TY - JOUR

T1 - Spatio-temporal spectral unmixing of time-series images

AU - Wang, Q.

AU - Ding, X.

AU - Tong, X.

AU - Atkinson, P.M.

PY - 2021/6/15

Y1 - 2021/6/15

N2 - Mixed pixels exist widely in remotely sensed images. To obtain more reliable land cover information than traditional hard classification, spectral unmixing methods have been developed to estimate the composition of the mixed pixels, in terms of the proportions of land cover classes. The existing spectral unmixing methods usually require pure spectra (i.e., endmembers) of each land cover class. However, in areas dominated by mixed pixels (e.g., highly heterogeneous areas), it can be a great challenge to extract a large number of pure endmembers, especially for long time-series data. Meanwhile, intra-class spectral variation remains a long-standing issue in spectral unmixing. In this paper, we propose a spatio-temporal spectral unmixing (STSU) approach to address these issues. The proposed method extends spectral unmixing from the traditional spatial domain to the spatio-temporal domain. It exploits fully the multi-scale spatio-temporal information, by using temporally neighboring fine spatial resolution images to detect land cover changes and, further, extracts the proportion information of unchanged mixed pixels required for training. The STSU method is free of the need for endmember extraction, using directly the extracted mixed training samples to construct a learning model, and it accounts for intra-class spectral variation. Therefore, it is a fully automatic method suitable for dynamic monitoring of land cover changes. The effectiveness of the STSU method was validated through experiments on Moderate Resolution Imaging Spectroradiometer (MODIS) data in five different areas. The proposed STSU method provides a new solution for spectral unmixing of time-series data based on the goal of continuous monitoring at the global scale.

AB - Mixed pixels exist widely in remotely sensed images. To obtain more reliable land cover information than traditional hard classification, spectral unmixing methods have been developed to estimate the composition of the mixed pixels, in terms of the proportions of land cover classes. The existing spectral unmixing methods usually require pure spectra (i.e., endmembers) of each land cover class. However, in areas dominated by mixed pixels (e.g., highly heterogeneous areas), it can be a great challenge to extract a large number of pure endmembers, especially for long time-series data. Meanwhile, intra-class spectral variation remains a long-standing issue in spectral unmixing. In this paper, we propose a spatio-temporal spectral unmixing (STSU) approach to address these issues. The proposed method extends spectral unmixing from the traditional spatial domain to the spatio-temporal domain. It exploits fully the multi-scale spatio-temporal information, by using temporally neighboring fine spatial resolution images to detect land cover changes and, further, extracts the proportion information of unchanged mixed pixels required for training. The STSU method is free of the need for endmember extraction, using directly the extracted mixed training samples to construct a learning model, and it accounts for intra-class spectral variation. Therefore, it is a fully automatic method suitable for dynamic monitoring of land cover changes. The effectiveness of the STSU method was validated through experiments on Moderate Resolution Imaging Spectroradiometer (MODIS) data in five different areas. The proposed STSU method provides a new solution for spectral unmixing of time-series data based on the goal of continuous monitoring at the global scale.

KW - Change detection

KW - Spatio-temporal domain

KW - Spectral unmixing

KW - Support vector machines (SVM)

KW - Time-series

KW - Classification (of information)

KW - Data mining

KW - Extraction

KW - Pixels

KW - Radiometers

KW - Support vector machines

KW - Endmembers

KW - Land cover

KW - Mixed pixel

KW - Spatio-temporal

KW - Spatio-temporal domains

KW - Support vector machine

KW - Time-series data

KW - Times series

KW - Time series

KW - detection method

KW - image analysis

KW - land cover

KW - MODIS

KW - pixel

KW - remote sensing

KW - satellite data

KW - spatial resolution

KW - time series analysis

U2 - 10.1016/j.rse.2021.112407

DO - 10.1016/j.rse.2021.112407

M3 - Journal article

VL - 259

JO - Remote Sensing of Environment

JF - Remote Sensing of Environment

SN - 0034-4257

M1 - 112407

ER -