Meteorite Hunting Using Deep Learning and UAVs

Aisha Alowais, Safa Naseem, Takwa Dawdi, Mariam Abdisalam, Yusra Elkalyoubi, Anas Adwan, Khawla Hassan, Ilias Fernini

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Citations (Scopus)

Abstract

In this paper, we present an automated meteorite detection system that employs an autonomous Unmanned Aerial Vehicle (UAV). It is programmed to recognize and locate meteorites using machine learning. In this design, the UAV carries a Single Board Computer (SBC), through which realtime data processing of the live video feed from an optical camera is performed. The integration of a GPS module into the system enables localization of the detected meteorites. The onboard processing, carried out by the SBC, involves analyzing each frame from the video and running it through our deep learning model. This model is trained on images of different types of commonly found meteorites, via Transfer Learning performed on Convolutional Neural Networks (CNN). The results were promising, with an accuracy of approximately 90%. Future enhancements, including the addition of an infrared sensor to capture thermal images, are also discussed.

Original languageEnglish
Title of host publication2019 2nd International Conference on Signal Processing and Information Security, ICSPIS 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728138732
DOIs
Publication statusPublished - Oct 2019
Externally publishedYes
Event2nd International Conference on Signal Processing and Information Security, ICSPIS 2019 - Dubai, United Arab Emirates
Duration: Oct 30 2019Oct 31 2019

Publication series

Name2019 2nd International Conference on Signal Processing and Information Security, ICSPIS 2019

Conference

Conference2nd International Conference on Signal Processing and Information Security, ICSPIS 2019
Country/TerritoryUnited Arab Emirates
CityDubai
Period10/30/1910/31/19

Keywords

  • Convolutional Neural Networks
  • Deep Learning
  • Drone
  • Machine Learning
  • Meteorite
  • UAV

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Signal Processing
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality
  • Health Informatics

Fingerprint

Dive into the research topics of 'Meteorite Hunting Using Deep Learning and UAVs'. Together they form a unique fingerprint.

Cite this