TY - GEN
T1 - Meteorite Hunting Using Deep Learning and UAVs
AU - Alowais, Aisha
AU - Naseem, Safa
AU - Dawdi, Takwa
AU - Abdisalam, Mariam
AU - Elkalyoubi, Yusra
AU - Adwan, Anas
AU - Hassan, Khawla
AU - Fernini, Ilias
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - 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.
AB - 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.
KW - Convolutional Neural Networks
KW - Deep Learning
KW - Drone
KW - Machine Learning
KW - Meteorite
KW - UAV
UR - http://www.scopus.com/inward/record.url?scp=85085561997&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85085561997&partnerID=8YFLogxK
U2 - 10.1109/ICSPIS48135.2019.9045905
DO - 10.1109/ICSPIS48135.2019.9045905
M3 - Conference contribution
AN - SCOPUS:85085561997
T3 - 2019 2nd International Conference on Signal Processing and Information Security, ICSPIS 2019
BT - 2019 2nd International Conference on Signal Processing and Information Security, ICSPIS 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2nd International Conference on Signal Processing and Information Security, ICSPIS 2019
Y2 - 30 October 2019 through 31 October 2019
ER -