TY - JOUR
T1 - ASTEROID SHAPE RECONSTRUCTION METHOD BASED ON CONVOLUTIONAL NEURAL NETWORK
AU - Yan, Chen
AU - Dong, Zehua
AU - Zhang, Na
AU - Ding, Zegang
N1 - Publisher Copyright:
© The Institution of Engineering & Technology 2023.
PY - 2023
Y1 - 2023
N2 - Radar is the most powerful remote sensing tool for measuring the physical characteristics of near-Earth objects. In this paper, we propose an asteroid shape reconstruction method using convolutional neural networks, which can reconstruct the three-dimensional shape features of asteroids based on radar observation data. Compared to traditional methods, it has the advantages of automatic optimization and minimal manual intervention. Experimental results have been conducted to demonstrate the effectiveness of this method.
AB - Radar is the most powerful remote sensing tool for measuring the physical characteristics of near-Earth objects. In this paper, we propose an asteroid shape reconstruction method using convolutional neural networks, which can reconstruct the three-dimensional shape features of asteroids based on radar observation data. Compared to traditional methods, it has the advantages of automatic optimization and minimal manual intervention. Experimental results have been conducted to demonstrate the effectiveness of this method.
KW - ASTEROID SHAPE RECONSTRUCTION
KW - DELAY-DOPPLER IMAGES
KW - NEURAL NETWORK
UR - http://www.scopus.com/inward/record.url?scp=85203177777&partnerID=8YFLogxK
U2 - 10.1049/icp.2024.1778
DO - 10.1049/icp.2024.1778
M3 - Conference article
AN - SCOPUS:85203177777
SN - 2732-4494
VL - 2023
SP - 4142
EP - 4145
JO - IET Conference Proceedings
JF - IET Conference Proceedings
IS - 47
T2 - IET International Radar Conference 2023, IRC 2023
Y2 - 3 December 2023 through 5 December 2023
ER -