@article{ec8d1879935f41a5a302e0374ba5046d,
title = "Toward Generalized Change Detection on Planetary Surfaces with Convolutional Autoencoders and Transfer Learning",
abstract = "Ongoing planetary exploration missions are returning large volumes of image data. Identifying surface changes in these images, e.g., new impact craters, is critical for investigating many scientific hypotheses. Traditional approaches to change detection rely on image differencing and manual feature engineering. These methods can be sensitive to irrelevant variations in illumination or image quality and typically require before and after images to be coregistered, which itself is a major challenge. Additionally, most prior change detection studies have been limited to remote sensing images of earth. We propose a new deep learning approach for binary patch-level change detection involving transfer learning and nonlinear dimensionality reduction using convolutional autoencoders. Our experiments on diverse remote sensing datasets of Mars, the moon, and earth show that our methods can detect meaningful changes with high accuracy using a relatively small training dataset despite significant differences in illumination, image quality, imaging sensors, coregistration, and surface properties. We show that the latent representations learned by a convolutional autoencoder yield the most general representations for detecting change across surface feature types, scales, sensors, and planetary bodies.",
keywords = "Change detection algorithms, earth, machine learning, mars, moon, neural networks, remote sensing, supervised learning, unsupervised learning",
author = "Kerner, {Hannah Rae} and Wagstaff, {Kiri L.} and Bue, {Brian D.} and Gray, {Patrick C.} and Iii, {James F.Bell} and Amor, {Heni Ben}",
note = "Funding Information: Manuscript received April 1, 2019; revised June 18, 2019; accepted August 7, 2019. Date of publication September 8, 2019; date of current version November 22, 2019. This work was supported by the Jet Propulsion Laboratory, California Institute of Technology, Internal Strategic University Research Partnerships (SURP) program under a contract with the National Aeronautics and Space Administration. (Corresponding author: Hannah Rae Kerner.) H. R. Kerner is with the Department of Geographical Sciences, University of Maryland, College Park, MD 20742 USA (e-mail: hkerner@umd.edu). Funding Information: This work was supported by the Jet Propulsion Laboratory, California Institute of Technology, Internal Strategic University Research Partnerships (SURP) program under a contract with the National Aeronautics and Space Administration. Funding Information: The authors would like to thank Dr. D. Stillman of the South-west Research Institute (SwRI) and Dr. I. Daubar of the Jet Propulsion Laboratory for their expert knowledge on RSL and meteorite impacts, the PDS for supporting the development of this article, and Dr. G. Doran of the Jet Propulsion Laboratory for his assistance with processing CTX image pairs. This research was carried out (in part) at the Jet Propulsion Laboratory, California Institute of Technology, under a contract with the National Aeronautics and Space Administration. Publisher Copyright: {\textcopyright} 2008-2012 IEEE.",
year = "2019",
month = oct,
doi = "10.1109/JSTARS.2019.2936771",
language = "English (US)",
volume = "12",
pages = "3900--3918",
journal = "IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing",
issn = "1939-1404",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "10",
}