SPATIO-TEMPORAL SUPER-RESOLUTION RECONSTRUCTION OF REMOTE SENSING DATA

Igor Yanovsky; Jing Qin

doi:10.1109/IGARSS47720.2021.9553433

SPATIO-TEMPORAL SUPER-RESOLUTION RECONSTRUCTION OF REMOTE SENSING DATA

Igor Yanovsky, Jing Qin

Mathematics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

We present a spatio-temporal super-resolution method for reconstructing a sequence of observations collected by imaging satellites. A sequence of observations is assumed to be defined on a low resolution spatio-temporal grid. It is further assumed that the sequence is generated by blurring of a captured scene with a spatio-temporal convolution kernel and is degraded by noise. Our method simultaneously exhibits deconvolution of the sequence of images from the effects of spatio-temporal blur, denoising of the data, and upsampling of the low-resolution sequence to a high resolution spatio-temporal grid. We perform the super-resolution in the space-time domain, as opposed to super-resolving the sequence separately and sequentially to a higher spatial and then temporal resolution grid. Simultaneous space-time optimization achieves a more efficient and more accurate reconstruction than reconstructing a sequence frame by frame. The proposed super-resolution methodology is based on total variation regularization and computes the solution using the alternating direction method of multipliers. Numerical results show our approach to be robust and computationally efficient.

Original language	English
Title of host publication	IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
Pages	2907-2910
Number of pages	4
ISBN (Electronic)	9781665403696
DOIs	https://doi.org/10.1109/IGARSS47720.2021.9553433
State	Published - 2021
Event	2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 - Brussels, Belgium Duration: Jul 12 2021 → Jul 16 2021

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2021-July

Conference

Conference	2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021
Country/Territory	Belgium
City	Brussels
Period	7/12/21 → 7/16/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Funding

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. The research of I. Yanovsky was also supported by the NSF grant DMS 2012868. The research of J. Qin was supported by the NSF grant DMS 1941197. The authors would like to thank Bjorn Lambrigtsen and Luminita Vese for their helpful discussions. 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. The research of I. Yanovsky was also supported by the NSF grant DMS 2012868. The research of J. Qin was supported by the NSF grant DMS 1941197.

Funders	Funder number
National Science Foundation (NSF)	DMS 1941197, DMS 2012868
National Aeronautics and Space Administration

Keywords

Alternating direction method of multipliers
Satellite images
Super-resolution
Upsampling

ASJC Scopus subject areas

Computer Science Applications
General Earth and Planetary Sciences

Access to Document

10.1109/IGARSS47720.2021.9553433

Cite this

@inproceedings{4a18d61a59f440e4820c5888728139f9,

title = "SPATIO-TEMPORAL SUPER-RESOLUTION RECONSTRUCTION OF REMOTE SENSING DATA",

abstract = "We present a spatio-temporal super-resolution method for reconstructing a sequence of observations collected by imaging satellites. A sequence of observations is assumed to be defined on a low resolution spatio-temporal grid. It is further assumed that the sequence is generated by blurring of a captured scene with a spatio-temporal convolution kernel and is degraded by noise. Our method simultaneously exhibits deconvolution of the sequence of images from the effects of spatio-temporal blur, denoising of the data, and upsampling of the low-resolution sequence to a high resolution spatio-temporal grid. We perform the super-resolution in the space-time domain, as opposed to super-resolving the sequence separately and sequentially to a higher spatial and then temporal resolution grid. Simultaneous space-time optimization achieves a more efficient and more accurate reconstruction than reconstructing a sequence frame by frame. The proposed super-resolution methodology is based on total variation regularization and computes the solution using the alternating direction method of multipliers. Numerical results show our approach to be robust and computationally efficient.",

keywords = "Alternating direction method of multipliers, Satellite images, Super-resolution, Upsampling",

author = "Igor Yanovsky and Jing Qin",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021 ; Conference date: 12-07-2021 Through 16-07-2021",

year = "2021",

doi = "10.1109/IGARSS47720.2021.9553433",

language = "English",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

pages = "2907--2910",

booktitle = "IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings",

}

Yanovsky, I & Qin, J 2021, SPATIO-TEMPORAL SUPER-RESOLUTION RECONSTRUCTION OF REMOTE SENSING DATA. in IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2021-July, pp. 2907-2910, 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021, Brussels, Belgium, 7/12/21. https://doi.org/10.1109/IGARSS47720.2021.9553433

SPATIO-TEMPORAL SUPER-RESOLUTION RECONSTRUCTION OF REMOTE SENSING DATA. / Yanovsky, Igor; Qin, Jing.
IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. 2021. p. 2907-2910 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2021-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - SPATIO-TEMPORAL SUPER-RESOLUTION RECONSTRUCTION OF REMOTE SENSING DATA

AU - Yanovsky, Igor

AU - Qin, Jing

PY - 2021

Y1 - 2021

N2 - We present a spatio-temporal super-resolution method for reconstructing a sequence of observations collected by imaging satellites. A sequence of observations is assumed to be defined on a low resolution spatio-temporal grid. It is further assumed that the sequence is generated by blurring of a captured scene with a spatio-temporal convolution kernel and is degraded by noise. Our method simultaneously exhibits deconvolution of the sequence of images from the effects of spatio-temporal blur, denoising of the data, and upsampling of the low-resolution sequence to a high resolution spatio-temporal grid. We perform the super-resolution in the space-time domain, as opposed to super-resolving the sequence separately and sequentially to a higher spatial and then temporal resolution grid. Simultaneous space-time optimization achieves a more efficient and more accurate reconstruction than reconstructing a sequence frame by frame. The proposed super-resolution methodology is based on total variation regularization and computes the solution using the alternating direction method of multipliers. Numerical results show our approach to be robust and computationally efficient.

AB - We present a spatio-temporal super-resolution method for reconstructing a sequence of observations collected by imaging satellites. A sequence of observations is assumed to be defined on a low resolution spatio-temporal grid. It is further assumed that the sequence is generated by blurring of a captured scene with a spatio-temporal convolution kernel and is degraded by noise. Our method simultaneously exhibits deconvolution of the sequence of images from the effects of spatio-temporal blur, denoising of the data, and upsampling of the low-resolution sequence to a high resolution spatio-temporal grid. We perform the super-resolution in the space-time domain, as opposed to super-resolving the sequence separately and sequentially to a higher spatial and then temporal resolution grid. Simultaneous space-time optimization achieves a more efficient and more accurate reconstruction than reconstructing a sequence frame by frame. The proposed super-resolution methodology is based on total variation regularization and computes the solution using the alternating direction method of multipliers. Numerical results show our approach to be robust and computationally efficient.

KW - Alternating direction method of multipliers

KW - Satellite images

KW - Super-resolution

KW - Upsampling

UR - https://www.scopus.com/pages/publications/85126013137

UR - https://www.scopus.com/inward/citedby.url?scp=85126013137&partnerID=8YFLogxK

U2 - 10.1109/IGARSS47720.2021.9553433

DO - 10.1109/IGARSS47720.2021.9553433

M3 - Conference contribution

AN - SCOPUS:85126013137

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 2907

EP - 2910

BT - IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium, Proceedings

T2 - 2021 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021

Y2 - 12 July 2021 through 16 July 2021

ER -

SPATIO-TEMPORAL SUPER-RESOLUTION RECONSTRUCTION OF REMOTE SENSING DATA

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this