Search

When high-resolution wide-swath (HRWS) multichannel synthetic aperture radar (MC-SAR) system is used for ocean observation, vast amount of redundant data is generated, significantly limiting its applications. Though compressive sensing (CS)-based method has been applied to the traditional single-channel or dual-channel SAR imaging system, it is no longer applicable for MC-SAR due to the existence of channel error when using the space-time equivalent sampling technique for azimuth signal reconstruction. By analyzing such periodic channel error, i.e., frequency-dependence phase mismatch (FD-PM), in this article, a novel dictionary is constructed for CS-based HRWS MC-SAR imaging after an improved range cell migration correction method is applied. As a result, a novel CS imaging mode is proposed for the ocean moving target based on the sparsity of the target scattering centers, by which the amount of data in MC-SAR can be reduced by sampling below the Nyquist sampling rate and the swath width can be further increased. Experimental results show that the proposed method clearly eliminates the azimuth defocus and blur caused by low sampling rate and FD-PM, and significantly reduces the amount of data to about one-third when compared to sampling at the Nyquist rate. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new framework for hyperspectral image classification, namely pseudolabel guided kernel learning (PLKL). The proposed framework is capable of fully utilizing unlabeled samples, making it very effective to handle the task with extremely limited training samples. Specifically, with multiple initial kernels and labeled samples, we first employ support vector machine (SVM) classifiers to predict pseudolabels independently for each unlabeled sample, and consistency voting is applied to the resulting pseudolabels to select and add a few unlabeled samples to the training set. Then, we refine the kernels to improve their discriminability with the augmented training set and a typical kernel learning method. Such phases are repeated until stable. Furthermore, we enhance the PLKL in terms of both the computation and memory efficiencies by using a bagging-like strategy, improving its practicality for large scale datasets. In addition, the proposed framework is quite flexible and general. That is, other advanced kernel-based methods can be incorporated to continuously improve the performance. Experimental results show that the proposed frameworks achieve much higher classification accuracy, compared with state-of-the-art methods. Especially, the classification accuracy improves more than 5% with very few training samples. [ABSTRACT FROM AUTHOR]

Within-class spectral variation, which is caused by varied imaging conditions, such as changes in illumination, environmental, atmospheric, and temporal conditions, significantly degrades the performance of hyperspectral image classification. Recent studies have shown that such spectral variation can be alleviated by exploring the low-rank property in the spectral domain, especially based on the low-rank subspace assumption. In this paper, the low-rank subspace assumption is approached by exploring the low-rank property in the local spectral domain. In addition, the low-rank property in the spatial domain is also explored to alleviate spectral variation. As a result, two novel spectral-spatial low-rank (SSLR) strategies are designed to alleviate spectral variation by exploring the low-rank property in both spectral and spatial domains. Experimental results on two benchmark hyperspectral datasets demonstrate that exploring the low-rank property in local spectral space can help to alleviate spectral variation and improve the performance of classification obviously for all tested data, while exploring the low-rank property in spatial space is more effective for images presenting large homogeneous areas. [ABSTRACT FROM PUBLISHER]

Spectral variation, which is inevitably present in hyperspectral data due to nonuniformity and inconsistency of illumination, may result in considerable difficulty in spectral unmixing. In this paper, a field endmember library is constructed to accommodate spectral variation by representing each endmember class by a batch of image-derived spectra. In order to perform unmixing by such a field endmember library, a novel spatial and spectral endmember selection (SSES) algorithm is designed to search for a spatial and spectral constrained endmember subset per pixel for abundance estimation (AE). The net effect is to achieve sparse unmixing equivalently, considering the fact that only a few endmembers in the large library have nonzero abundances. Thus, the resulting algorithm is called spatial and spectral constrained sparse unmixing (SSCSU). Experimental results using both synthetic and real hyperspectral images demonstrate that the proposed SSCSU algorithm not only improves the performance of traditional AE algorithms by considering spectral variation, but also outperforms the existing sparse unmixing approaches. [ABSTRACT FROM PUBLISHER]

Hopfield Neural Network (HNN) has been demonstrated to be an effective tool for Spectral Mixture Analysis (SMA). However, the spectrum of pure ground objects, known as endmember, must be known previously. In this paper, the HNN is utilized to solve unsupervised SMA, in which Endmember Extraction (EE) and Abundance Estimation (AE) are performed iteratively. Two different HNNs are constructed to solve such multiplicative updating procedure, respectively. The proposed HNN based unsupervised SMA framework is then applied to solve three second-order constrained Nonnegative Matrix Factorization (NMF) models for SMA, including Minimum Distance Constrained NMF (MDC-NMF), Minimum endmember-wise Distance Constrained NMF (MewDC-NMF), and Minimum Dispersion Constrained NMF (MiniDisCo-NMF). As a result, our proposed HNN based algorithms are able to perform unsupervised SMA and extract virtual endmembers without assuming the presence of spectrally pure constituents in highly mixed hyperspectral data. Experimental results on both synthetic and real hyperspectral images demonstrate that our proposed HNN based algorithms clearly outperform traditional Projected Gradient (PG) based solutions for these constrained NMF based SMA. [ABSTRACT FROM PUBLISHER]