Showing papers by "Xiuping Jia published in 2013"

Feature Mining for Hyperspectral Image Classification

Abstract: Hyperspectral sensors record the reflectance from the Earth's surface over the full range of solar wavelengths with high spectral resolution. The resulting high-dimensional data contain rich information for a wide range of applications. However, for a specific application, not all the measurements are important and useful. The original feature space may not be the most effective space for representing the data. Feature mining, which includes feature generation, feature selection (FS), and feature extraction (FE), is a critical task for hyperspectral data classification. Significant research effort has focused on this issue since hyperspectral data became available in the late 1980s. The feature mining techniques which have been developed include supervised and unsupervised, parametric and nonparametric, linear and nonlinear methods, which all seek to identify the informative subspace. This paper provides an overview of both conventional and advanced feature reduction methods, with details on a few techniques that are commonly used for analysis of hyperspectral data. A general form that represents several linear and nonlinear FE methods is also presented. Experiments using two widely available hyperspectral data sets are included to illustrate selected FS and FE methods.

Wavelet Packet Analysis and Gray Model for Feature Extraction of Hyperspectral Data

Abstract: Wavelet packet analysis (WPA) and gray model (GM) are investigated for nonlinear unsupervised feature extraction of hyperspectral remote sensing data in this letter. Treated as derivative series, a hyperspectral response curve of each pixel is decomposed into an approximation and various detailed compositions by WPA, and then, GM is continuously applied to find the relationship among those detailed compositions. Cluster-space representation is used for determining the optimal wavelet. New extracted features can reveal the intrinsic identities of hyperspectral data. Experimental results show the feasibility and reliability of our proposed method in terms of classification accuracy.

Spectral Unmixing in Multiple-Kernel Hilbert Space for Hyperspectral Imagery

Abstract: In this paper, we address a spectral unmixing problem for hyperspectral images by introducing multiple-kernel learning (MKL) coupled with support vector machines. To effectively solve issues of spectral unmixing, an MKL method is explored to build new boundaries and distances between classes in multiple-kernel Hilbert space (MKHS). Integrating reproducing kernel Hilbert spaces (RKHSs) spanned by a series of different basis kernels in MKHS is able to provide increased power in handling general nonlinear problems than traditional single-kernel learning in RKHS. The proposed method is developed to solve multiclass unmixing problems. To validate the proposed MKL-based algorithm, both synthetic data and real hyperspectral image data were used in our experiments. The experimental results demonstrate that the proposed algorithm has a strong ability to capture interclass spectral differences and improve unmixing accuracy, compared to the state-of-the-art algorithms tested.

Hyperspectral Imagery Clustering With Neighborhood Constraints

Abstract: This letter presents a new technique for clustering hyperspectral images that exploits neighborhood-constrained spatial information. The main feature of the proposed method is the introduction of a neighborhood homogeneity index (NHI) and the use of this index to measure the spatial homogeneity in a local area. A new similarity measurement integrates NHI and spectral information using an adaptive distance norm for clustering. The performance of the proposed neighborhood-constrained-clustering algorithm was assessed through a synthetic image and a real hyperspectral image and compared with those obtained by advanced spectral-spatial clustering algorithms. Experimental results show that the proposed scheme gives better performances.

Superpixel-based Markov random field for classification of hyperspectral images

Abstract: The paper presents a supervised classification method based on superpixels and Markov random field (MRF). Hyperspectral image is over-segmented into superpixels that are as basic unit of Markov random field instead of operating at the pixel level. Adaptive weight coefficient is introduced to determine contextual relationship between superpixels. Support vector machines are implemented for better estimation of spectral contribution to this approach. An experiment of real hyperspectral image reveals efficient performance.

A New Target Detector for Hyperspectral Data Using Cointegration Theory

Abstract: This paper introduces Cointegration Theory to address the problem of adaptive target detection in hyperspectral imagery. Cointegration Theory aims at mining a long-term equilibrium relationship, which refers to the condition that an appropriate linear combination of several non-stationary series can be stationary as long as they have similar or related drift. Hyperspectral response sequences, which are highly non-stationary, have similar patterns among the same materials. To be treated as a time series, each given hyperspectral curve is matched with the reference spectrum via the Johansen Cointegration Test. The statistic of the test is then used for target detection. Experimental results indicate that our proposed method is effective and has a strong capacity to identify interesting objects from their background.

Genetic Algorithm for distorted point set matching

Abstract: For image registration, point matching is still a fundamental problem because of the complex distortion such as transformation, missing and irrelevant points involved in two point sets detected from images. In this paper, a new method based on Genetic Algorithm (GA) is proposed to find the optimal affine transformation between two different point sets. In order to deal with the influence of the missing and spurious points, we define a fitness function in the combination of global topology of point set and individual point property. The experimental results on randomly generated 2D point sets demonstrate that the proposed GA-based point matching algorithm can achieve good performance in terms of correct matching (CM), false matching (FM), and missing matching (MM).

Subspace detection based on the combination of nonlinear feature extraction and feature selection

Abstract: In this study, a subspace detection technique is developed using a hybrid approach which combines both feature extraction and feature selection for the task of hyperspectral image classification. The proposed approach applies Kernel Principal Component Analysis (KPCA) at the first step, then feature selection from the KPCA images is accomplished by combining the KPCA score with a Jeffries-Matusita (JM) distance based ranking score. Experimental analysis is carried out on a hyperspectral image acquired by the AVIRIS sensor and the results show the advantage of the proposed approach in terms of classification accuracy in the tested cases.

Feature Mining for Hyperspectral Image Classification A general overview and analysis of feature reduction methods for classification of hyperspectral images is provided. Experimental results give the performance of selected feature selection and feature extraction approaches.

Abstract: Hyperspectral sensors record the reflectance from the Earth's surface over the full range of solar wave- lengths with high spectral resolution. The resulting high- dimensional data contain rich information for a wide range of applications. However, for a specific application, not all the measurements are important and useful. The original feature space may not be the most effective space for representing the data. Feature mining, which includes feature generation, fea- ture selection (FS), and feature extraction (FE), is a critical task for hyperspectral data classification. Significant research effort has focused on this issue since hyperspectral data became available in the late 1980s. The feature mining techniques which have been developed include supervised and unsuper- vised, parametric and nonparametric, linear and nonlinear methods, which all seek to identify the informative subspace. This paper provides an overview of both conventional and ad- vanced feature reduction methods, with details on a few techniques that are commonly used for analysis of hyperspec- tral data. A general form that represents several linear and nonlinear FE methods is also presented. Experiments using two widely available hyperspectral data sets are included to illustrate selected FS and FE methods.

Incorporating spatial properties in subspace detection

Abstract: The aim of this analysis is to develop a subspace detection technique using a hybrid approach which combines nonlinear feature extraction and feature selection for the task of hyperspectral image classification. In the proposed approach Kernel Principal Component Analysis (KPCA) is applied at the first step to generate the new features from the original data. Then pixel based spatial correlation is measured for each of the KPCA images to rank them based on their spatial objects/contents. These KPCA and spatial correlation based ranking scores are combined to obtain an informative subset of features. The experimental analysis conducted on a real hyperspectral image acquired by the AVIRIS sensor shows the advantage of the proposed approach in terms of classification accuracy.

Fuzzy Knowledge-Based Subspace Clustering for Life Science Data Analysis

Abstract: Features or attributes play an important role when handling multi-dimensional datasets. Generally, not all the features are needed to find several groups of similar objects in traditional clustering methods because some of the features may not be relevant and also redundant. Hence, the concept of identifying subsets of the features that are relevant to clusters is introduced, instead of using the full set of features. This chapter discusses the use of the prior knowledge of the importance of features and their interaction in constructing both fuzzy measures and signed fuzzy measures for subspace clustering. The Choquet integral, which is known as a useful aggregation operator with respect to fuzzy measure, is used to aggregate the importance and interaction of the features. The concept of fuzzy knowledge-based subspace clustering is applied especially to the analysis of life science data in this chapter.

A hybrid segmentation technique for objected-based hyperspectral data classification over complex sub-urban landscape

Abstract: In this study a hybrid segmentation algorithm is developed to overcome over segmentation and under segemntation. The reliable segmentation results are critical for object based hyperspectral image classification using both spectral and spatial information. A multi resolution segmentation approach is adopted with further improvement. The application of the proposed procedure is demonstrated using a hyperspectral image acquired by HyMap over a complex sub-urban landscape. The results show the improvement provided by the proposed method.