Abstract
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.
Highlights
In recent years, satellite technology and remote sensing technology [1] is fast developing
To solve the effect of light conditions on object recognition, this paper proposes a Hue – Bi-dimensional empirical mode decomposition (H-bi-dimensional empirical mode decomposition (BEMD)) method to detect the object of interest on Earth’s surface [24]
- Introduction - Hue – Bi-dimensional empirical mode decomposition (H-BEMD): we propose an improvement algorithm to detect landslide region on hue channel from satellite image. - The combination methodology between Convolution Neural Network (CNN) and H-BEMD: An architecture of combining CNN and HueBEMD to predict the scaling of landslide based on satellite image data. - Simulation Results
Summary
Satellite technology and remote sensing technology [1] is fast developing. - Introduction - Hue – Bi-dimensional empirical mode decomposition (H-BEMD): we propose an improvement algorithm to detect landslide region on hue channel from satellite image. This paper proposes an algorithm Hue – Bi-dimensional empirical mode decomposition (H-BEMD) to detect landslide objects in satellite images. To prove the formula for defining extrema location, a hue value image with size 224×224 is applied to identify the maxima and minima points. Radial Basis Functions (RBFs) [20] is an algorithm to reconstruct smooth, manifold surfaces from pointcloud data and to repair incomplete meshes In this sifting process step, a 2D ‘envelope’ is generated by connecting the maxima points (respectively, minima point) with RBFs. RBFs make the value out of range. We present a proposed methodology to combine CNN and H-BEMD to locate the landslide region from satellite database.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
