preprints.org > engineering > control and systems engineering > doi: 10.20944/preprints202010.0343.v1

Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Version 1 : Received: 15 October 2020 / Approved: 16 October 2020 / Online: 16 October 2020 (08:32:07 CEST)
Version 2 : Received: 9 November 2020 / Approved: 9 November 2020 / Online: 9 November 2020 (14:21:39 CET)

For the Remotely Piloted Aircraft Systems (RPAS) market to continue its current growth rate, cost-effective "Detect and Avoid" systems which enable safe beyond visual line of sight (BVLOS) operations are critical. We propose an audio-based "Detect and Avoid" system, composed of microphones and an embedded computer, which performs real-time inferences using a sound event detection (SED) deep learning model. Two state-of-the-art SED models, YAMNet and VGGish, are fine-tuned using our aircraft sounds dataset and their performances are compared for a wide range of configurations. YAMNet, whose MobileNet architecture is designed for embedded applications, outperformed VGGish both in terms of aircraft detection and computational performance. YAMNet's optimal configuration, with > 70% true positive rate and precision, results from combining data augmentation and undersampling with the highest available inference frequency (i.e. 10 Hz). While our proposed "Detect and Avoid" system already allows the detection of small aircraft from sound in real time, a larger dataset, sensor fusion, or the use of cloud-based services for remote computations could further improve its performance.

deep learning; sound event detection; convolutional neural networks; audio processing; embedded systems

Engineering, Control and Systems Engineering

* All users must log in before leaving a comment