Accuracy Of Hyperspectral Image Classification Research Articles

Spectral–spatial hyperspectral image ensemble classification via joint sparse representation

Ensemble learning can improve the performance of classification by integrating a set of classifiers, and shows significant potential benefits to the classification of hyperspectral image. However, the ensemble strategy remarkably influences the classification results, which include determining the minimum number of classifiers and assigning advisable weights associated with each classifier. In this paper, we present a novel sparse ensemble learning method with spectral–spatial knowledge for hyperspectral image classification. It considers the ensemble strategy under sparse recovery framework, where the solved non-zero coefficients reveal the importance of the selected classifier, from which a compact and effective ensemble learning system can be derived. Moreover, the spatial information is incorporated into the classification to develop a spectral–spatial joint sparse representation based ensemble learning algorithm for more accurate classification of hyperspectral images. Experimental results on several real hyperspectral images show that the proposed sparse ensemble system can achieve better performance than traditional ensemble learning methods using all classifiers, and it largely improves the efficiency in testing phase.

Spectral–Spatial Hyperspectral Image Classification Based on KNN

Fusion of spectral and spatial information is an effective way in improving the accuracy of hyperspectral image classification. In this paper, a novel spectral–spatial hyperspectral image classification method based on K nearest neighbor (KNN) is proposed, which consists of the following steps. First, the support vector machine is adopted to obtain the initial classification probability maps which reflect the probability that each hyperspectral pixel belongs to different classes. Then, the obtained pixel-wise probability maps are refined with the proposed KNN filtering algorithm that is based on matching and averaging nonlocal neighborhoods. The proposed method does not need sophisticated segmentation and optimization strategies while still being able to make full use of the nonlocal principle of real images by using KNN, and thus, providing competitive classification with fast computation. Experiments performed on two real hyperspectral data sets show that the classification results obtained by the proposed method are comparable to several recently proposed hyperspectral image classification methods.

GURLS vs LIBSVM: Performance Comparison of Kernel Methods for Hyperspectral Image Classification

Kernel based methods have emerged as one of the most promising techniques for Hyper Spectral Image classification and has attracted extensive research efforts in recent years. This paper introduces a new kernel based framework for Hyper Spectral Image (HSI) classification using Grand Unified Regularized Least Squares (GURLS) library. The proposed work compares the performance of different kernel methods available in GURLS package with the library for Support Vector Machines namely, LIBSVM. The assessment is based on HSI classification accuracy measures and computation time. The experiment is performed on two standard Hyper Spectral datasets namely, Salinas A and Indian Pines subset captured by AVIRIS (Airborne Visible Infrared Imaging Spectrometer) sensor. From the analysis, it is observed that GURLS library is competitive to LIBSVM in terms of its prediction accuracy whereas computation time seems to favor LIBSVM. The major advantage of GURLS toolbox over LIBSVM is its simplicity, ease of use, automatic parameter selection and fast training and tuning of multi-class classifier. Moreover, GURLS package is provided with an implementation of Random Kitchen Sink algorithm, which can easily handle high dimensional Hyper Spectral Images at much lower computational cost than LIBSVM.

Semantic classification for hyperspectral image by integrating distance measurement and relevance vector machine

Accurate hyperspectral image classification requires not only image features but also semantic concept. Similarity and relevance relation are both key factors in building image features and semantic measurement. To perform hyperspectral image classification from the viewpoint of semantic, this study focuses on creating a semantic annotation-based image classification method with relevance and similarity measurement. First, the computational model of relevance vector machine is utilized to perform cluster computation for hyperspectral image data. Then multi-distance learning algorithm is optimized as holding capability for multiple dimensions data. The proposed multi-distance learning algorithm with multiple dimensions is used to measure the similarity, according to the result of cluster computation through relevance vector machine. Finally, semantic annotation is introduced to complete classification of hyperspectral image with semantic concept. Validation with the ground truth data illustrates that the proposed method can provide more accurate and integrated classification result compared with the other methodologies. Therefore, the integration of similarity and relevance measurement is able to improve the performance of hyperspectral image classification.

Hyperspectral Image Classification Using Functional Data Analysis

The large number of spectral bands acquired by hyperspectral imaging sensors allows us to better distinguish many subtle objects and materials. Unlike other classical hyperspectral image classification methods in the multivariate analysis framework, in this paper, a novel method using functional data analysis (FDA) for accurate classification of hyperspectral images has been proposed. The central idea of FDA is to treat multivariate data as continuous functions. From this perspective, the spectral curve of each pixel in the hyperspectral images is naturally viewed as a function. This can be beneficial for making full use of the abundant spectral information. The relevance between adjacent pixel elements in the hyperspectral images can also be utilized reasonably. Functional principal component analysis is applied to solve the classification problem of these functions. Experimental results on three hyperspectral images show that the proposed method can achieve higher classification accuracies in comparison to some state-of-the-art hyperspectral image classification methods.

Feature Extraction of Hyperspectral Images With Image Fusion and Recursive Filtering

Feature extraction is known to be an effective way in both reducing computational complexity and increasing accuracy of hyperspectral image classification. In this paper, a simple yet quite powerful feature extraction method based on image fusion and recursive filtering (IFRF) is proposed. First, the hyperspectral image is partitioned into multiple subsets of adjacent hyperspectral bands. Then, the bands in each subset are fused together by averaging, which is one of the simplest image fusion methods. Finally, the fused bands are processed with transform domain recursive filtering to get the resulting features for classification. Experiments are performed on different hyperspectral images, with the support vector machines (SVMs) serving as the classifier. By using the proposed method, the accuracy of the SVM classifier can be improved significantly. Furthermore, compared with other hyperspectral classification methods, the proposed IFRF method shows outstanding performance in terms of classification accuracy and computational efficiency.

Spectral–Spatial Preprocessing Using Multihypothesis Prediction for Noise-Robust Hyperspectral Image Classification

Spectral-spatial preprocessing using multihypothesis prediction is proposed for improving accuracy of hyperspectral image classification. Specifically, multiple spatially collocated pixel vectors are used as a hypothesis set from which a prediction for each pixel vector of interest is generated. Additionally, a spectral-band-partitioning strategy based on inter-band correlation coefficients is proposed to improve the representational power of the hypothesis set. To calculate an optimal linear combination of the hypothesis predictions, a distance-weighted Tikhonov regularization to an ill-posed least-squares optimization is used. The resulting predictions effectively integrate spectral and spatial information and thus are used during classification in lieu of the original pixel vectors. This processed hyperspectral image dataset has less intraclass variability and more spatial regularity as compared to the original dataset. Classification results for two hyperspectral image datasets demonstrate that the proposed method can enhance the classification accuracy of both maximum-likelihood and support vector classifiers, especially under small sample size constraints and noise corruption.

A Novel Method for Hyperspectral Image Classification Based on Laplacian Eigenmap Pixels Distribution-Flow

The accurate classification of hyperspectral images is an important task for many practical applications. In this paper, a new method for hyperspectral image classification is proposed based on manifold learning algorithm, The approach introduced here presents three major contributions: 1) a new Laplacian eigenmap pixels distribution-flow (LE PD-Flow) is proposed for hyperspectral image analysis, in which, a new joint spatial-pixel characteristics distance (JSPCD) measure is constructed to improve the accuracy of classification and a suitable weighting factor is used to distinguish data points of different classes by combining the spectral feature with the spatial feature; 2) the adjustment strategy of each manifold mappings is addressed, which allows not only better visualization of the results, but also the comparisons of mapping results with an appropriate measurement; 3) in order to get useful boundary points used for classification, single threshold and multiple thresholds method are presented to solve small scale and large scale classification problem, respectively. We can easily obtain the expected classification results by adjusting the weights of the two kinds of feature of hyperspectral image. With the LE PD-Flow, variation of pixels on the boundaries for classification can be found, and then hyperspectral data can be labeled with high accuracy. Experimental results show that the proposed method is effective for classification of hyperspectral image.

Hyperspectral Image Classification Using Empirical Mode Decomposition With Spectral Gradient Enhancement

This paper proposes to use empirical mode decomposition (EMD) with spectral gradient enhancement to increase the classification accuracy of hyperspectral images with support vector machine (SVM) classification. Recently, it has been shown that higher hyperspectral image classification accuracy can be achieved by using 2-D EMD that is applied to each hyperspectral band separately to obtain the intrinsic mode functions (IMFs) of each band, while the sum of the IMFs are used as feature data in the SVM classification process. In the previous approach, IMFs have been summed directly, i.e., with equal weights. It is shown in this paper, that it is possible to significantly increase the classification accuracy by using appropriate weights for the IMFs in the summation process. In the proposed approach, the weights of the IMFs are obtained so as to optimize the total absolute spectral gradient, and a genetic algorithm-based optimization strategy has been adopted to obtain the weights automatically in this way. While the 2-D EMD basically provides spatial processing, the proposed method further incorporates spectral enhancement into the process. It is shown that a significant increase in hyperspectral image classification accuracy can be achieved using the proposed approach.

Using OWA Fusion Operators for the Classification of Hyperspectral Images

In this paper, we propose a novel ensemble-based classification system for improving the classification accuracy of hyperspectral images. To generate the ensemble, we run the mean-shift (MS) algorithm several times on different bands randomly selected from the hyperspectral cube and with distinct kernel width parameters. The resulting set of MS maps are then successively labeled via a pair wise labeling procedure with respect to a spectral-based classification map generated by the support vector machine (SVM) classifier. To this end, for each region in the MS maps, the weighted-majority-voting (WMV) rule is applied to the corresponding pixels in the SVM map. The output of this step is a set of spectral-spatial classification maps termed as SVM-MS maps. In order to generate the final classification result, we propose to aggregate this set of SVM-MS maps using the ordered weighted averaging (OWA) operator. The determination of the associated weights is made using the idea of a stress function. The performance of the proposed classification system is assessed on three different hyperspectral datasets acquired by the Reflective Optics System Imaging Spectrometer (ROSIS-03), the Digital Imagery Collection Experiment (HYDICE) and the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) sensors.

Advances in Spectral-Spatial Classification of Hyperspectral Images

Recent advances in spectral-spatial classification of hyperspectral images are presented in this paper. Several techniques are investigated for combining both spatial and spectral information. Spatial information is extracted at the object (set of pixels) level rather than at the conventional pixel level. Mathematical morphology is first used to derive the morphological profile of the image, which includes characteristics about the size, orientation, and contrast of the spatial structures present in the image. Then, the morphological neighborhood is defined and used to derive additional features for classification. Classification is performed with support vector machines (SVMs) using the available spectral information and the extracted spatial information. Spatial postprocessing is next investigated to build more homogeneous and spatially consistent thematic maps. To that end, three presegmentation techniques are applied to define regions that are used to regularize the preliminary pixel-wise thematic map. Finally, a multiple-classifier (MC) system is defined to produce relevant markers that are exploited to segment the hyperspectral image with the minimum spanning forest algorithm. Experimental results conducted on three real hyperspectral images with different spatial and spectral resolutions and corresponding to various contexts are presented. They highlight the importance of spectral-spatial strategies for the accurate classification of hyperspectral images and validate the proposed methods.

A novel binary tree support vector machine for hyperspectral remote sensing image classification

According to the principle of support vector machine (SVM) and the inter-class separability rule of hyperspectral data, a novel binary tree SVM classifier based on separability measure among different classes is proposed for hyperspectral image classification. J–M distance is used to measure the separability in order to generate the binary tree automatically. By experiments using airborne operational modular imaging spectrometer II (OMIS II) data, satellite EO-1 Hyperion hyperspectral data and airborne AVIRIS data, the classification accuracy of different multi-class SVMs is obtained and compared. Experimental results indicate that the proposed adaptive binary tree classifier outperforms other existing multi-class SVM strategies. Use of the adaptive binary tree SVM classifier is a novel approach to improve the accuracy of hyperspectral image classification and expand the possibilities for interpretation and application of hyperspectral remote sensing image.

组合多核支持向量机和小波变换的高光谱遥感影像分类方法研究

Many remote sensing image classifiers are limited in their ability to combine spectral features with spatial features. Multi-kernel classifiers, however, are capable of integrating spectral features with spatial or structural features using multiple kernels and summing them for final outputs. Using a support vector machine (SVM) as classifier, different multi-kernel classifiers are constructed and tested using 64-band Operational Modular Imaging Spectrometer II hyperspectral image of Changping Area, Beijing City. Results show that by integrating spectral and wavelet texture information, multi-kernel SVM classifiers can obtain more accurate classification results than sole-kernel SVM classifiers and cross-information SVM kernel classifiers. Moreover, when the multi-kernel SVM classifier is used, the combination of the first four principal components from principal component analysis and wavelet texture provides the highest accuracy (97.06%). Multi-kernel SVM is therefore an effective approach to improve the accuracy of hyperspectral image classification and to expand possibilities for remote sensing image interpretation and application.

SVM- and MRF-Based Method for Accurate Classification of Hyperspectral Images

The high number of spectral bands acquired by hyperspectral sensors increases the capability to distinguish physical materials and objects, presenting new challenges to image analysis and classification. This letter presents a novel method for accurate spectral-spatial classification of hyperspectral images. The proposed technique consists of two steps. In the first step, a probabilistic support vector machine pixelwise classification of the hyperspectral image is applied. In the second step, spatial contextual information is used for refining the classification results obtained in the first step. This is achieved by means of a Markov random field regularization. Experimental results are presented for three hyperspectral airborne images and compared with those obtained by recently proposed advanced spectral-spatial classification techniques. The proposed method improves classification accuracies when compared to other classification approaches.

Hyperspectral Analysis of Columbia Spotted Frog Habitat

Abstract: Wildlife managers increasingly are using remotely sensed imagery to improve habitat delineations and sampling strategies. Advances in remote sensing technology, such as hyperspectral imagery, provide more information than previously was available with multispectral sensors. We evaluated accuracy of high‐resolution hyperspectral image classifications to identify wetlands and wetland habitat features important for Columbia spotted frogs (Rana luteiventris) and compared the results to multispectral image classification and United States Geological Survey topographic maps. The study area spanned 3 lake basins in the Salmon River Mountains, Idaho, USA. Hyperspectral data were collected with an airborne sensor on 30 June 2002 and on 8 July 2006. A 12‐year comprehensive ground survey of the study area for Columbia spotted frog reproduction served as validation for image classifications. Hyperspectral image classification accuracy of wetlands was high, with a producer's accuracy of 96% (44 wetlands) correctly classified with the 2002 data and 89% (41 wetlands) correctly classified with the 2006 data. We applied habitat‐based rules to delineate breeding habitat from other wetlands, and successfully predicted 74% (14 wetlands) of known breeding wetlands for the Columbia spotted frog. Emergent sedge microhabitat classification showed promise for directly predicting Columbia spotted frog egg mass locations within a wetland by correctly identifying 72% (23 of 32) of known locations. Our study indicates hyperspectral imagery can be an effective tool for mapping spotted frog breeding habitat in the selected mountain basins. We conclude that this technique has potential for improving site selection for inventory and monitoring programs conducted across similar wetland habitat and can be a useful tool for delineating wildlife habitats.

Hyperspectral Analysis of Columbia Spotted Frog Habitat

Wildlife managers increasingly are using remotely sensed imagery to improve habitat delineations and sampling strategies. Advances in remote sensing technology, such as hyperspectral imagery, provide more information than previously was available with multispectral sensors. We evaluated accuracy of high-resolution hyperspectral image classifications to identify wetlands and wetland habitat features important for Columbia spotted frogs (Rana luteiventris) and compared the results to multispectral image classification and United States Geological Survey topographic maps. The study area spanned 3 lake basins in the Salmon River Mountains, Idaho, USA. Hyperspectral data were collected with an airborne sensor on 30 June 2002 and on 8 July 2006. A 12-year comprehensive ground survey of the study area for Columbia spotted frog reproduction served as validation for image classifications. Hyperspectral image classification accuracy of wetlands was high, with a producer's accuracy of 96% (44 wetlands) correctly classified with the 2002 data and 89% (41 wetlands) correctly classified with the 2006 data. We applied habitat-based rules to delineate breeding habitat from other wetlands, and successfully predicted 74% (14 wetlands) of known breeding wetlands for the Columbia spotted frog. Emergent sedge microhabitat classification showed promise for directly predicting Columbia spotted frog egg mass locations within a wetland by correctly identifying 72% (23 of 32) of known locations. Our study indicates hyperspectral imagery can be an effective tool for mapping spotted frog breeding habitat in the selected mountain basins. We conclude that this technique has potential for improving site selection for inventory and monitoring programs conducted across similar wetland habitat and can be a useful tool for delineating wildlife habitats.

Influence Of Lossy Compression OnHyperspectral Image Classification Accuracy

In this paper the relationship between compression rate and classification accuracy for hyperspectral images is studied. We construct several classification trees using CART and then, for various rates, we measure their classification accuracy after the input image has been compressed. We compare two kinds of classification trees: first, we construct onestage trees, which classify the input image using only a single classification stage. Second, we construct multi-stage trees; these use a mixed class that delays classification of problematic pixels for which the accuracy achieved in the current stage is not enough. Then, for several compression rates, we study the classification accuracy evolution of such trees when a lossy compression method is applied to the input image before the classification stage. The JPEG standard for still image compression is taken as the basis lossy method. We then employ a three-dimensional extension of the JPEG standard in order to take advantage of band correlation. We also reduce the input image dimension using a basic analysis based on a previous classification tree, so that the best set of classification features is chosen. Our experiments show that it is possible to achieve high compression rates without degrading classification accuracy too much. Results indicate that multi-stage classification trees yield similar classification performance than one-stage trees at a reduced cost. In addition, it is also possible to obtain higher compression rates by means of a three-dimensional lossy compression method. Data Mining II, C.A. Brebbia & N.F.F. Ebecken (Editors) © 2000 WIT Press, www.witpress.com, ISBN 1-85312-821-X