Lianru Gao

Adaptive Markov Random Field Approach for Classification of Hyperspectral Imagery

An adaptive Markov random field (MRF) approach is proposed for classification of hyperspectral imagery in this letter. The main feature of the proposed method is the introduction of a relative homogeneity index for each pixel and the use of this index to determine an appropriate weighting coefficient for the spatial contribution in the MRF classification. In this way, overcorrection of spatially high variation areas can be avoided. Support vector machines are implemented for improved class modeling and better estimate of spectral contribution to this approach. Experimental results of a synthetic hyperspectral data set and a real hyperspectral image demonstrate that the proposed method works better on both homogeneous regions and class boundaries with improved classification accuracy.

Endmember Extraction of Hyperspectral Remote Sensing Images Based on the Ant Colony Optimization (ACO) Algorithm

Spectral mixture analysis has been an important research topic in remote sensing applications, particularly for hyperspectral remote sensing data processing. On the basis of linear spectral mixture models, this paper applied directed and weighted graphs to describe the relationship between pixels. In particular, we transformed the endmember extraction problem in the decomposition of mixed pixels into an issue of optimization and built feasible solution space to evaluate the practical significance of the objective function, thereby establishing two ant colony optimization algorithms for endmember extraction. In addition to the detailed process of calculation, we also addressed the effects of different operating parameters on algorithm performance. Finally we designed two sets of simulation data experiments and one set of actual data experiments, and the results of those experiments prove that endmember extraction based on ant colony algorithms can avoid some defects of N-FINDR, VCA and other algorithms, improve the representation of endmembers for all image pixels, decrease the average value of root-mean-square error, and therefore achieve better endmember extraction results than the N-FINDR and VCA algorithms.

Subspace-Based Support Vector Machines for Hyperspectral Image Classification

Hyperspectral image classification has been a very active area of research in recent years. It faces challenges related with the high dimensionality of the data and the limited availability of training samples. In order to address these issues, subspace-based approaches have been developed to reduce the dimensionality of the input space in order to better exploit the (limited) training samples available. An example of this strategy is a recently developed subspace-projection-based multinomial logistic regression technique able to characterize mixed pixels, which are also an important concern in the analysis of hyperspectral data. In this letter, we extend the subspace-projection-based concept to support vector machines (SVMs), a very popular technique for remote sensing image classification. For that purpose, we construct the SVM nonlinear functions using the subspaces associated to each class. The resulting approach, called SVMsub, is experimentally validated using a real hyperspectral data set collected using the National Aeronautics and Space Administrations Airborne Visible/Infrared Imaging Spectrometer. The obtained results indicate that the proposed algorithm exhibits good performance in the presence of very limited training samples.

A Comparative Study on Linear Regression-Based Noise Estimation for Hyperspectral Imagery

In the traditional signal model, signal is assumed to be deterministic, and noise is assumed to be random, additive and uncorrelated to the signal component. A hyperspectral image has high spatial and spectral correlation, and a pixel can be well predicted using its spatial and/or spectral neighbors; any prediction error can be considered from noise. Using this concept, several algorithms have been developed for noise estimation for hyperspectral images. However, these algorithms have not been rigorously analyzed with a unified scheme. In this paper, we conduct a comparative study for such linear regression-based algorithms using simulated images with different signal-to-noise ratio (SNR) and real images with different land cover types. Based on experimental results, instructive guidance is concluded for their practical applications.

Weighted-RXD and Linear Filter-Based RXD: Improving Background Statistics Estimation for Anomaly Detection in Hyperspectral Imagery

Anomaly detection is an active topic in hyperspectral imaging, with many practical applications. Reed-Xiaoli detector (RXD), a widely used method for anomaly detection, uses the covariance matrix and mean vector to represent background signals, assuming that the background information adjusts to a multivariate normal distribution. However, in general, real images present very complex backgrounds. As a result, in many situations, the background information cannot be properly modeled. An important reason is that that background samples often contain also anomalous pixels and noise, which lead to a high false alarm rate. Therefore, the characterization of the background is essential for successful anomaly detection. In this paper, we develop two novel approaches: weighted-RXD (W-RXD) and linear filter-based RXD (LF-RXD) aimed at improving background in RXD-based anomaly detection. By reducing the weight of the anomalous pixels or noise signals and increasing the weight of the background samples, W-RXD can provide better estimations of the background information. In turn, LF-RXD uses the probability of each pixel as background to filter wrong anomalous or noisy instances. Our experimental results, intended to analyze the performance of the newly developed anomaly detectors, indicate that the proposed approaches achieve good performance when compared with other classic approaches for anomaly detection in the literature.

A New Operational Method for Estimating Noise in Hyperspectral Images

A new method for estimating noise in hyperspectral images is described in this letter. Our method is based on the general internal regularity of Earth objects and the strong spectral correlation of hyperspectral images. It can be used to automatically estimate noise for both radiance and reflectance images. Unlike other methods discussed in this letter, our method is more reliable and adaptable, which we demonstrate using simulated images with different scene contents. Finally, we successfully applied this new method in estimating noise for pushbroom hyperspectral imager (PHI) data.

Spectral-Spatial Hyperspectral Image Classification Using Subspace-Based Support Vector Machines and Adaptive Markov Random Fields

This paper introduces a new supervised classification method for hyperspectral images that combines spectral and spatial information. A support vector machine (SVM) classifier, integrated with a subspace projection method to address the problems of mixed pixels and noise, is first used to model the posterior distributions of the classes based on the spectral information. Then, the spatial information of the image pixels is modeled using an adaptive Markov random field (MRF) method. Finally, the maximum posterior probability classification is computed via the simulated annealing (SA) optimization algorithm. The combination of subspace-based SVMs and adaptive MRFs is the main contribution of this paper. The resulting methods, called SVMsub-eMRF and SVMsub-aMRF, were experimentally validated using two typical real hyperspectral data sets. The obtained results indicate that the proposed methods demonstrate superior performance compared with other classical hyperspectral image classification methods.

A maximum noise fraction transform with improved noise estimation for hyperspectral images

Feature extraction is often performed to reduce spectral dimension of hyperspectral images before image classification. The maximum noise fraction (MNF) transform is one of the most commonly used spectral feature extraction methods. The spectral features in several bands of hyperspectral images are submerged by the noise. The MNF transform is advantageous over the principle component (PC) transform because it takes the noise information in the spatial domain into consideration. However, the experiments described in this paper demonstrate that classification accuracy is greatly influenced by the MNF transform when the ground objects are mixed together. The underlying mechanism of it is revealed and analyzed by mathematical theory. In order to improve the performance of classification after feature extraction when ground objects are mixed in hyperspectral images, a new MNF transform, with an improved method of estimating hyperspectral image noise covariance matrix (NCM), is presented. This improved MNF transform is applied to both the simulated data and real data. The results show that compared with the classical MNF transform, this new method enhanced the ability of feature extraction and increased classification accuracy.

PSO-EM: A Hyperspectral Unmixing Algorithm Based On Normal Compositional Model

A new hyperspectral unmixing algorithm is proposed based on the normal compositional model (NCM) to estimate the endmembers and abundance parameters jointly in this paper. The NCM considers the hyperspectral imaging as a stochastic process and interprets each pixel value as a random vector, which is linearly mixed by the endmembers. More precisely, these endmembers are also treated as random variables as opposed to deterministic values in order to capture spectral variability that is not well described by the linear mixing model (LMM). However, the higher complexity of such an unmixing model leads to more difficulty in parameter estimation. A particle swarm optimization-expectation maximization (PSO-EM) algorithm, a “winner-take-all” version of the EM, is proposed to solve the parameter estimation problem, which employs a partial E step. The main contribution of the proposed PSO-EM is making optimum use of particle swarm optimization method (PSO) in the partial E step, which solves the difficulty of the integrals in the NCM model. The performance of the proposed methodology is evaluated through synthetic and real data experiments. Our obtained results demonstrate the superior performance of PSO-EM compared to other NCM-based as well as LMM-based methods.

Image quality evaluation on Chinese first earth observation hyperspectral satellite

A Micro-satellite Constellation for Environment and Disaster Monitoring was successfully launched in China on September 6, 2008, which includes two small satellites, Satellite-A (HJ-1A) and Satellite-B (HJ-1B). The interferometric imaging spectrometer (IFIS) installed on HJ-1A is the first hyperspectral earth observation sensor in China. To assess the data quality of IFIS, a calibration experiment was carried out at the Dunhuang Calibration Site on October 20, 2008. With the simultaneous measurements acquired from the Dunhuang calibration field, the 6s radiative transfer code was used to retrieve the ground surface reflectance. By comparing the in-situ reflectance and 6S reflectance of the Dunhuang calibration target, the radiometric and spectral performance of the IFIS was evaluated. From the homogeneous image of the calibration target, the Signal-to-Noise Ratio (SNR) of IFIS data was estimated based on the high correlation between bands. This noise estimation results was used to estimate noise covariance matrix needed for hyperspectral data dimension reduction, such as Maximum Noise Fractions (MNF). The assessment results indicated that the IFIS has good performance and will be promising in the applications of environment and disaster monitoring.