Home > Research > Publications & Outputs > Real-Time Spatiotemporal Spectral Unmixing of M...

Links

Text available via DOI:

View graph of relations

Real-Time Spatiotemporal Spectral Unmixing of MODIS Images

Research output: Contribution to journalJournal articlepeer-review

E-pub ahead of print

Standard

Real-Time Spatiotemporal Spectral Unmixing of MODIS Images. / Wang, Q.; Ding, X.; Tong, X.; Atkinson, P.M.

In: IEEE Transactions on Geoscience and Remote Sensing, 02.09.2021.

Research output: Contribution to journalJournal articlepeer-review

Harvard

Wang, Q, Ding, X, Tong, X & Atkinson, PM 2021, 'Real-Time Spatiotemporal Spectral Unmixing of MODIS Images', IEEE Transactions on Geoscience and Remote Sensing. https://doi.org/10.1109/TGRS.2021.3108540

APA

Vancouver

Wang Q, Ding X, Tong X, Atkinson PM. Real-Time Spatiotemporal Spectral Unmixing of MODIS Images. IEEE Transactions on Geoscience and Remote Sensing. 2021 Sep 2. https://doi.org/10.1109/TGRS.2021.3108540

Author

Wang, Q. ; Ding, X. ; Tong, X. ; Atkinson, P.M. / Real-Time Spatiotemporal Spectral Unmixing of MODIS Images. In: IEEE Transactions on Geoscience and Remote Sensing. 2021.

Bibtex

@article{e67db76359ab4112a5876aa901b58338,
title = "Real-Time Spatiotemporal Spectral Unmixing of MODIS Images",
abstract = "Mixed pixels are a ubiquitous problem in remote sensing images. Spectral unmixing has been used widely for mixed pixel analysis. However, up to now, most spectral unmixing methods require endmembers and cannot consider fully intraclass spectral variation. The recently proposed spatiotemporal spectral unmixing (STSU) method copes with the aforementioned problems through exploitation of the available temporal information. However, this method requires coarse-to-fine spatial image pairs both before and after the prediction time and is, thus, not suitable for important real-time applications (i.e., where the fine spatial resolution data after the prediction time are unknown). In this article, we proposed a real-time STSU (RSTSU) method for real-time monitoring. RSTSU requires only a single coarse-to-fine spatial resolution image pair before, and temporally closest to, the prediction time, coupled with the coarse image at the prediction time, to extract samples automatically to train a learning model. By fully incorporating the multiscale spatiotemporal information, the RSTSU method inherits the key advantages of STSU; it does not need endmembers and can account for intraclass spectral variation. More importantly, RSTSU is suitable for real-time analysis and, thus, facilitates the timely monitoring of land cover changes. The effectiveness of the method was validated by experiments on four Moderate Resolution Imaging Spectroradiometer (MODIS) datasets. RSTSU utilizes and enriches the theory underpinning the advanced STSU method and enhances greatly the applicability of spectral unmixing for time-series data. ",
keywords = "Artificial satellites, Earth, Machine learning, MODIS, real time, Real-time systems, Remote sensing, Spatial resolution, spatiotemporal spectral unmixing (STSU), spectral unmixing., Training, Forecasting, Image resolution, Pixels, Mixed pixel analysis, Moderate resolution imaging spectroradiometer, Real time monitoring, Real-time application, Remote sensing images, Spatial resolution images, Spatiotemporal information, Temporal information, Radiometers",
author = "Q. Wang and X. Ding and X. Tong and P.M. Atkinson",
year = "2021",
month = sep,
day = "2",
doi = "10.1109/TGRS.2021.3108540",
language = "English",
journal = "IEEE Transactions on Geoscience and Remote Sensing",
issn = "0196-2892",
publisher = "IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC",

}

RIS

TY - JOUR

T1 - Real-Time Spatiotemporal Spectral Unmixing of MODIS Images

AU - Wang, Q.

AU - Ding, X.

AU - Tong, X.

AU - Atkinson, P.M.

PY - 2021/9/2

Y1 - 2021/9/2

N2 - Mixed pixels are a ubiquitous problem in remote sensing images. Spectral unmixing has been used widely for mixed pixel analysis. However, up to now, most spectral unmixing methods require endmembers and cannot consider fully intraclass spectral variation. The recently proposed spatiotemporal spectral unmixing (STSU) method copes with the aforementioned problems through exploitation of the available temporal information. However, this method requires coarse-to-fine spatial image pairs both before and after the prediction time and is, thus, not suitable for important real-time applications (i.e., where the fine spatial resolution data after the prediction time are unknown). In this article, we proposed a real-time STSU (RSTSU) method for real-time monitoring. RSTSU requires only a single coarse-to-fine spatial resolution image pair before, and temporally closest to, the prediction time, coupled with the coarse image at the prediction time, to extract samples automatically to train a learning model. By fully incorporating the multiscale spatiotemporal information, the RSTSU method inherits the key advantages of STSU; it does not need endmembers and can account for intraclass spectral variation. More importantly, RSTSU is suitable for real-time analysis and, thus, facilitates the timely monitoring of land cover changes. The effectiveness of the method was validated by experiments on four Moderate Resolution Imaging Spectroradiometer (MODIS) datasets. RSTSU utilizes and enriches the theory underpinning the advanced STSU method and enhances greatly the applicability of spectral unmixing for time-series data.

AB - Mixed pixels are a ubiquitous problem in remote sensing images. Spectral unmixing has been used widely for mixed pixel analysis. However, up to now, most spectral unmixing methods require endmembers and cannot consider fully intraclass spectral variation. The recently proposed spatiotemporal spectral unmixing (STSU) method copes with the aforementioned problems through exploitation of the available temporal information. However, this method requires coarse-to-fine spatial image pairs both before and after the prediction time and is, thus, not suitable for important real-time applications (i.e., where the fine spatial resolution data after the prediction time are unknown). In this article, we proposed a real-time STSU (RSTSU) method for real-time monitoring. RSTSU requires only a single coarse-to-fine spatial resolution image pair before, and temporally closest to, the prediction time, coupled with the coarse image at the prediction time, to extract samples automatically to train a learning model. By fully incorporating the multiscale spatiotemporal information, the RSTSU method inherits the key advantages of STSU; it does not need endmembers and can account for intraclass spectral variation. More importantly, RSTSU is suitable for real-time analysis and, thus, facilitates the timely monitoring of land cover changes. The effectiveness of the method was validated by experiments on four Moderate Resolution Imaging Spectroradiometer (MODIS) datasets. RSTSU utilizes and enriches the theory underpinning the advanced STSU method and enhances greatly the applicability of spectral unmixing for time-series data.

KW - Artificial satellites

KW - Earth

KW - Machine learning

KW - MODIS

KW - real time

KW - Real-time systems

KW - Remote sensing

KW - Spatial resolution

KW - spatiotemporal spectral unmixing (STSU)

KW - spectral unmixing.

KW - Training

KW - Forecasting

KW - Image resolution

KW - Pixels

KW - Mixed pixel analysis

KW - Moderate resolution imaging spectroradiometer

KW - Real time monitoring

KW - Real-time application

KW - Remote sensing images

KW - Spatial resolution images

KW - Spatiotemporal information

KW - Temporal information

KW - Radiometers

U2 - 10.1109/TGRS.2021.3108540

DO - 10.1109/TGRS.2021.3108540

M3 - Journal article

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

SN - 0196-2892

ER -