Research on Feature Recognition of UAV Acoustic Signal Based on SVM

Abstract

At present, the analysis of UAV flight acoustic signals is mainly based on traditional speech signal processing methods, and has not been analyzed in depth. According to the flight signal of UAV, combined with the aerodynamic characteristics of UAV, the characteristics of UAV’s acoustic signal are analyzed. The three feature extraction algorithms of pitch period, FFT and Mel Cepstral Coefficient (MFCC) are analyzed and compared. Feature extraction is performed, and a support vector machine (SVM) classification algorithm is applied to perform multi-classification model recognition. The measured and experimental results show that based on SVM classification and recognition, the three feature recognition methods all realize the classification of the model. The comprehensive FFT is the best, and the MFCC is the second. The pitch period is not suitable as the feature extraction method alone.

Acoustic signal recognition of UAV based on GAF and convolutional neural network

“…The UAV sound signal recognition is divided into two steps, namely the feature extraction of the sound signal and the classification and recognition based on the feature vector. The current mainstream feature extraction methods mainly include Fourier transform [3] , wavelet transform [4] , Mel-Frequency Cepstral Coefficients [5] (Mel-Frequency Cepstral Coefficients, MFCC) and so on. Qiu Kaibin [6] extracted MFCC features from the perspective of auditory perception and combined ΔMFCC with time-varying characteristics to improve the separability of feature vectors, but the recognition accuracy needs to be improved.…”