Independent-component analysis for hyperspectral remote sensing imagery classification (original) (raw)
Related papers
Classifying hyperspectral remote sensing imagery with independent component analysis
In this paper, we investigate the application of independent component analysis (ICA) to remotely sensed hyperspectral image classification. We focus on the performance of Joint Approximate Diagonalization of Eigenmatrices (JADE) algorithm, although the proposed method is applicable to other popular ICA algorithms. The major advantage of using ICA is its capability of classifying objects with unknown spectral signatures in an unknown image scene, i.e., unsupervised classification. However, ICA suffers from computational expensiveness, which limits its application to high dimensional data analysis. In order to make it applicable to hyperspectral image classification, a data preprocessing procedure is employed to reduce the data dimensionality. Noise adjusted principal component analysis (NAPCA) is used for this purpose, which can reorganize the original data information in terms of signal-to-noise ratio, a more appropriate criterion than variance when dealing with images. The preliminary results demonstrate that the selected major components from NAPCA can better represent the object information in the original data than those from ordinary principal component analysis (PCA). As a result, better classification using ICA is expected.
Classifying hyperspectral remote sensing imagery with independent component analysis
Independent Component Analyses, Wavelets, Unsupervised Smart Sensors, and Neural Networks III, 2005
In this paper, we investigate the application of independent component analysis (ICA) to remotely sensed hyperspectral image classification. We focus on the performance of Joint Approximate Diagonalization of Eigenmatrices (JADE) algorithm, although the proposed method is applicable to other popular ICA algorithms. The major advantage of using ICA is its capability of classifying objects with unknown spectral signatures in an unknown image scene, i.e., unsupervised classification. However, ICA suffers from computational expensiveness, which limits its application to high dimensional data analysis. In order to make it applicable to hyperspectral image classification, a data preprocessing procedure is employed to reduce the data dimensionality. Noise adjusted principal component analysis (NAPCA) is used for this purpose, which can reorganize the original data information in terms of signal-to-noise ratio, a more appropriate criterion than variance when dealing with images. The preliminary results demonstrate that the selected major components from NAPCA can better represent the object information in the original data than those from ordinary principal component analysis (PCA). As a result, better classification using ICA is expected.
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014
This paper presents a thorough study on the performances of different Independent Component Analysis (ICA) algorithms for the extraction of class-discriminant information in remote sensing hyperspectral image classification. The study considers the three implementations of ICA that are most widely used in signal processing, namely Infomax, FastICA and JADE. The analysis aims to address a number of important issues regarding the use of ICA in the RS domain. Three scenarios are considered and the performances of the ICA algorithms are evaluated and compared against each other, in order to reach the final goal of identifying the most suitable approach to the analysis of hyperspectral images in supervised classification. Different feature extraction and selection techniques are used for dimensionality reduction with ICA and are then compared to the commonly used strategy, which is based on pre-processing data with Principal Components Analysis (PCA) prior to classification. Experimental results obtained on three real hyperspectral data sets from each of the considered algorithms are presented and analyzed in terms of both classification accuracies and computational time.
Classification of Hyperspectral Image using Principal component and Independent Component Analysis
Hyperspectral remote sensing sensors have the ability to acquire images in many narrow spectral bands that are found in the electromagnetic spectrum from visible, near infrared, medium infrared to thermalinfrared. Hyperspectral sensors capture energy from in 200 bands or more which means that they continuously cover the reflecting spectrum for each pixel in the scene. Bands characteristic for these types of sensors arecontinuous and narrow, allowing an indepth examination of features and details on Earth which recorded with multispectral sensors would be lost. The benefits of Hyperion hyperspectral data to LULC mapping have been studied at sites over some areas of Nilgiris district. The purpose of this study is to analyze the classification of hyperspectral images using Principal Component Analysis (PCA) and Independent Component Analysis (ICA). Hyperspectral imagery provides the potential for more accurate and detailed information extraction than is possible with other types of remotely sensed data. The processing of hyperspectral images (Hyperion data) and reducing the redundant signatures through PCA. The PCA processed data will be analyzed for LULC mapping using the Visual Interpretation method over some parts of Nilgiris district. Further the ICA is performed to isolate the spectral signature and that processed image is also applied for LULC Mapping. Finally the two results will get compared to determine the Accuracy Assessment between PCA and ICA. The expected result is, ICA provide more accuracy than the PCA.
Dependent component analysis for hyperspectral image classification
Proceedings of Spie the International Society For Optical Engineering, 2009
Independent component analysis (ICA) has been widely used for hyperspectral image classification in an unsupervised fashion. It is assumed that classes are statistically mutual independent. In practice, this assumption may not be true. In this paper, we apply dependent component analysis (DCA) to unsupervised classification, which does not require the class independency. The basic idea of our DCA approaches is to find a transform that can improve the class independency but leave the basis mixing matrix unchanged; thus, an original ICA method can be employed to the transformed data where classes are less statistically dependent. Linear transforms that possess such a required invariance property and generate less dependent sources include: high-pass filtering, innovation, and wavelet transforms. These three transforms correspond to three different DCA algorithms, which will be investigated in this paper. Preliminary results show that the DCA algorithms can slightly improve the classification accuracy.
IGARSS 2001. Scanning the Present and Resolving the Future. Proceedings. IEEE 2001 International Geoscience and Remote Sensing Symposium (Cat. No.01CH37217), 2001
Independent Component Analysis (ICA) is a multivariate data analysis process largely sudied these last years in the signal processing community for blind source separation. This paper proposes to show the interest of ICA as a tool for unsupervised analysis of hyperspectral images. The commonly used Principal Component Analysis (PCA) is the mean square optimal projection for gaussian data leading to uncorrelated components by using second order statistics. ICA rather uses higher order statistics and leads to independent components, a stronger statistical assumption revealing interesting features in the usually non gaussian hyperspectral data sets.
Dependent component analysis for hyperspectral image classification
Image and Signal Processing for Remote Sensing XV, 2009
Independent component analysis (ICA) has been widely used for hyperspectral image classification in an unsupervised fashion. It is assumed that classes are statistically mutual independent. In practice, this assumption may not be true. In this paper, we apply dependent component analysis (DCA) to unsupervised classification, which does not require the class independency. The basic idea of our DCA approaches is to find a transform that can improve the class independency but leave the basis mixing matrix unchanged; thus, an original ICA method can be employed to the transformed data where classes are less statistically dependent. Linear transforms that possess such a required invariance property and generate less dependent sources include: high-pass filtering, innovation, and wavelet transforms. These three transforms correspond to three different DCA algorithms, which will be investigated in this paper. Preliminary results show that the DCA algorithms can slightly improve the classification accuracy.
INDEPENDENT COMPONENT ANALYSIS FOR CLASSIFYING MULTISPECTRAL IMAGES WITH DIMENSIONALITY LIMITATION
International Journal of Information Acquisition, 2004
Airborne and spaceborne remote sensors can acquire invaluable information about earth surface, which have many important applications. The acquired information usually is represented as two-dimensional grids, i.e. images. One of techniques to processing such images is Independent Component Analysis (ICA), which is particularly useful for classifying objects with unknown spectral signatures in an unknown image scene, i.e. unsupervised classification. Since the weight matrix in ICA is a square matrix for the purpose of mathematical tractability, the number of objects that can be classified is equal to the data dimensionality, i.e. the number of spectral bands. When the number of sensors (or spectral channels) is very small (e.g. a 3-band CIR photograph and 6-band Landsat image with the thermal band being removed), it is impossible to classify all the different objects present in an image scene using the original data. In order to solve this problem, we present a data dimensionality expansion technique to generate artificial bands. Its basic idea is to use nonlinear functions to capture and highlight the similarity/dissimilarity between original spectral measurements, which can provide more data with additional information for detecting and classifying more objects. The results from such a nonlinear band generation approach are compared with a linear band generation method using cubic spline interpolation of pixel spectral signatures. The experiments demonstrate that nonlinear band generation approach can significantly improve unsupervised classification accuracy, while linear band generation method cannot since no new information can be provided. It is also demonstrated that ICA is more powerful than other frequently used unsupervised classification algorithms such as ISODATA.
Band Selection Using Independent Component Analysis for Hyperspectral Image Processing
2003
Although hyperspectral images provide abundant information about objects, their high dimensionality also substantially increases computational burden. Dimensionality reduction offers one approach to Hyperspectral Image (HSI) analysis. Currently, there are two methods to reduce the dimension, band selection and feature extraction. In this paper, we present a band selection method based on Independent Component Analysis (ICA). This method, instead of transforming the original hyperspectral images, evaluates the weight matrix to observe how each band contributes to the ICA unmixing procedure. It compares the average absolute weight coefficients of individual spectral bands and selects bands that contain more information. As a significant benefit, the ICA-based band selection retains most physical features of the spectral profiles given only the observations of hyperspectral images. We compare this method with ICA transformation and Principal Component Analysis (PCA) transformation on classification accuracy. The experimental results show that ICA-based band selection is more effective in dimensionality reduction for HSI analysis.
On the use of ICA for hyperspectral image analysis
2009
Independent component analysis (ICA) is a very popular method that has shown success in blind source separation, feature extraction and unsupervised recognition. In recent years ICA has been largely studied by researchers from the signal processing community. This paper addresses a more in-depth study on the use of this method, applied to hyperspectral images used for remote sensing purposes. In a first part, source separation is addressed. Since the independence of sources is usually not verified in hyperspectral real data images, ICA, if used alone, is not a suitable tool to unmix sources. We propose a hierarchical approximation for the use of ICA as a pre-processing step for a Bayesian Positive Source Separation method. In a second part, the use of ICA for dimensionality reduction is studied in the frame of hyperspectral data classification. Experimental results show the effectiveness of ICA when used for hyperspectral image pre-processing for the two considered applications.