Deep Learning for Landslide Recognition in Satellite Architecture

IEEE Access

Pei-Jun Lee¹  Trong-An Bui¹  Kai-Yew Lum¹  Clarissa Loh²  Kyo Tan² 

[1] Electrical Engineering Department, National Chi Nan University, Puli, Taiwan;School of Engineering, Nanyang Polytechnic University, Singapore;

关键词: H-BEMD;    CNN;    object recognition;    landslide localization;    Earth;    remote sensing;   

DOI  :  10.1109/ACCESS.2020.3014305

来源: DOAJ

【 摘 要 】

Using the optical camera in remote sensing is limited in various environmental conditions. This paper presents a system of combining deep learning and image transform algorithms to detect landslide location in satellite images. In the deep learning part, a convolution neural network is used to classify satellite images contain landslides. From landslide images classified, in order to accurately identify landslides under different lighting conditions, this paper proposes a transformation algorithm Hue - Bi-dimensional empirical mode decomposition (H-BEMD) to determine the landslide region and size. After the location of landslide is detected, we discover the size change of the landslide based on different time points. In this study, we record an accuracy of up to 96% in the classification process, and the accuracy of landslide location almost absolute.

【 授权许可】

Unknown