English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Analyzing multi–domain learning for enhanced rockfall mapping in known and unknown planetary domains

Bickel, V. T., Mandrake, L., & Doran, G. (2021). Analyzing multi–domain learning for enhanced rockfall mapping in known and unknown planetary domains. ISPRS Journal of Photogrammetry and Remote Sensing, 182, 1-13. doi:10.1016/j.isprsjprs.2021.09.018.

Item is

Basic

show hide
Genre: Journal Article

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Bickel, Valentin Tertius1, Author              
Mandrake, Lukas, Author
Doran, Gary, Author
Affiliations:
1Department Planets and Comets, Max Planck Institute for Solar System Research, Max Planck Society, ou_1832288              

Content

show
hide
Free keywords: Rockfall Transfer learning Domain adaptation Moon Mars Ceres
 Abstract: Rockfalls are small–scale mass wasting events that have been observed across the solar system. They provide valuable information about the endo- and exogenic activity of their host body, but are difficult to identify and map in satellite imagery, especially on global scales and in big data sets. Past work implemented convolutional neural networks to automate rockfall mapping on the Moon and Mars with the caveat of (1) achieving sub–optimal performance and (2) requiring substantial manual image labeling efforts. Mixing annotated image data from the Moon and Mars while keeping the total number of labels constant, we show that including a small number (10%) of rockfall labels from a foreign domain (e.g. Moon) during detector training can increase performance in the home domain (e.g. Mars) by up to 6% Average Precision (AP) in comparison to a purely home domain-trained detector. We additionally show that using a large number of foreign domain training examples (90%) in combination with a small number (10%) of home domain labels can be as powerful or more powerful as exclusively (100%) using home labels in the home domain. We further observe that rockfall detectors trained on multiple domains outperform single–domain trained detectors in completely unknown domains by up to 16% AP, using image data from Ceres and comet 67P. We conduct an experiment varying only image resolution on a single planetary body (Mars) to test whether the improvement was due to training on differing resolutions specifically and show that none of the improvement can be explained by this effect alone. This means that the benefits of multi–domain training mostly draw from either variations in lighting condition, differing physical appearance/backgrounds around the target of interest for generalization purposes, or both. Our findings have important applications such as machine learning–enabled science discovery in legacy and new planetary datasets. The used dataset of martian and lunar rockfalls including a detailed description is available here: https://edmond.mpdl.mpg.de/imeji/collection/DowTY91csU3jv9S2.

Details

show
hide
Language(s): eng - English
 Dates: 2021
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: Peer
 Identifiers: DOI: 10.1016/j.isprsjprs.2021.09.018
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: ISPRS Journal of Photogrammetry and Remote Sensing
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Amsterdam [u.a.] : Elsevier
Pages: - Volume / Issue: 182 Sequence Number: - Start / End Page: 1 - 13 Identifier: ISSN: 0924-2716
CoNE: https://pure.mpg.de/cone/journals/resource/0924-2716