Spatial-spectral Hyperspectral Image Classification Research Articles

Artificial gorilla troops optimizer enfolded broad learning system for spatial-spectral hyperspectral image classification

The key challenge of hyperspectral image (HSI) classification is to develop effective feature representations for reducing intra-class variations while expanding inter-class differences. It is of great interest to exploit texture information in the preprocess stage for HSI classification by using feature extraction operators. Additionally, deep learning (DL) networks have focused on spatial-spectral information extraction. Nevertheless, DL-based approaches are time-consuming to compute and difficult to understand owing to the large number of network parameters and insufficient training data. Responding to these issues, this paper introduces a novel spatial-spectral classification framework based on local optimal oriented pattern (LOOP), artificial gorilla troops optimizer (GTO) enfolded broad learning system (BLS), and bi-exponential edge-preserving smoother (LGBB), which mainly includes the following parts: First, the principal component analysis is used to shrink HSI’s spectral dimensions, and then LOOP extracts the rotation-invariant texture-based spatial signatures from the principal components; Next, GTO, a novel nature-inspired and gradient-free optimization algorithm, is first introduced to BLS for finding the global optimum feature subsets, and then LOOP features are fed into the improved BLS to produce soft-classified probability maps; Finally, post-processing filtering is conducted to optimize the soft-classified probability maps by considering spatial contextual information. Experiment results on four actual HSIs demonstrate that the LGBB framework outperforms previous state-of-the-art approaches in quantitative and qualitative outcomes, especially when training samples are constrained.

Hybrid optimal joint spatial-spectral hyperspectral image classification using modified DHO-based GIF with JRKNN

ABSTRACT Hyperspectral images (HSI) have been extensively utilized in environmental protection, agriculture, and land cover applications. But, it is difficult to classify due to improper exploitation of spatial and spectral features. As a result, this paper proposes a unified guided image filtering (GIF) method that uses a joint representation model of the K-nearest neighbour algorithm (JRKNN) to extract spatial context information and preserve edges while denoising classification results. In addition, a new meta-heuristic optimization algorithm called modified deer hunting optimization (MDHO) is implemented to minimize the cost function in GIF by optimizing the regularization parameter and edge-aware weighting, which is named GIF-MDHO. Finally, the simulation results show that the GIF-MDHO with JRKNN approach performed superior as compared to the existing support vector machine (SVM) by KNN and even the KNN-GIF methods with an improved accuracy of 1.02%, precision, recall , and F1-score of 0.78%, 0.91%, and 0.74%, respectively.

Combined Spatial-Spectral Hyperspectral Image Classification Based on Adaptive Guided Filtering

Hyperspectral image classification has a low accuracy in the face of a small training set. To solve the problem, this paper proposes a combined spatial-spectral hyperspectral image classification approach based on adaptive guided filtering. From coarse to fine classification, the local binary pattern (LBP) histogram features were improved, the spatial contrast description was enhanced, and enhanced spatial-spectral features were prepared through Gabor transform of different scales and directions, combined with super pixel blocks. Then, the pre-classification was completed by the support vector machine (SVM) classifier. To reduce noise interference, the pre-classification results were filtered again by a guided filter based on the adaptive regularization factor. To verify its effectiveness, the proposed approach was compared with the state-of-the-arts approaches through repeated experiments. The comparison shows that our approach achieved a high classification accuracy, while suppressing noise interference. This research provides a new tool for hyperspectral image classification with a small training set.

Task-driven nonlocal uncertainty analysis for hyperspectral image classification using a context-based Bayesian framework

ABSTRACT Spatial contextual information could help to further improve hyperspectral image classification performance. However, most spatial-spectral hyperspectral image classification methods introduce spatial information primarily by combining pixels in a small neighbourhood. These strategies consider only limited spatial structures during classification, which reduces classification accuracy. To this end, a novel, context-based Bayesian framework with a task-driven nonlocal uncertainty analysis model is proposed to combine spectral-spatial features for hyperspectral image classification. Task-dependent measures are often needed to formulate similarity, which is used to express various relationships. Based on this observation, in this paper, we introduce a task-driven similarity measure based on nonlocal uncertainty analysis for hyperspectral classification. Nonlocal-local spatial a priori is constructed using the Dempster-Shafer theory after analysing the spatial uncertainty to a nonlocal extent, which further expands the sample capacity and spatial extent. Furthermore, an improved iterated conditional mode is proposed to acquire the energy function’s local minimum in the context-based Bayesian framework. The experimental results, using both simulated data and two popular hyperspectral data sets, indicate that the proposed methods can significantly improve classification accuracy when compared with other state-of-the-art methods.

Semisupervised Discriminative Random Field for Hyperspectral Image Classification

The integration of spectral and spatial information is crucial in remotely sensed hyperspectral image classification. Some available approaches extract spatial features before classification, while other techniques include spatial information as a spatial regularizer. Due to the model complexity, these methods generally assume that a given pixel is only dependent on itself and its neighboring pixels. However, it is known that there are strong interactions among the pixels in different areas of the image, and as a result, this general assumption can limit the classifier performance. In this work, we develop a new semi-supervised discriminative random field (DRF) technique for spatial-spectral classification of hyperspectral images, which constructs the complete model using the whole image. Furthermore, to cope with the unlabeled samples in the model, a new expectation maximization (EM) based algorithm is introduced to optimize the learning of DRF parameters, where the missing labels of these samples serve as the latent variable. As compared to other conventional learning approaches such as maximum a posteriori marginal (MPM) labeling, the proposed approach can obtain better optimization that leads to improved classification performance. Our experimental results, conducted using real hyperspectral datasets, indicate that the newly developed DRF algorithm exhibits very good performance.

Spatial aware probabilistic multi-kernel collaborative representation for hyperspectral image classification using few labelled samples

ABSTRACT Spatial-spectral hyperspectral image classification methods have gained increasing attention over the past decade. Although most of the methods achieve high performances in classification, they may give unreliable performances under some conditions. One of the most challenging problems is to use a small number of training samples from the data set that contains highly spectral variabilities. In order to overcome this problem, two novel hybrid methods based on spatial aware probabilistic multi-kernel collaborative representation are developed for hyperspectral image classification. These methods consist of dimension reduction, feature extraction, and classification stages. For feature extraction, two powerful methods including domain transform filtering and intrinsic image decomposition are used as spatial-spectral features. In the former method, multiple-kernel matrices of these features are fused with composite kernel technique, and then they are applied to spatial aware probabilistic kernel collaborative representation (PKCR). Here, compared to PKCR, spatial aware PKCR considers an additional spatial term that exploits superpixel-based spatial coordinate relation. In the latter method, kernel matrices are separately applied to spatial aware PKCR and their probabilistic decisions are fused to provide robust performance. In fact, the proposed methods are constructed by feature fusion and decision fusion manner. Experiments are carried out on three widely used data sets, namely, Indian Pines, Pavia University, and Salinas. We have compared the proposed methods with ten different state-of-the-art methods in terms of overall and average accuracies, Kappa coefficients (κ), McNemar Z-scores, and classification maps. Experimental results demonstrate that the proposed methods not only achieve the best classification accuracies among other methods for few labelled samples but also presents effective performances in higher number of training samples.

Spatial-spectral classification of hyperspectral images based on multiple fractal-based features

Hyperspectral images are efficient tools for discriminating different types of earth's surface materials. Spectral features traditionally perform classification of hyperspectral images, but different studies have proved the efficiency of spatial features as complementary information in increasing the classification accuracy. The fractal geometry can be regarded as a potent tool for spatial data modeling. This study proposes a new classification method based on the integration of fractal and spectral features. For this purpose, three groups of fractal features, including mono-fractal, lacunarity and multi-fractal features are generated from the first few principal components of the hyperspectral image in different window sizes. These features are later stacked with spectral features and then fed to support vector machines classifier. The experiments are conducted on two real hyperspectral images Indian Pines, Pavia University. Final classification accuracy proved the superiority of the proposed classification method against the other competitive spatial-spectral methods.

Spatial-spectral hyperspectral image classification based on information measurement and CNN

In order to construct virtual land environment for virtual test, we propose a construction method of virtual land environment using multi-satellite remote sensing data, the key step of which is accurate recognition of ground object. In this paper, a method of ground object recognition based on hyperspectral image (HSI) was proposed, i.e., a HSI classification method based on information measure and convolutional neural networks (CNN) combined with spatial-spectral information. Firstly, the most important three spectra of the hyperspectral image was selected based on information measure. Specifically, the entropy and color-matching functions were applied to determine the candidate spectra sets from all the spectra of the hyperspectral image. Then three spectra with the largest amount of information were selected through the minimum mutual information. Through the above two steps, the dimensionality reduction for hyperspectral images was effectively achieved. Based on the three selected spectra, the CNN network input combined with the spatial-spectral information was designed. Two input strategies were designed: (1) The patch surrounding the pixel to be classified was directly intercepted from the grayscale images of the three selected spectra. (2) In order to highlight the effect of the spectrum of the pixel to be classified, all the spectral components of this pixel were superimposed on the patch obtained by the previous strategy. As a result, a new patch with more prominent spectral components of the pixel to be classified was obtained. Using the two public hyperspectral datasets, Salinas and Pavia Center, the experiments of on both parameter selection and classification performance were performed to verify that the proposed methods had better classification performance.

Spatial‐spectral classification of hyperspectral images: a deep learning framework with Markov Random fields based modelling

For the spatial-spectral classification of hyperspectral images (HSIs), a deep learning framework is proposed in this study, which consists of convolutional neural networks (CNNs) and Markov random fields (MRFs). Firstly, a CNN model to learn the deep spectral feature from the HSI is built and the class posterior probability distribution is estimated. The CNN with a dropout layer can relieve the overfitting in classification. The CNN is utilised as a pixel-classifier, so it only works in the spectral domain. Then, the spatial information will be encoded by MRF-based multilevel logistic prior for regularising the classification. To derive the correlation of both spectral and spatial features for improving algorithm performance, the marginal probability distribution in HSI is learned using MRF-based loopy belief propagation. In comparison with several state-of-the-art approaches for data classification on three publicly available HSI datasets, experimental results have demonstrated the superior performance of the proposed methodology.

Sparse Representation-Based Hyperspectral Image Classification Using Multiscale Superpixels and Guided Filter

We propose a spatial-spectral hyperspectral image classification method based on multiscale superpixels and guided filter (MSS-GF). In order to use spatial information effectively, MSSs are used to get local information from different region scales. Sparse representation classifier is used to generate classification maps for each region scale. Then, multiple binary probability maps are obtained for each of the classification maps. Adding GF denoises the classification results and then improves the classification accuracy. Finally, the class label of each pixel is determined by majority voting rule.

Joint spatial-spectral hyperspectral image classification based on convolutional neural network

Hyperspectral image (HSI) classification technology has been widely used in many earth observation tasks, such as detection, recognition, and surveillance. The traditional hyperspectral image classification methods mainly utilize hand-crafted features, such as edge and texture descriptors, which are not robust for different input data. By contrast, deep learning based methods exploit high-level features for hyperspectral image classification, but they usually degenerate the spatial-spectral structure, depend on a large number of training samples, and ignore a large amount of implicitly useful information. To address these problems, a new joint spatial-spectral hyperspectral image classification method based on different-scale two-stream convolutional network and spatial enhancement strategy is proposed in this paper. First, the pixel blocks at different scales around the center pixel are selected as the basic units to be processed. Then, a spatial enhancement strategy is designed to obtain various spatial location information under the limited training samples by the spatial rotation and row-column transformation. Finally, the spatial-spectral feature is learned by a different-scale two-stream convolutional network, and the classification result of the center pixel is obtained by a softmax layer. Experimental results on two datasets demonstrate that the proposed method outperforms other state-of-the-art methods qualitatively and quantitatively.

Region-Based Relaxed Multiple Kernel Collaborative Representation for Hyperspectral Image Classification

This paper presents a region-based relaxed multiple kernel collaborative representation method for the spatial-spectral classification of hyperspectral images. The proposed method consists of three steps. In the first step, a multiscale method achieved by extending a superpixel segmentation algorithm is designed to capture the spatial-spectral information of hyperspectral images. For each scale, a hyperspectral image can be segmented into several nonoverlapping spectrally similar regions that consist of some spatially adjacent pixels. In the second step, two criteria (i.e., the first two moments) are computed within the regions of each scale to generate the corresponding spatial features. In the final step, a relaxed multiple kernel technique is proposed to fuse the obtained spatial multiscale features and original spectral features in the framework of column generation kernel collaborative representation classification. Experimental results obtained from two real hyperspectral images demonstrate the effectiveness of the proposed method as compared with some popular spatial-spectral techniques.

Locality Preserving Genetic Algorithms for Spatial-Spectral Hyperspectral Image Classification

Recent developments in remote sensing technologies have made hyperspectral imagery (HSI) readily available to detect and classify objects on the earth using pattern recognition techniques. Hyperspectral signatures are composed of densely sampled reflectance values over a wide range of the spectrum. Although most of the traditional approaches for HSI analysis entail per-pixel spectral classification, spatial-spectral exploitation of HSI has the potential to further improve the classification performance-particularly when there is unique class-specific textural information in the scene. Since the dimensionality of such remotely sensed imagery is often very large, especially in spatial-spectral feature domain, a large amount of training data is required to accurately model the classifier. In this paper, we propose a robust dimensionality reduction approach that effectively addresses this problem for hyperspectral imagery (HSI) analysis using spectral and spatial features. In particular, we propose a new dimensionality reduction algorithm, GA-LFDA where a Genetic Algorithm (GA) based feature selection and Local-Fisher's Discriminant Analysis (LFDA) based feature projection are performed in a raw spectral-spatial feature space for effective dimensionality reduction. This is followed by a parametric Gaussian mixture model classifier. Classification results with experimental data show that our proposed method outperforms traditional dimensionality reduction and classification algorithms in challenging small training sample size and mixed pixel conditions.