Tensor completion for on-board compression of hyperspectral images

Nan Li, Baoxin Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

31 Citations (Scopus)

Abstract

We present a new image compression scheme for hyperspectral images based on the newly-emerged matrix/tensor completion theory. Unlike typical transform-coding based methods, the proposed approach does not require any transform to be performed by the imaging sensor when doing on-board compression. Only a small set of pixels on a sparse set of locations on the imaging sensor needs to be captured and transmitted for each image. The decoder side relies on matrix/tensor completion for reconstructing the original images. Hence the scheme can drastically reduce the computation and bandwidth requirements on the on-board imaging sensors. Experiments show that the proposed method is able to obtain compression performance close to JPEG2000 while enjoying the afore-mentioned unique benefits.

Original languageEnglish (US)
Title of host publicationProceedings - International Conference on Image Processing, ICIP
Pages517-520
Number of pages4
DOIs
StatePublished - 2010
Event2010 17th IEEE International Conference on Image Processing, ICIP 2010 - Hong Kong, Hong Kong
Duration: Sep 26 2010Sep 29 2010

Other

Other2010 17th IEEE International Conference on Image Processing, ICIP 2010
CountryHong Kong
CityHong Kong
Period9/26/109/29/10

Fingerprint

Tensors
Imaging techniques
Sensors
Image compression
Pixels
Mathematical transformations
Bandwidth
Experiments

Keywords

  • Hyperspectral image compression
  • Matrix completion
  • Tensor completion

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Li, N., & Li, B. (2010). Tensor completion for on-board compression of hyperspectral images. In Proceedings - International Conference on Image Processing, ICIP (pp. 517-520). [5651225] https://doi.org/10.1109/ICIP.2010.5651225

Tensor completion for on-board compression of hyperspectral images. / Li, Nan; Li, Baoxin.

Proceedings - International Conference on Image Processing, ICIP. 2010. p. 517-520 5651225.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, N & Li, B 2010, Tensor completion for on-board compression of hyperspectral images. in Proceedings - International Conference on Image Processing, ICIP., 5651225, pp. 517-520, 2010 17th IEEE International Conference on Image Processing, ICIP 2010, Hong Kong, Hong Kong, 9/26/10. https://doi.org/10.1109/ICIP.2010.5651225
Li N, Li B. Tensor completion for on-board compression of hyperspectral images. In Proceedings - International Conference on Image Processing, ICIP. 2010. p. 517-520. 5651225 https://doi.org/10.1109/ICIP.2010.5651225
Li, Nan ; Li, Baoxin. / Tensor completion for on-board compression of hyperspectral images. Proceedings - International Conference on Image Processing, ICIP. 2010. pp. 517-520
@inproceedings{066c6b85f28a4f9c88630ea55bed25ec,
title = "Tensor completion for on-board compression of hyperspectral images",
abstract = "We present a new image compression scheme for hyperspectral images based on the newly-emerged matrix/tensor completion theory. Unlike typical transform-coding based methods, the proposed approach does not require any transform to be performed by the imaging sensor when doing on-board compression. Only a small set of pixels on a sparse set of locations on the imaging sensor needs to be captured and transmitted for each image. The decoder side relies on matrix/tensor completion for reconstructing the original images. Hence the scheme can drastically reduce the computation and bandwidth requirements on the on-board imaging sensors. Experiments show that the proposed method is able to obtain compression performance close to JPEG2000 while enjoying the afore-mentioned unique benefits.",
keywords = "Hyperspectral image compression, Matrix completion, Tensor completion",
author = "Nan Li and Baoxin Li",
year = "2010",
doi = "10.1109/ICIP.2010.5651225",
language = "English (US)",
isbn = "9781424479948",
pages = "517--520",
booktitle = "Proceedings - International Conference on Image Processing, ICIP",

}

TY - GEN

T1 - Tensor completion for on-board compression of hyperspectral images

AU - Li, Nan

AU - Li, Baoxin

PY - 2010

Y1 - 2010

N2 - We present a new image compression scheme for hyperspectral images based on the newly-emerged matrix/tensor completion theory. Unlike typical transform-coding based methods, the proposed approach does not require any transform to be performed by the imaging sensor when doing on-board compression. Only a small set of pixels on a sparse set of locations on the imaging sensor needs to be captured and transmitted for each image. The decoder side relies on matrix/tensor completion for reconstructing the original images. Hence the scheme can drastically reduce the computation and bandwidth requirements on the on-board imaging sensors. Experiments show that the proposed method is able to obtain compression performance close to JPEG2000 while enjoying the afore-mentioned unique benefits.

AB - We present a new image compression scheme for hyperspectral images based on the newly-emerged matrix/tensor completion theory. Unlike typical transform-coding based methods, the proposed approach does not require any transform to be performed by the imaging sensor when doing on-board compression. Only a small set of pixels on a sparse set of locations on the imaging sensor needs to be captured and transmitted for each image. The decoder side relies on matrix/tensor completion for reconstructing the original images. Hence the scheme can drastically reduce the computation and bandwidth requirements on the on-board imaging sensors. Experiments show that the proposed method is able to obtain compression performance close to JPEG2000 while enjoying the afore-mentioned unique benefits.

KW - Hyperspectral image compression

KW - Matrix completion

KW - Tensor completion

UR - http://www.scopus.com/inward/record.url?scp=78651077838&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78651077838&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2010.5651225

DO - 10.1109/ICIP.2010.5651225

M3 - Conference contribution

SN - 9781424479948

SP - 517

EP - 520

BT - Proceedings - International Conference on Image Processing, ICIP

ER -