwon Y., Yang H.- Y. Empirical study of drone sound detection in real-life environment with deep neural networks. In: Signal Processing Conference (EUSIPCO), 2017 25th European, pages 1858–1862. IEEE, 2017.
• 10. Jeon S., Shin J.-W., Lee Y.-J., Kim W.-H., Kwon Y.,Yang. H.- Y. Empirical study of drone sound detection in reallife environment with deep neural networks. In: Signal Processing Conference (EUSIPCO), 2017 25th European, 1858–1862. IEEE, 2017.
• 11. Rutherford A. Introducing ANOVA and ANCOVA: A GLM Approach. SAGE Publications Ltd, London 2001.
• 12. Shannon C., Weaver W. The mathematical theory of communication. University Illinois Press, Urbana 1949.
• 13. Paszkowski W., Loska A. The use of neural network model in the assessment of annoyance of the industrial noise sources. Intelligent Systems in Production Engineering and Maintenance (ISPEM 2017). Book Series: Advances in Intelligent Systems and Computing, 637, 428-439. Springer Verlag 2018, doi: https://doi.org/10.1007/978-3-319-64465-3_41.
• 14. Loska A. Variant assessment of exploitation policy of selected companies managing technical network systems. Management Systems in Production Engineering 2015; 3(19), 179-188, doi: 10.12914/MSPE-13-03-2015.
• 15. Rozporządzenie Ministra Klimatu i Środowiska z dnia 7 września 2021 r. w sprawie wymagań w zakresie prowadzenia pomiarów wielkości emisji. Dziennik Ustaw Rzeczypospolitej Polskiej, poz. 1710.
• 16. PN-85/N-01333. Hałas. Dokładne metody określenia mocy akustycznej hałasu maszyn w komorze bezechowej i w otwartej przestrzeni.
• 17. PN-EN ISO 3746:2011. Akustyka. Wyznaczanie poziomów mocy akustycznej i poziomów energii akustycznej źródeł hałasu na podstawie pomiarów ciśnienia akustycznego. Metoda orientacyjna z zastosowaniem otaczającej powierzchni pomiarowej nad płaszczyzną odbijającą dźwięk.
• 18. Rozporządzenie Ministra Środowiska z dnia 30 października 2014 r. w sprawie wymagań w zakresie prowadzenia pomiarów wielkości emisji oraz pomiarów ilości pobieranej wody. Dz. U., poz. 1542.
• 19. https://www.tensorflow.org/tutorials/images/classification.
• 20. Casabianca P., Zhang Y.: Acoustic-based UAV detection using late fusion of deep neural networks. Drones 2021, 5(3), 54; https://doi.org/10.3390/drones5030054
• 21. Al-Emadi S., Al-Ali A. Audio-based drone detection and identification using deep learning techniques with dataset enhancement through generative adversarial networks. Sensors (Basel). 2021 Aug; 21(15): 4953. Doi: 10.3390/s21154953
• 22. Jeon S., Shin J., Lee Y., Kim W., Kwon Y., Yang H. Empirical study of drone sound detection in reallife environment with deep neural networks. Materiały z 25. Europejskiej Konferencji Przetwarzania Sygnałów 2017 (EUSIPCO); Kos, Grecja. 28.08 – 2.09.2017 r.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).