Spectral Unmixing with Estimated Adaptive Endmember Index Using Extended Support Vector Machine

Sarker, Chandrama; Jia, Xiuping; Wang, Liguo; Fraser, Donald; Lymburner, Leo

doi:10.1007/978-94-017-9771-9_3

Cited by 3 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the success of SU is highly dependent on the quality of spectral endmembers. Selecting pure endmembers in vegetated floodplains is particularly difficult [25,30]. This is demonstrated in Figure 14a,b, where both the low (MERIS) and highresolution (TM) data contain , even in the areas with dense vegetation.…”

Section: Discussionmentioning

confidence: 99%

“…The reflectance of a pixel in a particular spectral band may be represented as the sum of the reflectance values of all subpixel components (endmembers) in that band, weighted by the fractional abundance of each component [22][23][24]. To deal with the mixed pixel challenge, several approaches such as spectral unmixing [25], fuzzy c-means (FCM) and possibilistic c-means (PCM) [26], and Bayesian unmixing models [27] have been developed to attribute the fractions of each pixel to classes.…”

Section: Introductionmentioning

confidence: 99%

“…Spectral unmixing (SU) is one of the most popular techniques used for analyzing mixed pixels and has been used in studies to derive flood maps in areas where water was partly covered by vegetation [20,23,25]. SU is the procedure by which the measured spectrum of a pixel is decomposed into a collection of spectral endmembers and a set of corresponding fractional abundances within the pixel [22,24,28].…”

Section: Introductionmentioning

confidence: 99%

“…As a rule, the endmembers must be fewer than the number of spectral bands, and all of the endmembers in the image must be specified. A method to improve the selection of endmembers by an adaptive procedure was presented by [25]. This method improved flood mapping on three different sets of Landsat TM images of three different flood events in Australia.…”

Section: Introductionmentioning

confidence: 99%

“…A comparison of linear and nonlinear unmixing was done by [33] and the study concluded that nonlinear approaches deal better with complex and mixed vegetation surfaces. For the sake of brevity, the reader is referred to [25,28,33,34] for an overview, examples and comparison of SU methods. Although both linear and nonlinear approaches have achieved significant progress in decomposing mixed spectral signals, a robust technique does not yet exist, leaving end-users with the difficult task of selecting the most appropriate approach [24].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Spectral Unmixing Method with Ensemble Estimation of Endmembers: Application to Flood Mapping in the Caprivi Floodplain

et al. 2017

View full text Add to dashboard Cite

The Caprivi basin in Namibia has been affected by severe flooding in recent years resulting in deaths, displacements and destruction of infrastructure. The negative consequences of these floods have emphasized the need for timely, accurate and objective information about the extent and location of affected areas. Due to the high temporal variability of flood events, Earth Observation (EO) data at high revisit frequency is preferred for accurate flood monitoring. Currently, EO data has either high temporal or coarse spatial resolution. Accurate methodologies for the estimation and monitoring of flooding extent using coarse spatial resolution optical image data are needed in order to capture spatial details in heterogeneous areas such as Caprivi. The objective of this work was the retrieval of the fractional abundance of water (γ w ) by applying a new spectral indices-based unmixing algorithm to Medium Resolution Imaging Spectrometer Full Resolution (MERIS FR) data using a minimum number of spectral bands. These images are technically similar to the OLCI image data acquired by the Sentinel-3 satellite, which are to be systematically provided in the near future. The normalized difference wetness index (NDWI) was applied to delineate the water surface and combined with normalized difference vegetation index (NDVI) to account for emergent vegetation within the water bodies. The challenge to map flooded areas by applying spectral unmixing is the estimation of spectral endmembers, i.e., pure spectra of land cover features. In our study, we developed and applied a new unmixing method based on the use of an ensemble of spectral endmembers to capture and take into account spectral variability within each endmember. In our case study, forty realizations of the spectral endmembers gave a stable frequency distribution of γ w . Quality of the flood map derived from the Envisat MERIS (MERIS) data was assessed against high (30 m) spatial resolution Landsat Thematic Mapper (TM) images on two different dates (17 April 2008 and 22 May 2009) during which floods occurred. The findings show that both the spatial and the frequency distribution of the γ w extracted from the MERIS data were in good agreement with the high-resolution TM retrievals. The use of conventional linear unmixing, instead, applied using the entire available spectra for each image, resulted in relatively large differences between TM and MERIS retrievals.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Spectral Unmixing Method with Ensemble Estimation of Endmembers: Application to Flood Mapping in the Caprivi Floodplain

et al. 2017

View full text Add to dashboard Cite

show abstract

The estimation of total suspended matter from satellite imagery of tropical coastal water Berau Estuary, Indonesia

Ambarwulan

Salama

Verhoef

et al. 2022

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Water in coastal and estuary areas needs to be investigated as human activities is allegedly decrease their quality. This has led to optical remote sensing for mapping optical water quality using empirical and semi-analytical approaches. Therefore, this study aims to estimate the Total Suspended Matter (TSM) concentration from Medium Resolution Imaging Spectrometer (MERIS) data using a spectral unmixing approach combined with a radiative transfer model. This approach was implemented in the equatorial tropical coastal water, the Berau estuary, Indonesia, by generating a look-up table (LUT) of top-of-atmosphere radiance spectra through the coupled forward models, and the endmembers were selected from the LUT. The spectral unmixing algorithm was employed to the MERIS data for decomposing the image into haze and sediment components. The data were then transformed into images of a constant haze level corresponding to 50 km visibility, and the atmospheric correction was applied. Furthermore, the TMS concentration was retrieved using the inverse semi-analytical Kubelka-Munk model. The result gave overestimated TSM concentration values on clear waters. However, in turbid waters, a lower RMSE was obtained, and the coefficient of determination was higher than in clear waters.

show abstract

Hyperspectral Anomaly Detection Through Spectral Unmixing and Dictionary-Based Low-Rank Decomposition

Wang

Guo

et al. 2018

IEEE Trans. Geosci. Remote Sensing

176

View full text Add to dashboard Cite

Spectral Unmixing with Estimated Adaptive Endmember Index Using Extended Support Vector Machine

Cited by 3 publications

References 12 publications

A Spectral Unmixing Method with Ensemble Estimation of Endmembers: Application to Flood Mapping in the Caprivi Floodplain

A Spectral Unmixing Method with Ensemble Estimation of Endmembers: Application to Flood Mapping in the Caprivi Floodplain

The estimation of total suspended matter from satellite imagery of tropical coastal water Berau Estuary, Indonesia

Hyperspectral Anomaly Detection Through Spectral Unmixing and Dictionary-Based Low-Rank Decomposition

Contact Info

Product

Resources

About