Yushi Chen

Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks

Due to the advantages of deep learning, in this paper, a regularized deep feature extraction (FE) method is presented for hyperspectral image (HSI) classification using a convolutional neural network (CNN). The proposed approach employs several convolutional and pooling layers to extract deep features from HSIs, which are nonlinear, discriminant, and invariant. These features are useful for image classification and target detection. Furthermore, in order to address the common issue of imbalance between high dimensionality and limited availability of training samples for the classification of HSI, a few strategies such as L2 regularization and dropout are investigated to avoid overfitting in class data modeling. More importantly, we propose a 3-D CNN-based FE model with combined regularization to extract effective spectral-spatial features of hyperspectral imagery. Finally, in order to further improve the performance, a virtual sample enhanced method is proposed. The proposed approaches are carried out on three widely used hyperspectral data sets: Indian Pines, University of Pavia, and Kennedy Space Center. The obtained results reveal that the proposed models with sparse constraints provide competitive results to state-of-the-art methods. In addition, the proposed deep FE opens a new window for further research.

Advanced Spectral Classifiers for Hyperspectral Images: A review

Hyperspectral image classification has been a vibrant area of research in recent years. Given a set of observations, i.e., pixel vectors in a hyperspectral image, classification approaches try to allocate a unique label to each pixel vector. However, the classification of hyperspectral images is a challenging task for a number of reasons, such as the presence of redundant features, the imbalance among the limited number of available training samples, and the high dimensionality of the data.

A Self-Improving Convolution Neural Network for the Classification of Hyperspectral Data

In this letter, a self-improving convolutional neural network (CNN) based method is proposed for the classification of hyperspectral data. This approach solves the so-called curse of dimensionality and the lack of available training samples by iteratively selecting the most informative bands suitable for the designed network via fractional order Darwinian particle swarm optimization. The selected bands are then fed to the classification system to produce the final classification map. Experimental results have been conducted with two well-known hyperspectral data sets: Indian Pines and Pavia University. Results indicate that the proposed approach significantly improves a CNN-based classification method in terms of classification accuracy. In addition, this letter uses the concept of dither for the first time in the remote sensing community to tackle overfitting.

Optimizing Subspace SVM Ensemble for Hyperspectral Imagery Classification

In hyperspectral remote sensing image classification, ensemble systems with support vector machine (SVM), such as the Random Subspace SVM Ensemble (RSSE), have significantly outperformed single SVM on the robustness and overall accuracy. In this paper, we introduce a novel subspace mechanism, the Optimizing Subspace SVM Ensemble (OSSE), to improve RSSE by selecting discriminating subspaces for individual SVMs. The framework is based on Genetic Algorithm (GA), adopting the Jeffries-Matusita (JM) distance as a criterion, to optimize the selected subspaces. The combination of optimizing subspaces is more suitable for classification than the random one, at the same time having the ability to accommodate requisite diversity within the ensemble. The modifications have improved the accuracies of individual classifiers; as a result, better overall accuracies are present. Experiments on the classification of two hyperspectral datasets reveal that our proposed OSSE obtains sound performances compared with RSSE, single SVM, and other ensemble with GA to optimize SVM.

Spectral-spatial classification of hyperspectral image using autoencoders

Hyperspectral image (HSI) classification is a hot topic in the remote sensing community. This paper proposes a new framework of spectral-spatial feature extraction for HSI classification, in which for the first time the concept of deep learning is introduced. Specifically, the model of autoencoder is exploited in our framework to extract various kinds of features. First we verify the eligibility of autoencoder by following classical spectral information based classification and use autoencoders with different depth to classify hyperspectral image. Further in the proposed framework, we combine PCA on spectral dimension and autoencoder on the other two spatial dimensions to extract spectral-spatial information for classification. The experimental results show that this framework achieves the highest classification accuracy among all methods, and outperforms classical classifiers such as SVM and PCA-based SVM.

Deep Fusion of Remote Sensing Data for Accurate Classification

The multisensory fusion of remote sensing data has obtained a great attention in recent years. In this letter, we propose a new feature fusion framework based on deep neural networks (DNNs). The proposed framework employs deep convolutional neural networks (CNNs) to effectively extract features of multi-/hyperspectral and light detection and ranging data. Then, a fully connected DNN is designed to fuse the heterogeneous features obtained by the previous CNNs. Through the aforementioned deep networks, one can extract the discriminant and invariant features of remote sensing data, which are useful for further processing. At last, logistic regression is used to produce the final classification results. Dropout and batch normalization strategies are adopted in the deep fusion framework to further improve classification accuracy. The obtained results reveal that the proposed deep fusion model provides competitive results in terms of classification accuracy. Furthermore, the proposed deep learning idea opens a new window for future remote sensing data fusion.

A BOI-Preserving-Based Compression Method for Hyperspectral Images

Hyperspectral images (HSI) regularly contain hundreds of bands, which are of different importance in the application. Most HSI compression methods usually deal with most bands in the same way, and they do not take the difference of different bands into consideration, which may cause the loss of important spectral information. In order to preserve the spectral information of interest for applications, a new band-of-interest (BOI)-preserving-based HSI compression method is proposed. The conception of BOI is proposed because some bands are significant in the specific applications, and BOI selection methods are chosen according to application requirements. BOI selection is first performed according to application measurements. Then, BOI information is fed into recursive bidirection prediction (RBP) and set partition in hierarchical trees (SPIHT) compression scheme which uses RBP for spectral decorrelation followed by SPIHT algorithm for coding the resulting decorrelated residual images. More bits are allocated to BOI to preserve BOI by two approaches, respectively. Compress BOI and non-BOI bands directly with low distortion and high distortion, respectively, and compress all bands with low distortion and perform a postcompression truncation. Experiments are implemented with different settings using AVIRIS images. Results indicate that the proposed two methods both can achieve excellent compression efficiency and reconstructed quality. In addition, they can improve the application effect in both material classification and target recognition. Compared with non-BOI compression algorithm, at the compression ratio of 80, the proposed methods improve the classification accuracy by 2% and target recognition accuracy by 9%.

Deep fusion of hyperspectral and LiDAR data for thematic classification

Recently, the fusion of hyperspectral and light detection and ranging (LiDAR) data has obtained a great attention in the remote sensing community. In this paper, we propose a new feature fusion framework using deep neural network (DNN). The proposed framework employs a novel 3D convolutional neural network (CNN) to extract the spectral-spatial features of hyperspectral data, a deep 2D CNN to extract the elevation features of LiDAR data, and then a fully connected deep neural network to fuse the extracted features in the previous CNNs. Through the aforementioned three deep networks, one can extract the discriminant and invariant features of hyperspectral and LiDAR data. At last, logistic regression is used to produce the final classification results. The experimental results reveal that the proposed deep fusion model provides competitive results. Furthermore, the proposed deep fusion idea opens a new window for future research.

Hyperspectral data clustering based on density analysis ensemble

ABSTRACT In this letter, we present a new hyperspectral data-clustering method, named density analysis ensemble, from a different perspective. Instead of distance-based metrics in traditional clustering methods, we use density analysis for hyperspectral data clustering. Moreover, in order to improve the performance, we use the random subspace ensemble method to formulate a set of clustering systems. The final results are retrieved through majority voting. Compared to the k-means method, the overall accuracies have been improved by 7.05% and 6.93% for the Salinas and Pavia University data sets, respectively.

Adaptive Morphological Filtering Method for Structural Fusion Restoration of Hyperspectral Images

Recovering hyperspectral image (HSI) from mixed noise degradation is a challenging and promising theme in remote sensing, particularly when stripes and deadlines exist in several contiguous bands. This paper proposes a HSIs restoration method making use of adaptive morphological filtering (AMF) and fusing structure information of an auxiliary color image. An adaptive structuring element (ASE) indicating morphological features of each pixel is generated through information fusion, to simultaneously remove the mixed noise and preserve fine spatial structures. This key technology contains three main steps. First, edges are extracted from the auxiliary image exploiting its color information; then, an edge-constraint growing algorithm is used to generate the clustering kernel; finally, the ASE is obtained via goal-guided k-means clustering. The ASE has extensive application value, for it can be an enhancing module for most filters-based restoration methods, to mitigate the structural damage due to the fixed mask. Among these methods, Gaussian filter for preprocessing and majority voting for postprocessing are introduced in this paper as representatives. In addition, the auxiliary image can be both visible image of multisensor and false RGB component of the undamaged bands of the HSI, so it is relatively available. Experiments on simulated and real data sets show obvious effects on denoising and destriping both subjectively and objectively. The advantage of ASE on structure details preserving, compared to conventional approaches, is clearly demonstrated. The application value of the proposed restoration frame and ASE is further proved through the decision-level postprocessing experiments.