Wavelet-Based Feature Extraction for Improved Endmember Abundance Estimation in Linear Unmixing of Hyperspectral Signals

Jiang, Li

doi:10.1109/tgrs.2003.822750

Cited by 84 publications

(33 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…noise assumption. Note finally that the model in (1) can be easily modified (see [38]) to handle more complicated noise models with different variances in each spectral band as in [39], or by taking into account correlations between spectral bands as in [19]. (3) with random proportions to obtain P = 2500 pixels.…”

Section: Linear Mixing Model and Problem Statementmentioning

confidence: 99%

See 1 more Smart Citation

Joint Bayesian Endmember Extraction and Linear Unmixing for Hyperspectral Imagery

Dobigeon

Moussaoui

Coulon

et al. 2009

IEEE Trans. Signal Process.

333

288

View full text Add to dashboard Cite

Abstract-This paper studies a fully Bayesian algorithm for endmember extraction and abundance estimation for hyperspectral imagery. Each pixel of the hyperspectral image is decomposed as a linear combination of pure endmember spectra following the linear mixing model. The estimation of the unknown endmember spectra is conducted in a unified manner by generating the posterior distribution of abundances and endmember parameters under a hierarchical Bayesian model. This model assumes conjugate prior distributions for these parameters, accounts for nonnegativity and fulladditivity constraints, and exploits the fact that the endmember proportions lie on a lower dimensional simplex. A Gibbs sampler is proposed to overcome the complexity of evaluating the resulting posterior distribution. This sampler generates samples distributed according to the posterior distribution and estimates the unknown parameters using these generated samples. The accuracy of the joint Bayesian estimator is illustrated by simulations conducted on synthetic and real AVIRIS images.Index Terms-Bayesian inference, endmember extraction, hyperspectral imagery, linear spectral unmixing, MCMC methods.

show abstract

Section: Linear Mixing Model and Problem Statementmentioning

confidence: 99%

“…The conditional distribution of , , is the following inverse Gamma distribution: (39) Simulating according to this inverse Gamma distribution can be achieved using a Gamma variate generator (see [53,Ch. 9…”

Section: Sampling Frommentioning

confidence: 99%

Joint Bayesian Endmember Extraction and Linear Unmixing for Hyperspectral Imagery

Dobigeon

Moussaoui

Coulon

et al. 2009

IEEE Trans. Signal Process.

333

288

View full text Add to dashboard Cite

show abstract

“…Data reduction techniques are therefore often applied imaging spectroscopy data sets prior to SMA [36]; two of the more common are Principal Component Analysis (PCA; [40]) and maximum noise fraction (MNF; [41]). PCA, MNF, and similar techniques reduce data dimensionality based on the spectral properties of the image; however, they do not necessarily do so in a manner that improves separability between endmember classes [42]. Asner and Lobell [43] proposed a data reduction technique designed specifically to improve the accuracy of SMA when applied to plant cover with AutoSWIR.…”

Section: Introductionmentioning

confidence: 99%

Evaluating Endmember and Band Selection Techniques for Multiple Endmember Spectral Mixture Analysis using Post-Fire Imaging Spectroscopy

et al. 2018

View full text Add to dashboard Cite

Abstract:Fire impacts many vegetated ecosystems across the world. The severity of a fire is major component in determining post-fire effects, including soil erosion, trace gas emissions, and the trajectory of recovery. In this study, we used imaging spectroscopy data combined with Multiple Endmember Spectral Mixture Analysis (MESMA), a form of spectral mixture analysis that accounts for endmember variability, to map fire severity of the 2013 Rim Fire. We evaluated four endmember selection approaches: Iterative Endmember Selection (IES), count-based within endmember class (In-CoB), Endmember Average Root Mean Squared Error (EAR), and Minimum Average Spectral Angle (MASA). To reduce the dimensionality of the imaging spectroscopy data we used uncorrelated Stable Zone Unmixing (uSZU). Fractional cover maps derived from MESMA were validated using two approaches: (1) manual interpretation of fine spatial resolution WorldView-2 imagery; and (2) ground plots measuring the Geo Composite Burn Index (GeoCBI) and the percentage of co-dominant and dominant trees with green, brown, and black needles. Comparison to reference data demonstrated fairly high correlation for green vegetation and char fractions (r 2 values as high as 0.741 for the MESMA ash fractions compared to classified WorldView-2 imagery and as high as 0.841 for green vegetation fractions). The combination of uSZU band selection and In-CoB endmember selection had the best trade-off between accuracy and computational efficiency. This study demonstrated that detailed fire severity retrievals based on imaging spectroscopy can be optimized using techniques that would be viable also in a satellite-based imaging spectrometer.

show abstract

“…Wavelet transforms have been used in the remote sensing community for image blending (GarguetDuport et al, 1996;Zhou et al, 1998), for detection of haze (Du et al, 2002), spectral unmixing of hyperspectral data (Li, 2004), post-classification change detection (Raja, 2013), and feature extraction (Fukuda and Hirosawa, 1999;Niedermeier et al, 2000;Simhadri et al, 1998). In relation to vegetation dynamics, Sakamoto et al (2005) developed a method for detection of crop phenology incorporating wavelet filters.…”

Section: Wavelet Transforms In Remote Sensing and Forestry Applicationsmentioning

confidence: 99%

“…To fit the model, a cross-validation process with ten iterations was performed and to avoid over-fitting, we considered the establishment of a minimum number of cases in terminal nodes and pruning with the 1 standard error rule (Breiman et al, 1984). TCA 1984, 1990, 2004, 2009NDVI 1984, 1990, 2004, 2009TCD 1984, 1990, 2004 …”

Section: Agb (1 To 350 T Ha -1mentioning

confidence: 99%

Historical forest biomass dynamics modelled with Landsat spectral trajectories

Gómez¹,

White²,

Wulder³

et al. 2014

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

Wavelet-Based Feature Extraction for Improved Endmember Abundance Estimation in Linear Unmixing of Hyperspectral Signals

Cited by 84 publications

References 16 publications

Joint Bayesian Endmember Extraction and Linear Unmixing for Hyperspectral Imagery

Joint Bayesian Endmember Extraction and Linear Unmixing for Hyperspectral Imagery

Evaluating Endmember and Band Selection Techniques for Multiple Endmember Spectral Mixture Analysis using Post-Fire Imaging Spectroscopy

Historical forest biomass dynamics modelled with Landsat spectral trajectories

Contact Info

Product

Resources

About