Development of an Acoustic System for UAV discovery and tracking employing Concurrent Neural Networks

The purpose of this paper is to investigate the possibility of developing and using an intelligent, flexible, and reliable acoustic system, designed to discover, locate, and transmit the position of an Unmanned Aerial Vehicle (UAV). Such an application may be useful for monitoring sensitive areas and land territories privacy. The software functional components of the proposed detection and location algorithm were developed employing Deep Neural Networks. An analysis of the detection and tracking performance for Remotely Piloted Aircraft Systems (RPASs), measured with a dedicated spiral microphone array with MEMS microphones, in the audio and ultrasonic bands, was also performed. The detection and tracking algorithms were implemented based on wavelet decomposition and adaptive filters. In this research, spectrograms with Cohen class decomposition, log-Mel spectrograms, harmonic-percussive source separation and raw audio waveforms of the audio sample collected from spiral microphone array as an input to the Concurrent Neural Networks (CNN’s) were used, in order to determine and classify the number of detected drones in the perimeter of interest. For this particular case study, the perimeter of interest was considered within a country's borders.