Luca Capobianco

Optimal MMSE Pan Sharpening of Very High Resolution Multispectral Images

In this paper, we propose an optimum algorithm, in the minimum mean-square-error (mmse) sense, for panchromatic (Pan) sharpening of very high resolution multispectral (MS) images. The solution minimizes the squared error between the original MS image and the fusion result obtained by spatially enhancing a degraded version of the MS image through a degraded version, by the same scale factor, of the Pan image. The fusion result is also optimal at full scale under the assumption of invariance of the fusion parameters across spatial scales. The following two versions of the algorithm are presented: a local mmse (lmmse) solution and a fast implementation which globally optimizes the fusion parameters with a moderate performance loss with respect to the lmmse version. We show that the proposed method is computationally practical, even in the case of local optimization, and it outperforms the best state-of-the-art Pan-sharpening algorithms, as resulted from the IEEE Data Fusion Contest 2006, on true Ikonos and QuickBird data and on simulated Pleiades data.

Analysis of the Effects of Pansharpening in Change Detection on VHR Images

In this letter, we investigate the effects of pansharpening (PS) applied to multispectral (MS) multitemporal images in change-detection (CD) applications. Although CD maps computed from pansharpened data show an enhanced spatial resolution, they can suffer from errors due to artifacts induced by the fusion process. The rationale of our analysis consists in understanding to which extent such artifacts can affect spatially enhanced CD maps. To this end, a quantitative analysis is performed which is based on a novel strategy that exploits similarity measures to rank PS methods according to their impact on CD performance. Many multiresolution fusion algorithms are considered, and CD results obtained from original MS and from spatially enhanced data are compared.

Target Detection With Semisupervised Kernel Orthogonal Subspace Projection

The orthogonal subspace projection (OSP) algorithm is substantially a kind of matched filter that requires the evaluation of a prototype for each class to be detected. The kernel OSP (KOSP) has recently demonstrated improved results for target detection in hyperspectral images. The use of kernel methods (KMs) makes the method nonlinear, helps to combat the high-dimensionality problem, and improves robustness to noise. This paper presents a semisupervised graph-based approach to improve KOSP. The proposed algorithm deforms the kernel by approximating the marginal distribution using the unlabeled samples. Two further improvements are presented. First, a contextual selection of unlabeled samples is proposed. This strategy helps in better modeling the data manifold, and thus, improved sensitivity-specificity rates are obtained. Second, given the high computational burden involved, we present two alternative formulations based on the Nystroumlm method and the incomplete Cholesky factorization to achieve operational processing times. The good performance of the proposed method is illustrated in a toy data set and two relevant hyperspectral image target-detection applications: crop identification and thermal hot-spot detection. A clear improvement is observed with respect to the linear and the nonlinear kernel-based OSP, demonstrating good generalization capabilities when a low number of labeled samples are available, which is usually the case in target-detection problems. The relevance of unlabeled samples and the computational cost are also analyzed in detail.

Quality assessment of data products from a new generation airborne imaging spectrometer

This work focuses on the assessment of noise parameters characterizing the hyperspectral images collected by a new generation high resolution sensor manufactured by Selex Galileo S.p.A., in Italy, and named Hyper SIM-GA, which is an imaging spectrometer operating in the push-broom configuration, with 512 bands (2 nm bandwidth) and 256 bands (6 nm bandwidth) in the V-NIR and SWIR wavelengths, respectively. To this purpose, an original method suitable for estimating the noise introduced by optical imaging systems is described. The power of the signal-dependent photonic noise is decoupled from that of the signal-independent noise generated by the electronic circuitry. The method relies on the multivariate regression of local sample mean and variance. Statistically homogeneous pixels produce scatter-points that are clustered along a straight line, whose slope and intercept measure the signal-dependent and the signal-independent components of the noise power, respectively. Experimental results on radiance data acquired by SIM-GA, highlight the accuracy of the proposed method and its robustness to image textures that may lead to a gross overestimation of the noise.

Spatial enhancement of hyperion hyperspectral data through ALI panchromatic image

This paper presents two novel image fusion methods, suitable for sharpening of hyperspectral (HS) images by means of a panchromatic (Pan) observation: the HS bands expanded to the finer scale of the Pan image are sharpened by adding the spatial details which are calculated by the PAN image. Since a direct, unconditioned injection of Pan details gives unsatisfactory results, a new injection model is proposed, which provides the optimum injection simulating fusion at degraded scale by minimizing the mean square error. Fusion tests are carried out both on spatially degraded data to objectively compare the proposed scheme to some fusion methods and on full resolution image data.

Hyperspectral pansharpening based on modulation of pixel spectra

This paper presents a novel image fusion methods, suitable for the sharpening of a hyperspectral (HS) image by means of a panchromatic (Pan) observation. The HS bands are expanded to the scale of the Pan image and sharpened by modulating HS pixel vectors by the ratio of the Pan image to its lowpass-filtered version. The main advantage of the proposed approach is that the spectral angle of pixel vectors are preserved after fusion is accomplished. The modulating factor is damped to avoid over-enhancement with consequent loss of spatial fidelity. Experiments carried out on a Hyperion + ALI dataset demonstrate that the proposed method favorably compares with other pansharpening approaches extended to hyperspectral data.

Weighted Least Squares Pan-Sharpening of Very High Resolution Multispectral Images

This paper presents a solution to the problem of enhancing the spatial resolution of multispectral images with high-resolution panchromatic observations. The proposed method exploits a Weighted Least Squares estimator to calculate injection parameters in the fusion model. For each pixel of the image a weight is calculated by a classification map. The classifier used in the experiments is a Support Vector Machine in order to obtain high accuracy on each land-cover type. Results are presented and discussed on very-high resolution images acquired by Quickbird and Ikonos satellite systems. Fusion simulations on spatially degraded data and fusion tests at full scale reveal that an accurate and reliable PAN-sharpening is achieved by the proposed method.

Target detection with a contextual kernel orthogonal subspace projection

The Orthogonal Subspace Projection (OSP) algorithm is substantially a kind of matched filter that requires the evaluation of a prototype for each class to be detected. The kernel OSP (KOSP) has recently demonstrated improved results for target detection in hyperspectral images. The use of kernel methods helps to combat the high dimensionality problem and makes the method robust to noise. This paper incorporates the contextual information to KOSP with a family of composite kernels of tunable complexity. The good performance of the proposed methods is illustrated in hyperspectral image target detection problems. The information contained in the kernel and the induced kernel mappings is analyzed, and bounds on generalization performance are given.

Semi-Supervised Kernel Orthogonal Subspace Projection

The Orthogonal Subspace Projection (OSP) algorithm is substantially a kind of matched filter that requires the evaluation of a prototype for each class to be detected. The kernel OSP (KOSP) has recently demonstrated improved results for target detection in hyperspectral images. The use of kernel helps to combat the high dimensionality problem and makes the method robust to noise. This paper presents a semi-supervised graph-based approach to improve KOSP. The proposed algorithm deforms the kernel by approximating the marginal distribution using the unlabeled samples. The good performance of the proposed method is illustrated in a toy dataset and an hyperspectral image target detection problem.

On the effects of pan-sharpening to target detection

We present an experimental study on the effects of pansharp-ening on target detection from multispectral and panchromatic images acquired by very-high resolution satellite sensors. Original and spatially-enhanced image data are used to detect relatively small targets (vehicles on an airport scenario) characterized by a sufficiently well-defined spectral signature in the four MS bands. The aim of the paper is to compare different pansharpening methods by evaluating the performances of target detection on true MS and panchromatic data. Both linear and kernel-based one-class classification methods are considered for the target detection process.