Piezoelectrics & Acoustooptics, Volume. 47, Issue 3, 597(2025)

UAV Acoustic Detection and Recognition Based on a Time-Frequency Attention and Soft Thresholding CNN

WU Canbo1 and HAN Gangtao2
Author Affiliations
  • 1Information Engineering Department,Zhengzhou Industrial Safety Vocational College,Zhengzhou 451192,China
  • 2School of Electrical and Information Engineering,Zhengzhou University,Zhengzhou 450001,China
  • show less

    In recent years,the widespread use of drones in various fields has introduced new security risks,making the monitoring and detection of drone activities crucial. This paper proposes a UAV acoustic detection and recognition method based on the mel spectrogram and time-frequency attention and soft thresholding convolutional neural network for detecting and classifying UAV audio from various environmental noises. This method converts UAV audio data into mel spectrograms and inputs them into the neural network model. The model automatically learns and identifies important time and frequency regions in the mel spectrogram through the attention mechanisms of time and frequency and assigns higher attention weights to them to improve recognition accuracy. Combined with soft thresholding,it suppresses the influence of environmental noise and outliers on the model and improves its classification and recognition performance under various environmental noise interferences. In this study,we collected an 8-category audio dataset for drones and enhanced it using background noise. We evaluated existing methods using this dataset. The results demonstrated that the proposed method is superior to existing methods in terms of accuracy,precision,recall,and F1-score.

    Tools

    Get Citation

    Copy Citation Text

    WU Canbo, HAN Gangtao. UAV Acoustic Detection and Recognition Based on a Time-Frequency Attention and Soft Thresholding CNN[J]. Piezoelectrics & Acoustooptics, 2025, 47(3): 597

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category:

    Received: Nov. 26, 2024

    Accepted: --

    Published Online: Jul. 11, 2025

    The Author Email:

    DOI:10.11977/j.issn.1004-2474.2025.03.030

    Topics