Audio features based ADS-CNN method for flight attitude recognition of quadrotor UAV

Abstract

With the rapid development of unmanned flight technology, it has been widely used in all walks of life. Quad-rotor unmanned aerial vehicle (QrUAV) is the most widely used, due to its advantages of simple structure, high stability, and easy control. Currently, efficient, fast and accurate identification of QrUAV is still a hot issue. To this end, this paper proposes an audio features based flight attitude recognition method for QrUAV. Using the newly recorded UAV Attitude Audio data set (UAVAA), a lightweight convolutional neural network (ADS-CNN) integrated with attention mechanism is established for the flight attitude recognition of QrUAV. The feature of this method is that a lightweight network structure is designed through depthwise separable convolution and residual connection, this structure effectively reduces the network parameter consumption, and increases the network depth as much as possible when the number of UAVAA samples is small, which effectively suppresses overfitting and improves the recognition accuracy. In addition, by introducing of the region of interest focusing module (IFA) into the network, the weight of the attitude features is divided to realize the importance of the features, so as to achieve efficient and high-accuracy recognition. Finally, by fusing the MFCC features and STFT features of the QrUAV audio, the feature dimension is increased and the recognition accuracy is improved. By experimental comparison and analysis, the accuracy rate of ADS-CNN reached 98.81%, which was 2.7% higher than that of VGG16, the model parameters of ADS-CNN were only 27.6% of VGG16, and the operation time was only 32% of VGG16, which shows that ADS –CNN can identify the flight attitude of the QrUAV more accurately and quickly by using attitude audio.