Active Diffusion and VCA-Assisted Image Segmentation of Hyperspectral Images

Sam L. Polk; Kangning Cui; Robert J. Plemmons; James M. Murphy

doi:10.1109/IGARSS46834.2022.9883894

Active Diffusion and VCA-Assisted Image Segmentation of Hyperspectral Images

Sam L. Polk, Kangning Cui, Robert J. Plemmons, James M. Murphy^*

^*Corresponding author for this work

Department of Mathematics

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

5 Citations (Scopus)

Abstract

Hyperspectral images encode rich structure that can be ex-ploited for material discrimination by machine learning al-gorithms. This article introduces the Active Diffusion and VCA-Assisted Image Segmentation (ADVIS) for active mate-rial discrimination. ADVIS selects high-purity, high-density pixels that are far in diffusion distance (a data-dependent met-ric) from other high-purity, high-density pixels in the hyper-spectral image. The ground truth labels of these pixels are queried and propagated to the rest of the image. The ADVIS active learning algorithm is shown to strongly outperform its fully unsupervised clustering algorithm counterpart, suggesting that the incorporation of a very small number of carefully-selected ground truth labels can result in substantially supe-rior material discrimination in hyperspectral images.

Original language	English
Title of host publication	IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium
Subtitle of host publication	Proceedings
Publisher	IEEE
Pages	1364-1367
ISBN (Electronic)	978-1-6654-2792-0
DOIs	https://doi.org/10.1109/IGARSS46834.2022.9883894
Publication status	Published - 2022
Event	2022 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2022) - Kuala Lumpur Convention Centre & Virtual, Kuala Lumpur, Malaysia Duration: 17 Jul 2022 → 22 Jul 2022 https://igarss2022.org/#

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2022-July

Conference

Conference	2022 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2022)
Place	Malaysia
City	Kuala Lumpur
Period	17/07/22 → 22/07/22
Internet address	https://igarss2022.org/#

Research Keywords

Active Learning
Diffusion Geome-try
Hyperspectral Imagery
Image Segmentation
Semi-supervised Machine Learning

Access Output

10.1109/IGARSS46834.2022.9883894

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Polk, S. L., Cui, K., Plemmons, R. J., & Murphy, J. M. (2022). Active Diffusion and VCA-Assisted Image Segmentation of Hyperspectral Images. In IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium: Proceedings (pp. 1364-1367). (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2022-July). IEEE. https://doi.org/10.1109/IGARSS46834.2022.9883894

@inproceedings{8ce269221ea2462ba7945b7697cdfbd0,

title = "Active Diffusion and VCA-Assisted Image Segmentation of Hyperspectral Images",

abstract = "Hyperspectral images encode rich structure that can be ex-ploited for material discrimination by machine learning al-gorithms. This article introduces the Active Diffusion and VCA-Assisted Image Segmentation (ADVIS) for active mate-rial discrimination. ADVIS selects high-purity, high-density pixels that are far in diffusion distance (a data-dependent met-ric) from other high-purity, high-density pixels in the hyper-spectral image. The ground truth labels of these pixels are queried and propagated to the rest of the image. The ADVIS active learning algorithm is shown to strongly outperform its fully unsupervised clustering algorithm counterpart, suggesting that the incorporation of a very small number of carefully-selected ground truth labels can result in substantially supe-rior material discrimination in hyperspectral images.",

keywords = "Active Learning, Diffusion Geome-try, Hyperspectral Imagery, Image Segmentation, Semi-supervised Machine Learning",

author = "Polk, {Sam L.} and Kangning Cui and Plemmons, {Robert J.} and Murphy, {James M.}",

year = "2022",

doi = "10.1109/IGARSS46834.2022.9883894",

language = "English",

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

publisher = "IEEE",

pages = "1364--1367",

booktitle = "IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium",

address = "United States",

note = "2022 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2022) ; Conference date: 17-07-2022 Through 22-07-2022",

url = "https://igarss2022.org/#",

}

Polk, SL, Cui, K, Plemmons, RJ & Murphy, JM 2022, Active Diffusion and VCA-Assisted Image Segmentation of Hyperspectral Images. in IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium: Proceedings. International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2022-July, IEEE, pp. 1364-1367, 2022 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2022), Kuala Lumpur, Malaysia, 17/07/22. https://doi.org/10.1109/IGARSS46834.2022.9883894

Active Diffusion and VCA-Assisted Image Segmentation of Hyperspectral Images. / Polk, Sam L.; Cui, Kangning; Plemmons, Robert J. et al.
IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium: Proceedings. IEEE, 2022. p. 1364-1367 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2022-July).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Active Diffusion and VCA-Assisted Image Segmentation of Hyperspectral Images

AU - Polk, Sam L.

AU - Cui, Kangning

AU - Plemmons, Robert J.

AU - Murphy, James M.

PY - 2022

Y1 - 2022

N2 - Hyperspectral images encode rich structure that can be ex-ploited for material discrimination by machine learning al-gorithms. This article introduces the Active Diffusion and VCA-Assisted Image Segmentation (ADVIS) for active mate-rial discrimination. ADVIS selects high-purity, high-density pixels that are far in diffusion distance (a data-dependent met-ric) from other high-purity, high-density pixels in the hyper-spectral image. The ground truth labels of these pixels are queried and propagated to the rest of the image. The ADVIS active learning algorithm is shown to strongly outperform its fully unsupervised clustering algorithm counterpart, suggesting that the incorporation of a very small number of carefully-selected ground truth labels can result in substantially supe-rior material discrimination in hyperspectral images.

AB - Hyperspectral images encode rich structure that can be ex-ploited for material discrimination by machine learning al-gorithms. This article introduces the Active Diffusion and VCA-Assisted Image Segmentation (ADVIS) for active mate-rial discrimination. ADVIS selects high-purity, high-density pixels that are far in diffusion distance (a data-dependent met-ric) from other high-purity, high-density pixels in the hyper-spectral image. The ground truth labels of these pixels are queried and propagated to the rest of the image. The ADVIS active learning algorithm is shown to strongly outperform its fully unsupervised clustering algorithm counterpart, suggesting that the incorporation of a very small number of carefully-selected ground truth labels can result in substantially supe-rior material discrimination in hyperspectral images.

KW - Active Learning

KW - Diffusion Geome-try

KW - Hyperspectral Imagery

KW - Image Segmentation

KW - Semi-supervised Machine Learning

UR - http://www.scopus.com/inward/record.url?scp=85140360127&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85140360127&origin=recordpage

U2 - 10.1109/IGARSS46834.2022.9883894

DO - 10.1109/IGARSS46834.2022.9883894

M3 - RGC 32 - Refereed conference paper (with host publication)

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 1364

EP - 1367

BT - IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium

PB - IEEE

T2 - 2022 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2022)

Y2 - 17 July 2022 through 22 July 2022

ER -

Active Diffusion and VCA-Assisted Image Segmentation of Hyperspectral Images

Abstract

Publication series

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this