EDGAR: Embedded Detection of Gunshots by AI in Real-time

TL;DR

This paper introduces EDGAR, a machine learning method for real-time gunshot detection and counting using weak labels, deployable on microcontrollers, outperforming existing algorithms in accuracy and efficiency.

Contribution

The study presents a novel weak-label learning technique for shot detection that requires minimal labeling and is suitable for real-time embedded systems.

Findings

Significant improvement over unsupervised algorithms.

Comparable performance to human-designed algorithms.

Real-time inference under 100ms on microcontrollers.

Abstract

Electronic shot counters allow armourers to perform preventive and predictive maintenance based on quantitative measurements, improving reliability, reducing the frequency of accidents, and reducing maintenance costs. To answer a market pressure for both low lead time to market and increased customisation, we aim to solve the shot detection and shot counting problem in a generic way through machine learning. In this study, we describe a method allowing one to construct a dataset with minimal labelling effort by only requiring the total number of shots fired in a time series. To our knowledge, this is the first study to propose a technique, based on learning from label proportions, that is able to exploit these weak labels to derive an instance-level classifier able to solve the counting problem and the more general discrimination problem. We also show that this technique can be deployed in heavily constrained microcontrollers while still providing hard real-time (<100ms) inference. We evaluate our technique against a state-of-the-art unsupervised algorithm and show a sizeable improvement, suggesting that the information from the weak labels is successfully leveraged. Finally, we evaluate our technique against human-generated state-of-the-art algorithms and show that it provides comparable performance and significantly outperforms them in some offline and real-world benchmarks.