Open AccessAccelerate fine-scale geological mapping with UAV and convolutional neural networks
Author(s) -
Liang Zhan,
Bin Liu,
Xuejia Sang,
Linfu Xue
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/768/7/072082
Subject(s) - convolutional neural network , scale (ratio) , computer science , field (mathematics) , geologic map , process (computing) , artificial intelligence , geological survey , high resolution , work (physics) , artificial neural network , remote sensing , pattern recognition (psychology) , data mining , geology , cartography , geography , engineering , geomorphology , geophysics , mathematics , pure mathematics , operating system , mechanical engineering
We propose a new fine-scale mapping process, which UAV and CNNs to distinguish the rock mass. Studies have shown that with UAV high-resolution images, comparing with traditional classification methods (52.92%~67.11%), the CNNs method has a much higher classification accuracy rate (86.54%). Although they can’t completely replace ground work, UAV and CNNs, together with appropriate field geological survey work, can quickly fill fine-scale geological maps. This is significant for harsh areas.