Nonlinear Hyperspectral Mixture Analysis for tree cover estimates in orchards

Somers, Ben; Cools, Kenneth; Delalieux, Stephanie; Stuckens, Jan; Zande, Dimitry Van der; Verstraeten, Willem; Coppin, Pol

doi:10.1016/j.rse.2009.02.003

Cited by 181 publications

(139 citation statements)

References 50 publications

Supporting

Mentioning

133

Contrasting

Order By: Relevance

“…However, the LMM can be inappropriate for some hyperspectral images where the detected photons interact with multiple components before they reach the sensor. In this case, nonlinear models can be more interesting for abundance estimation, e.g., for scenes including mixtures of orchards [2] or vegetation [3]. This paper considers a generalized bilinear model (GBM) introduced in [4] for nonlinear unmixing of hyperspectral images.…”

Section: Introductionmentioning

confidence: 99%

Nonlinear unmixing of hyperspectral images using a generalized bilinear model

Halimi

Altmann

Dobigeon

et al. 2011

2011 IEEE Statistical Signal Processing Workshop (SSP)

120

240

View full text Add to dashboard Cite

Nonlinear models have recently shown interesting properties for spectral unmixing. This paper considers a generalized bilinear model recently introduced for unmixing hyperspectral images. Different algorithms are studied to estimate the parameters of this bilinear model. The positivity and sum-to-one constraints for the abundances are ensured by the proposed algorithms. The performance of the resulting unmixing strategy is evaluated via simulations conducted on synthetic and real data.Index Terms-hyperspectral imagery, spectral unmixing, bilinear model, Bayesian inference, MCMC methods, gradient descent algorithm, least square algorithm.

show abstract

Section: Introductionmentioning

confidence: 99%

Nonlinear unmixing of hyperspectral images using a generalized bilinear model

Halimi

Altmann

Dobigeon

et al. 2011

2011 IEEE Statistical Signal Processing Workshop (SSP)

120

240

View full text Add to dashboard Cite

show abstract

“…Using the minimum mean squared error (MMSE) criterion, the predictorŷ g of y is defined as the mean of the predictive distribution in (8). Thus the GP estimatorŷ g of the observation y iŝ…”

Section: Gp Regressionmentioning

confidence: 99%

“…The simplest of these models assumes linear mixing of the endmember contributions [3] (Linear Mixing Model -LMM). However, it has been recognized that the mixing in some pixels of a region is actually nonlinear [3][4][5][6][7][8][9][10][11]. This finding has triggered a plethora of techniques for analyzing nonlinearly mixed pixels (see for instance [4,5] and references therein).…”

Section: Introductionmentioning

confidence: 99%

Detection of nonlinear mixtures using Gaussian processes: Application to hyperspectral imaging

Imbiriba

Bermudez

Tourneret

et al. 2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This paper investigates the use of Gaussian processes to detect nonlinearly mixed pixels in hyperspectral images. The proposed technique is independent of nonlinear mixing mechanism, and therefore is not restricted to any prescribed nonlinear mixing model. The observed reflectances are estimated using both the least squares method and a Gaussian process. The fitting errors of the two approaches are combined in a test statistics for which it is possible to estimate a detection threshold for a required probability of false alarm. The proposed detector is compared to a robust nonlinearity detector recently proposed using synthetic data and is shown to lead to a better detection performance. The new detector is also tested on a real hyperspectral image.

show abstract

“…Finally, we consider 5) the K-Hype method [8] to compare our algorithm with a state-of-the art kernel based unmixing method. The kernel used in this paper is the polynomial, second order symmetric kernel whose Gram matrix is defined by (5). This kernel provides better performance on this data set than the kernels studied in [8].…”

Section: Simulations: Real Hyperspectral Imagementioning

confidence: 99%

“…They have been proposed in the hyperspectral image literature and can be divided into two main classes [3]. The first class of NLMMs consists of physical models based on the nature of the environment (e.g., intimate mixtures [4] and multiple scattering effects [5,6,7]). The second class of NLMMs contains more flexible models allowing different kinds of nonlinearities to be approximated.…”

Section: Introductionmentioning

confidence: 99%

Residual component analysis of hyperspectral images for joint nonlinear unmixing and nonlinearity detection

Altmann

Dobigeon

McLaughlin

et al. 2014

2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

This paper presents a nonlinear mixing model for joint hyperspectral image unmixing and nonlinearity detection. The proposed model assumes that the pixel reflectances are linear mixtures of endmembers, corrupted by an additional nonlinear term and an additive Gaussian noise. A Markov random field is considered for nonlinearity detection based on the spatial structure of the nonlinear terms. The observed image is segmented into regions where nonlinear terms, if present, share similar statistical properties. A Bayesian algorithm is proposed to estimate the parameters involved in the model yielding a joint nonlinear unmixing and nonlinearity detection algorithm. Simulations conducted with synthetic and real data show the accuracy of the proposed unmixing and nonlinearity detection strategy for the analysis of hyperspectral images.

show abstract

Nonlinear Hyperspectral Mixture Analysis for tree cover estimates in orchards

Cited by 181 publications

References 50 publications

Nonlinear unmixing of hyperspectral images using a generalized bilinear model

Nonlinear unmixing of hyperspectral images using a generalized bilinear model

Detection of nonlinear mixtures using Gaussian processes: Application to hyperspectral imaging

Residual component analysis of hyperspectral images for joint nonlinear unmixing and nonlinearity detection

Contact Info

Product

Resources

About