Papers by Magnus Ulfarsson
Sparse representation of hyperspectral data using CUR matrix decomposition
2013 IEEE International Geoscience and Remote Sensing Symposium - IGARSS, 2013
ABSTRACT We propose CUR methods for hyperspectral unmixing that decompose the data matrix into no... more ABSTRACT We propose CUR methods for hyperspectral unmixing that decompose the data matrix into non-negative endmembers and abundance maps. The endmembers will be selected from a dictionary constructed from the data matrix. Each endmember will coincide with certain columns of the data matrix. By doing this we are assured that the dictionary will be physically meaningful and may be interpreted unambiguously from the data set. This assumption, that the endmembers are contained within the data, is called the pixel purity assumption. We compare two regularization terms to promote sparsity in our solutions, the first is ℓ2 regularization and the second is vector ℓ0 regularization. The methods are evaluated both on simulated data and a real hyperspectral image of an urban landscape.
A smooth hyperspectral unmixing method using cyclic descent
2012 IEEE International Geoscience and Remote Sensing Symposium, 2012
ABSTRACT Hyperspectral unmixing is the process where the reflectance spectrum from a mixed pixel ... more ABSTRACT Hyperspectral unmixing is the process where the reflectance spectrum from a mixed pixel is decomposed into separate distinct spectral signatures (endmembers). A mixed pixel results when spectra from more than one material is recorded by a sensor in one pixel. The goal of linear unmixing is to identify the number of endmembers in an image, the endmembers themselves and their abundances in each pixel. This paper presents a new smooth method for unmixing hyperspectral images using nonnegative cyclic descent. The proposed method uses iterative cyclic descent algorithm to find the endmembers and their abundances. The algorithm uses an ℒ1 norm to promote sparseness in the abundances. Because the spectrum of the endmembers varies smoothly, a first order roughness penalty is added to discourage roughness in the endmembers. The algorithm does not use any prior information about the data. The method is tested using a real hyperspectral image of an urban landscape.
Smooth noisy PCA using a 1<sup>st</sup> order roughness penalty
2010 IEEE International Workshop on Machine Learning for Signal Processing, 2010
ABSTRACT Principal component analysis (PCA) and other multivariate methods have proven to be usef... more ABSTRACT Principal component analysis (PCA) and other multivariate methods have proven to be useful in a variety of engineering and science fields. PCA is commonly used for dimensionality reduction. PCA has also proven to be useful in functional magnetic resonance imaging (fMRI) research where it is used to decompose the fMRI data into components which can be associated with biological processes. In this paper we develop a smooth version of PCA derived from a maximum likelihood framework. A 1st order roughness penalty term is added to the log-likelihood function which is then maximized for the parameters of interest with an expectation maximization (EM) algorithm. This new method is applied both to simulated data and real fMRI data.
In this paper an endmember constrained semi-supervised hyperspectral unmixing method is proposed.... more In this paper an endmember constrained semi-supervised hyperspectral unmixing method is proposed. The linear model is used to represent the hyperspectral data. A priori information about the endmembers is incorporated into the objective function with soft regularization. This information can be acquired from a spectral library or from the data itself. Quantitative evaluation of the method is done using simulated data and it is shown the soft regularization can yield better results than hard regularization. The method is also applied on a real hyperspectral data set and the estimated abundance maps improve when a priori information is used to aid the unmixing.
2014 IEEE Geoscience and Remote Sensing Symposium, 2014
Hyperspectral images (HSI) are often corrupted by noise making their analysis and interpretation ... more Hyperspectral images (HSI) are often corrupted by noise making their analysis and interpretation difficult. In this paper we develop a sparse low rank model for HSI, which is useful for denoising. The two key benefits of the model for denoising are dimensionality reduction via noisy principal component analysis (nPCA) and the exploitation of sparseness in the dual-tree complex wavelet transform (CWT) coefficients of the loading matrix associated with the principal components (PCs). We present denoising examples of both synthetic and real data and compare our method to a PCA based 2-dimensional (2D) bivariate shrinkage method.
2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2014
There are two main approaches to independent component analysis (ICA); maximization of non-Gaussi... more There are two main approaches to independent component analysis (ICA); maximization of non-Gaussianity of the sources and the exploitation of temporal correlation in Gaussian sources. In this paper, we present a novel sparse noisy ICA model where we have introduced temporal correlation in the sources, described by a first order auto regressive (AR(1)) process. The correlation structure of the sources eliminates the rotational invariance of the estimates, enabling their separation. Using simulated data, we demonstrate both source separation and denoising, where we compare our results to a sparse PCA method and the fastICA method. Additionally, we apply the method on a real hyperspectral dataset.
2014 IEEE Geoscience and Remote Sensing Symposium, 2014
In this paper, a hyperspectral feature extraction method is proposed. A low-rank linear model usi... more In this paper, a hyperspectral feature extraction method is proposed. A low-rank linear model using the right eigenvector of the observed data is given for hyperspectral images. A total variation (TV) based regularization called Low-Rank TV regularization (LRTV) is used for hyperspectral feature extraction. The feature extraction is used for hyperspectral image classification. The classification accuracies obtained are significantly better than the ones obtained using features extracted by Principal Component Analysis (PCA) and Maximum Noise Fraction (MNF).
2014 IEEE Geoscience and Remote Sensing Symposium, 2014
Mean squared error (MSE) is commonly used for evaluating the performance of hyperspectral imaging... more Mean squared error (MSE) is commonly used for evaluating the performance of hyperspectral imaging (HSI) methods. MSE depends on the true (unknown) signal to be estimated and is therefore not computable for real data. Therefore, HSI methods are usually evaluated using simulated data. Stein's unbiased risk estimator (SURE) is an unbiased estimator of the MSE that does not require knowledge of the true signal. The main aim of this paper is to promote the use of SURE for evaluating HSI models. To achieve that goal we compare three wavelet models, spectral, spatial and spectralspatial, for hyperspectral images. Hyperspectral images are modeled based on their sparse wavelet components. The penalized least squares with 1 penalty (to promote sparsity) is considered for sparse reconstruction. By comparing the SURE values for the three models, it is shown that the spatial model performs better than spectral model and spectralspatial model outperforms both spectral and spatial models.
IEEE Transactions on Geoscience and Remote Sensing, 2000
In this paper, a method called wavelet-based sparse reduced-rank regression (WSRRR) is proposed f... more In this paper, a method called wavelet-based sparse reduced-rank regression (WSRRR) is proposed for hyperspectral image restoration. The method is based on minimizing a sparse regularization problem subject to an orthogonality constraint. A cyclic descent-type algorithm is derived for solving the minimization problem. For selecting the tuning parameters, we propose a method based on Stein's unbiased risk estimation. It is shown that the hyperspectral image can be restored using a few sparse components. The method is evaluated using signal-to-noise ratio and spectral angle distance for a simulated noisy data set and by classification accuracies for a real data set. Two different classifiers, namely, support vector machines and random forest, are used in this paper. The method is compared to other restoration methods, and it is shown that WSRRR outperforms them for the simulated noisy data set. It is also shown in the experiments on a real data set that WSRRR not only effectively removes noise but also maintains more fine features compared to other methods used. WSRRR also gives higher classification accuracies.
IEEE Geoscience and Remote Sensing Letters, 2000
In this letter, we present a new method for the pansharpening of multispectral satellite imagery.... more In this letter, we present a new method for the pansharpening of multispectral satellite imagery. Pansharpening is the process of synthesizing a high spatial resolution multispectral image from a low spatial resolution multispectral image and a high-resolution panchromatic (PAN) image. The method uses total variation to regularize an ill-posed problem dictated by a widely used explicit image formation model. This model is based on the assumptions that a linear combination of the bands of the pansharpened image gives the PAN image and that a decimation of the pansharpened image gives the original multispectral image. Experimental results are based on two real datasets and the quantitative quality of the pansharpened images is evaluated using a number of spatial and spectral metrics, some of which have been recently proposed and do not need a reference image. The proposed method compares favorably to other well-known methods for pansharpening and produces images of excellent spatial and spectral quality.
Semi-Supervised Hyperspectral Unmixing
Abstract 18715: Left Atrial Pressure and Dominant Frequency of Atrial Fibrillation in Humans
Circulation, Nov 23, 2010
In this paper, a new denoising method for hyperspectral images using First Order Roughness Penalt... more In this paper, a new denoising method for hyperspectral images using First Order Roughness Penalty (FORP) is proposed. The proposed algorithm is applied in the wavelet domain to exploit the multiresolution analysis property of wavelets and thus improving the denoising results. Stein's Unbiased Risk Estimator (SURE) is used to choose the tuning parameters automatically. The experimental results show improvements for simulated data sets based on Signal to Noise Ratio (SNR) and visually for real data set.
Principal Component Analysis (PCA) has widely been used in hyperspectral image analysis as a prep... more Principal Component Analysis (PCA) has widely been used in hyperspectral image analysis as a preprocessing step for further processing. Recently, sparse PCA methods have emerged as a powerful alternative. In this paper we propose a wavelet based sparse PCA method for hyperspectral image denoising. The proposed method is evaluated by using simulated and real data.
Wavelet footprints for speckle reduction of SAR images
IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477), 2003
Wavelet footprints, proposed by Dragotti (2002), are used for speckle reduction of synthetic aper... more Wavelet footprints, proposed by Dragotti (2002), are used for speckle reduction of synthetic aperture radar (SAR) images. Wavelet footprints contain all wavelet coefficients associated with a singular structure of a signal. Consequently, the dependency across scales that is inherent in wavelet transformation is eliminated. In the present paper, coefficients of wavelet footprints are thresholded with hard thresholding. The denoising method
IGARSS 2001. Scanning the Present and Resolving the Future. Proceedings. IEEE 2001 International Geoscience and Remote Sensing Symposium (Cat. No.01CH37217), 2001
This paper will concentrate on linear feature extraction methods for neural network classifiers. ... more This paper will concentrate on linear feature extraction methods for neural network classifiers. The considered feature extraction method is based on discrete wavelet transformations (.DWTS) and cluster-based procedure, i.e., cluster-based feature extraction of the wavelet coefficients of remote sensing and geographic data is considered. The cluster-based feature extraction is a preprocessing routine that computes feature-vectors to group the wavelet coefficients in an unsupervised way. These feature-vectors are then used as a mask or a filter for the selection of representative wavelet coefficients that are used to train the neural network classifiers. In experiments, the proposed feature extraction methods performed well in neural networks classifications of multisource remote sensing and geographic data. 0-7803-7031-7/01/$10.00 (C) 2001 IEEE 867 0-7803-7031-7/01/$17.00 (C) 2001 IEEE
2010 IEEE International Geoscience and Remote Sensing Symposium, 2010
Hyperspectral imaging is a continuously growing area of remote sensing application. The wide spec... more Hyperspectral imaging is a continuously growing area of remote sensing application. The wide spectral range, providing a very high spectral resolution, allows to detect and classify surfaces and chemical elements of the observed image. The main problem of hyperspectral data is that the high spectral resolution is usually complementary to the spatial one, which can vary from a few to tens of meters. Many factors, such as imperfect imaging optics, atmospheric scattering, secondary illumination effects and sensor noise cause a degradation of the acquired image quality, making the spatial resolution one of the most expensive and hardest to improve in imaging systems. In this work, a novel method, based on the use of source separation technique and a spatial regularization step by simulated annealing is proposed to improve the spatial resolution of cover classification maps. Experiments have been carried out on both synthetic and real hyperspectral data and show the effectiveness of the proposed method.
Rank selection in noist PCA with sure and random matrix theory
2008 IEEE International Conference on Acoustics, Speech and Signal Processing, 2008
Principal component analysis (PCA) is probably the best known method for dimensionality reduction... more Principal component analysis (PCA) is probably the best known method for dimensionality reduction. Perhaps the most important problem in PCA is to determine the number of principal components in a given data set, and in effect separate signal from noise in the data set. Many methods have been proposed to deal with this problem but almost all of them fail
Speckle reduction of SAR images in the curvelet domain
IEEE International Geoscience and Remote Sensing Symposium, 2002
Abstract Curvelet transform (CT), proposed by E. Candes et al.(1999), is used for speckle reducti... more Abstract Curvelet transform (CT), proposed by E. Candes et al.(1999), is used for speckle reduction of SAR images. The CT is useful for speckle reduction through its subband images and the speckle reduction is obtained by thresholding the subband-image coefficients of ...
IEEE International Geoscience and Remote Sensing Symposium, 2002
A linear feature extraction method based on the discrete wavelet transform (DWT) is applied. A bi... more A linear feature extraction method based on the discrete wavelet transform (DWT) is applied. A binary genetic algorithm is used to select the best features from the different DWT representations in terms of cost. The feature extraction/selection methods are applied in classification of multisource remote sensing and geographic data. In experiments, the proposed methods performed well in terms of overall accuracies as compared to results obtained with other well-known feature extraction/selection methods.
Uploads
Papers by Magnus Ulfarsson