TY - JOUR
T1 - 月表陨检测轻化深度学习方法
AU - Gao, Ai
AU - Zhou, Yongjun
AU - Wang, Junwei
AU - Wu, Zezhao
N1 - Publisher Copyright:
© 2022 China Spaceflight Society. All rights reserved.
PY - 2022/6/1
Y1 - 2022/6/1
N2 - A lightweight deep learning crater detection method is proposed to address the problems of large number of model parameters and slow detection of the current deep learning crater detection methods. Firstly, the channel pruning method is used to delete the redundant convolution kernel in convolution neural network to obtain a compact and efficient crater detection model. Then, the lightweight depthwise separable convolution operation is used to replace the standard convolution operation in the basic crater detection model, which further reduces the complexity of the model. The simulation results show that the proposed lightweight crater detection model can ensure high pixel prediction accuracy, and can adapt to the influence of interference factors such as brightness and image noise. Moreover, compared with the model before lightweight processing, the amount of parameters is reduced by 99.2% and the detection speed is improved by 94%.
AB - A lightweight deep learning crater detection method is proposed to address the problems of large number of model parameters and slow detection of the current deep learning crater detection methods. Firstly, the channel pruning method is used to delete the redundant convolution kernel in convolution neural network to obtain a compact and efficient crater detection model. Then, the lightweight depthwise separable convolution operation is used to replace the standard convolution operation in the basic crater detection model, which further reduces the complexity of the model. The simulation results show that the proposed lightweight crater detection model can ensure high pixel prediction accuracy, and can adapt to the influence of interference factors such as brightness and image noise. Moreover, compared with the model before lightweight processing, the amount of parameters is reduced by 99.2% and the detection speed is improved by 94%.
KW - Convolutional neural networks
KW - Crater detection
KW - Deep learning
KW - Lightweight processing
KW - Lunar landing exploration
UR - http://www.scopus.com/inward/record.url?scp=85138475836&partnerID=8YFLogxK
U2 - 10.3873/j.issm.1000-1328.2022.06.014
DO - 10.3873/j.issm.1000-1328.2022.06.014
M3 - 文章
AN - SCOPUS:85138475836
SN - 1000-1328
VL - 43
SP - 830
EP - 838
JO - Yuhang Xuebao/Journal of Astronautics
JF - Yuhang Xuebao/Journal of Astronautics
IS - 6
ER -