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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Borkiewicz, Kalina, Shah, Viraj, Naiman, J. P., Shen, Chuanyue, Levy, Stuart, Carpenter, Jeff
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909372785885184
author Borkiewicz, Kalina
Shah, Viraj
Naiman, J. P.
Shen, Chuanyue
Levy, Stuart
Carpenter, Jeff
author_facet Borkiewicz, Kalina
Shah, Viraj
Naiman, J. P.
Shen, Chuanyue
Levy, Stuart
Carpenter, Jeff
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2110_13819
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle CloudFindr: A Deep Learning Cloud Artifact Masker for Satellite DEM Data
Borkiewicz, Kalina
Shah, Viraj
Naiman, J. P.
Shen, Chuanyue
Levy, Stuart
Carpenter, Jeff
Computer Vision and Pattern Recognition
Graphics
Machine Learning
Image and Video Processing
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.
title CloudFindr: A Deep Learning Cloud Artifact Masker for Satellite DEM Data
topic Computer Vision and Pattern Recognition
Graphics
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2110.13819