Home > Research > Publications & Outputs > Fast and Slow Changes Constrained Spatio-tempor...

Electronic data

  • Final

    Rights statement: ©2022 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

    Accepted author manuscript, 2.87 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Fast and Slow Changes Constrained Spatio-temporal Subpixel Mapping

Research output: Contribution to Journal/MagazineJournal articlepeer-review

E-pub ahead of print

Standard

Fast and Slow Changes Constrained Spatio-temporal Subpixel Mapping. / Zhang, C.; Wang, Q.; Lu, P.; Ge, Y.; Atkinson, P.M.

In: IEEE Transactions on Geoscience and Remote Sensing, 07.12.2021.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Zhang C, Wang Q, Lu P, Ge Y, Atkinson PM. Fast and Slow Changes Constrained Spatio-temporal Subpixel Mapping. IEEE Transactions on Geoscience and Remote Sensing. 2021 Dec 7. https://doi.org/10.1109/TGRS.2021.3133534

Author

Zhang, C. ; Wang, Q. ; Lu, P. ; Ge, Y. ; Atkinson, P.M. / Fast and Slow Changes Constrained Spatio-temporal Subpixel Mapping. In: IEEE Transactions on Geoscience and Remote Sensing. 2021.

Bibtex

@article{22c9672947d04bc9ad7a5b2c7850895b,
title = "Fast and Slow Changes Constrained Spatio-temporal Subpixel Mapping",
abstract = "Subpixel mapping (SPM) is a technique to tackle the mixed pixel problem and produce land cover and land use (LCLU) maps at a finer spatial resolution than the original coarse data. However, uncertainty exists unavoidably in SPM, which is an ill-posed downscaling problem. Spatio-temporal SPM methods have been proposed to deal with this uncertainty, but current methods fail to explore fully the information in the time-series images, especially more rapid changes over a short-time interval. In this paper, a fast and slow changes constrained spatio-temporal subpixel mapping (FSSTSPM) method is proposed to account for fast LCLU changes over a short-time interval and slow changes over a long-time interval. Namely, both fast and slow change-based temporal constraints are proposed and incorporated simultaneously into the FSSTSPM to increase the accuracy of SPM. The proposed FSSTSPM method was validated using two synthetic datasets with various proportion errors. It was also applied to oil-spill mapping using a real PlanetScope-Sentinel-2 dataset and Amazon deforestation mapping using a real Landsat-MODIS dataset. The results demonstrate the superiority of FSSTSPM. Moreover, the advantage of FSSTSPM is more obvious with an increase in proportion errors. The concepts of the fast and slow changes, together with the derived temporal constraints, provide a new insight to enhance SPM by taking fuller advantage of the temporal information in the available time-series images. ",
keywords = "downscaling, Hopfield neural network (HNN), Image resolution, Land cover and land use (LCLU), Monitoring, Neurons, Remote sensing, Satellites, Spatial resolution, spatio-temporal dependence, subpixel mapping (SPM), super-resolution mapping, Uncertainty",
author = "C. Zhang and Q. Wang and P. Lu and Y. Ge and P.M. Atkinson",
note = "{\textcopyright}2022 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. ",
year = "2021",
month = dec,
day = "7",
doi = "10.1109/TGRS.2021.3133534",
language = "English",
journal = "IEEE Transactions on Geoscience and Remote Sensing",
issn = "0196-2892",
publisher = "IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC",

}

RIS

TY - JOUR

T1 - Fast and Slow Changes Constrained Spatio-temporal Subpixel Mapping

AU - Zhang, C.

AU - Wang, Q.

AU - Lu, P.

AU - Ge, Y.

AU - Atkinson, P.M.

N1 - ©2022 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 2021/12/7

Y1 - 2021/12/7

N2 - Subpixel mapping (SPM) is a technique to tackle the mixed pixel problem and produce land cover and land use (LCLU) maps at a finer spatial resolution than the original coarse data. However, uncertainty exists unavoidably in SPM, which is an ill-posed downscaling problem. Spatio-temporal SPM methods have been proposed to deal with this uncertainty, but current methods fail to explore fully the information in the time-series images, especially more rapid changes over a short-time interval. In this paper, a fast and slow changes constrained spatio-temporal subpixel mapping (FSSTSPM) method is proposed to account for fast LCLU changes over a short-time interval and slow changes over a long-time interval. Namely, both fast and slow change-based temporal constraints are proposed and incorporated simultaneously into the FSSTSPM to increase the accuracy of SPM. The proposed FSSTSPM method was validated using two synthetic datasets with various proportion errors. It was also applied to oil-spill mapping using a real PlanetScope-Sentinel-2 dataset and Amazon deforestation mapping using a real Landsat-MODIS dataset. The results demonstrate the superiority of FSSTSPM. Moreover, the advantage of FSSTSPM is more obvious with an increase in proportion errors. The concepts of the fast and slow changes, together with the derived temporal constraints, provide a new insight to enhance SPM by taking fuller advantage of the temporal information in the available time-series images.

AB - Subpixel mapping (SPM) is a technique to tackle the mixed pixel problem and produce land cover and land use (LCLU) maps at a finer spatial resolution than the original coarse data. However, uncertainty exists unavoidably in SPM, which is an ill-posed downscaling problem. Spatio-temporal SPM methods have been proposed to deal with this uncertainty, but current methods fail to explore fully the information in the time-series images, especially more rapid changes over a short-time interval. In this paper, a fast and slow changes constrained spatio-temporal subpixel mapping (FSSTSPM) method is proposed to account for fast LCLU changes over a short-time interval and slow changes over a long-time interval. Namely, both fast and slow change-based temporal constraints are proposed and incorporated simultaneously into the FSSTSPM to increase the accuracy of SPM. The proposed FSSTSPM method was validated using two synthetic datasets with various proportion errors. It was also applied to oil-spill mapping using a real PlanetScope-Sentinel-2 dataset and Amazon deforestation mapping using a real Landsat-MODIS dataset. The results demonstrate the superiority of FSSTSPM. Moreover, the advantage of FSSTSPM is more obvious with an increase in proportion errors. The concepts of the fast and slow changes, together with the derived temporal constraints, provide a new insight to enhance SPM by taking fuller advantage of the temporal information in the available time-series images.

KW - downscaling

KW - Hopfield neural network (HNN)

KW - Image resolution

KW - Land cover and land use (LCLU)

KW - Monitoring

KW - Neurons

KW - Remote sensing

KW - Satellites

KW - Spatial resolution

KW - spatio-temporal dependence

KW - subpixel mapping (SPM)

KW - super-resolution mapping

KW - Uncertainty

U2 - 10.1109/TGRS.2021.3133534

DO - 10.1109/TGRS.2021.3133534

M3 - Journal article

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

SN - 0196-2892

ER -