Particle Identification In Camera Image Sensors Using Computer Vision

TL;DR

This paper introduces a deep learning-based computer vision algorithm that accurately classifies charged particles in camera sensors, enabling real-time cosmic-ray detection and analysis within a global smartphone network.

Contribution

The study develops a convolutional neural network for particle classification in camera images, achieving human-level accuracy and high purity in a large, real-world cosmic-ray data set.

Findings

Achieves ≥90% purity across all event types

Estimates 95% purity for cosmic-ray muons

Operates in real-time on public data set

Abstract

We present a deep learning, computer vision algorithm constructed for the purposes of identifying and classifying charged particles in camera image sensors. We apply our algorithm to data collected by the Distributed Electronic Cosmic-ray Observatory (DECO), a global network of smartphones that monitors camera image sensors for the signatures of cosmic rays and other energetic particles, such as those produced by radioactive decays. The algorithm, whose core component is a convolutional neural network, achieves classification performance comparable to human quality across four distinct DECO event topologies. We apply our model to the entire DECO data set and determine a selection that achieves $\ge90\%$ purity for all event types. In particular, we estimate a purity of $95\%$ when applied to cosmic-ray muons. The automated classification is run on the public DECO data set in real time in order to provide classified particle interaction images to users of the app and other interested members of the public.