Denoising by neural network for muzzle blast detection

TL;DR

This paper presents a lightweight neural network-based denoising method that significantly improves muzzle blast detection performance in noisy environments, especially on moving military vehicles.

Contribution

A novel, computationally efficient neural network architecture for denoising muzzle blast signals enhances detection accuracy in challenging acoustic conditions.

Findings

Detection rate more than doubled with denoising

Effective on hardware-constrained platforms

Improved performance in high-noise environments

Abstract

Acoem develops gunshot detection systems, consisting of a microphone array and software that detects and locates shooters on the battlefield. The performance of such systems is obviously affected by the acoustic environment in which they are operating: in particular, when mounted on a moving military vehicle, the presence of noise reduces the detection performance of the software. To limit the influence of the acoustic environment, a neural network has been developed. Instead of using a heavy convolutional neural network, a lightweight neural network architecture was chosen to limit the computational resources required to embed the algorithm on as many hardware platforms as possible. Thanks to the combination of a two hidden layer perceptron and appropriate signal processing techniques, the detection rate of impulsive muzzle blast waveforms (the wave coming from the detonation and indicating the position of the shooter) is significantly increased. With a rms value of noise of the same order as the muzzle blast peak amplitude, the detect rate is more than doubled with this denoising processing.