Object classification on video data of meteors and meteor-like phenomena: algorithm and data

TL;DR

This paper introduces the NightSkyUCP dataset and four open source machine learning solutions for classifying meteor events in sky video data, achieving high accuracy and aiding celestial research.

Contribution

It provides a new balanced dataset and four reusable algorithms for meteor detection, addressing the lack of high-quality training data in the field.

Findings

Achieved 99.1% mean accuracy in meteor classification

Developed four open source solutions for meteor event detection

Published dataset and code publicly for research use

Abstract

Every moment, countless meteoroids enter our atmosphere unseen. The detection and measurement of meteors offer the unique opportunity to gain insights into the composition of our solar systems' celestial bodies. Researchers, therefore, carry out a wide-area-sky-monitoring to secure 360-degree video material, saving every single entry of a meteor. Existing machine intelligence cannot accurately recognize events of meteors intersecting the earth's atmosphere due to a lack of high-quality training data publicly available. This work presents four reusable open source solutions for researchers trained on data we collected due to the lack of available labeled high-quality training data. We refer to the proposed dataset as the NightSkyUCP dataset, consisting of a balanced set of 10,000 meteor- and 10,000 non-meteor-events. Our solutions apply various machine learning techniques, namely classification, feature learning, anomaly detection, and extrapolation. For the classification task, a mean accuracy of 99.1\% is achieved. The code and data are made public at figshare with DOI: 10.6084/m9.figshare.16451625