CloudFindr: A Deep Learning Cloud Artifact Masker for Satellite DEM Data

TL;DR

This paper describes a method for creating cloud artifact masks which can be used to remove artifacts from satellite imagery using a combination of traditional image processing together with deep learning based on U-Net.

Abstract

Artifact removal is an integral component of cinematic scientific visualization, and is especially challenging with big datasets in which artifacts are difficult to define. In this paper, we describe a method for creating cloud artifact masks which can be used to remove artifacts from satellite imagery using a combination of traditional image processing together with deep learning based on U-Net. Compared to previous methods, our approach does not require multi-channel spectral imagery but performs successfully on single-channel Digital Elevation Models (DEMs). DEMs are a representation of the topography of the Earth and have a variety applications including planetary science, geology, flood modeling, and city planning.

Figures (8)

• Figure 1: A 3D visualization of a DEM region without cloud artifact removal, showing large spikes where the height of the land is incorrectly labelled with the height of a cloud.
• Figure 2: Final cloud-free cinematic rendering of the Jakobshavn glacier used in the Atlas of a Changing Earth documentary.
• Figure 3: Example showing the inputs (left, middle) used to output a hand-drawn mask (right) for one sample timestep. Top row shows individual strips, bottom row shows accumulated buildup of strips. Left column shows DEM data, middle column shows artificially shaded preview, right column shows resulting mask (repeated in both rows).
• Figure 4: GLCM features for three main types of land covers.
• Figure 5: The CloudFindr architecture, based on U-Netunet.