Reflective Optics System Imaging Spectrometer Research Articles

Hyperspectral remote sensing image classification based on tighter random projection with minimal intra-class variance algorithm

Aiming at solving the problem of image size limiting in the traditional Random Projection (RP) algorithm, a novel Tighter Random Projection (TRP), which combines the scheme with Minimal Intra-class Variance (TRP-MIV) for hyperspectral remote sensing image classification is proposed. First, a new tighter dimensional boundary for expanding image size with the TRP-MIV matrix selected by multiple sampling for improving the class separability is defined to reduce dimension. Then the proposed algorithm is implemented, which integrates TRP-MIV for dimensionality reduction and Minimum Distance (MD) classifier for image classification. Finally, the image size and dimensionality reduction are evaluated by the number of spectral pixels under different theorems, and the spectral difference before and after dimensionality reduction, respectively. Classification performance is evaluated by kappa coefficient, Overall Accuracy (OA), Average Accuracy (AA), Average Precision Rate (APR) and running time. Classification results are obtained from the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) scanner and the Reflective Optics System Imaging Spectrometer (ROSIS) scanner, which indicate that the proposed algorithm is efficient and promising.

Performance Analysis of Advanced Decision Forest Algorithms in Hyperspectral Image Classification

In this study, the performances of random forest (<small>RF</small>), rotation forest (<small>RoF</small>), and canonical correlation forest (<small>CCF</small>) algorithms were compared and analyzed for classification of hyperspectral imagery. For this purpose, the Airborne Visible/Infrared Imaging Spectrometer (<small>AVIRIS</small>) Indian Pine (<small>IP</small>), the Reflective Optics System Imaging Spectrometer University of Pavia, and the AVIRIS Kennedy Space Center (<small>KSC</small>) data sets were used as main data sources. In addition to the confusion matrix–derived accuracy measures (overall accuracy, kappa coefficient, F-scores), the performances of the algorithms were analyzed in detail considering three diversity measures (Q statistics, correlations, and interrater agreements) and a kappa-error diagram. Results showed that the highest classification accuracies (87% for IP, 94% for PU, and 93% for KSC data sets) were achieved with the use of CCF algorithm, and improvements in classification accuracy were statistically significant compared to RF and RoF. Based on the diversity measures and the kappa-error diagram, individual learners in the CCF ensemble were found to be more diverse and accurate.

Hyperspectral image classification using graph-based wavelet transform

ABSTRACTGraph-based methods are developed to efficiently extract data information. In particular, these methods are adopted for high-dimensional data classification by exploiting information residing on weighted graphs. In this paper, we propose a new hyperspectral texture classifier based on graph-based wavelet transform. This recent graph transform allows extracting textural features from a constructed weighted graph using sparse representative pixels of hyperspectral image. Different measurements of spectral similarity between representative pixels are tested to decorrelate close pixels and improve the classification precision. To achieve the hyperspectral texture classification, Support Vector Machine is applied on spectral graph wavelet coefficients. Experimental results obtained by applying the proposed approach on Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) and Reflective Optics System Imaging Spectrometer (ROSIS) datasets provide good accuracy which could exceed 98.7%. Compared to other famous classification methods as conventional deep learning-based methods, the proposed method achieves better classification performance. Results have shown the effectiveness of the method in terms of robustness and accuracy.

A novel spatial recurrent neural network for hyperspectral imagery classification

Abstract. Hyperspectral images (HSIs) contain hundreds of spectral bands, providing high-resolution spectral information pertaining to the Earth’s surface. Additionally, abundant spatial contextual information can also be obtained simultaneously from a HSI. To characterize the properties of ground objects, classification is the most widely-used technology in the field of remote sensing, where each pixel in a HSI is assigned to a pre-defined class. Over the past decade, deep learning has attracted increasing attention in the machine-learning and computer-vision domains, due to its favourable performances for various types of tasks, and it has been successfully introduced to the remote-sensing community. Instead of utilizing the shallow features within in a given image, which is the approach that is generally adopted in other conventional classification methods, deep-learning algorithms can extract hierarchical features from raw HSI data. Within the deep-learning framework, recurrent neural networks (RNNs), which are able to encode sequential features, have exhibited promising capabilities and have achieved encouraging performances, especially for the natural-language processing and speech-recognition communities. As multi-temporal remote-sensing images can be readily obtained from increasing numbers of satellite and unmanned aircraft systems, and since analysis of such multi-temporal data comprises a critical issue within numerous research subfields, including land-cover and land-change analyses, and land-resource management, RNNs have been applied in recent studies in order to extract temporal sequential features from multi-temporal remote-sensing images for the purpose of image classification. Apart from using multi-temporal image datasets, RNNs can also be utilized on a single image, where the spectral feature/band of each individual pixel can be taken as a sequential feature for the input layer of RNNs. However, the application of such sequential feature extraction that relies on a single image still needs to be further investigated since applying RNNs to spectral bands will directly introduce more parameters that need to be optimized, consequently increasing the total training time.In this study, we propose a novel RNN-based HSI classification framework. In this framework, unlabelled pixels obtained from a single image are considered when constructing sequential features. Two spatial similarity measurements, referred to as pixel-matching and block-matching, respectively, are employed to extract pixels that are “similar” to the target pixel. Then, the sequential feature of the target pixel is constructed by exploiting several of the most “similar” pixels and ordering them based on their similarities to the target pixel. The aforementioned two schemes are advantageous, as unlabelled pixels within the given HSI are taken into consideration for similarity measurement and sequential feature construction for the RNN model. Moreover, the block-matching scheme also takes advantage of spatial contextual information, which has been widely utilized in spatial-spectral-based HSI classification methods. To evaluate the proposed methods, two benchmark HSIs are used, including a HSI collected over Pavia University, Italy by the airborne Reflective Optics System Imaging Spectrometer (ROSIS) sensor, and an image acquired over the Salinas Valley, California, USA via the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) sensor. Spatio-temporally coincident ground-reference data accompanies each of these respective HSIs. In addition, the proposed methods are compared with three state-of-the-art algorithms, including support vector machine (SVM), the 1-dimensional convolutional neural network (1DCNN), and the 1-dimensional RNN (1DRNN).Experimental results indicate that our proposed methods achieve markedly better classification performance compared with the baseline algorithms on both datasets. For example, for the Pavia University image, the block-matching based RNN achieves the highest overall classification accuracy, with 94.32% accuracy, which is 9.87% higher than the next most accurate algorithm of the aforementioned three baseline methods, which in this case is the 1DCNN, with 84.45% overall accuracy. More specifically, the block-matching method performs better than the pixel-matching method in terms of both quantitative and qualitative assessments. Based on visual assessment/interpretation of the classification maps, it is apparent that “salt-and-pepper” noise is markedly alleviated; with block-matching, smoother classified images are generated compared with pixel-matching-based methods and the three baseline algorithms. Such results demonstrate the effectiveness of utilizing spatial contextual information in the similarity measurement.

A Novel Tri-Training Technique for the Semi-Supervised Classification of Hyperspectral Images Based on Regularized Local Discriminant Embedding Feature Extraction

This paper introduces a novel semi-supervised tri-training classification algorithm based on regularized local discriminant embedding (RLDE) for hyperspectral imagery. In this algorithm, the RLDE method is used for optimal feature information extraction, to solve the problems of singular values and over-fitting, which are the main problems in the local discriminant embedding (LDE) and local Fisher discriminant analysis (LFDA) methods. An active learning method is then used to select the most useful and informative samples from the candidate set. In the experiments undertaken in this study, the three base classifiers were multinomial logistic regression (MLR), k-nearest neighbor (KNN), and random forest (RF). To confirm the effectiveness of the proposed RLDE method, experiments were conducted on two real hyperspectral datasets (Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) and Reflective Optics System Imaging Spectrometer (ROSIS)), and the proposed RLDE tri-training algorithm was compared with its counterparts of tri-training alone, LDE, and LFDA. The experiments confirmed that the proposed approach can effectively improve the classification accuracy for hyperspectral imagery.

A new neuro-fuzzy-based classification approach for hyperspectral remote sensing images

Hyperspectral images are widely used in many applications. However, finding the appropriate hyperspectral image classification technique is a challenge. In this paper, we propose a new method by using an artificial intelligence-based method for hyperspectral image classification. The system has two parts: first, a pre-processing step, which helps the training phase to work faster; and second, the training part, which consists of calculating the neuro-fuzzy parameters. The prepared system is then applied to the classification of images. Three well-known hyperspectral datasets, including Pavia University from reflective optics system imaging spectrometer, the Botswana image from Hyperion and the Indian Pine image from airborne visible/infrared imaging spectrometer, were chosen to test the method. The final results of the experiments show that this system outperforms two classical methods of hyperspectral classification: support vector machine and spectral angle mapper. The comparison of the final results was made using two different metrics: overall accuracy and total disagreement. The proposed method increases the overall accuracy by about 5% for the Pavia University dataset, 2% for the Botswana dataset and 7% for the Indian Pine dataset. The total disagreement was reduced by about 0.01 for the Pavia University, 0.03 for the Botswana and 0.1 for the Indian Pine dataset when the proposed method was applied.

Supervised classification methods applied to airborne hyperspectral images: comparative study using mutual information

Nowadays, the hyperspectral remote sensing imagery HSI becomes an important tool to observe the Earth’s surface, detect the climatic changes and many other applications. The classification of HSI is one of the most challenging tasks due to the large amount of spectral information and the presence of redundant and irrelevant bands. Although great progresses have been made on classification techniques, few studies have been done to provide practical guidelines to determine the appropriate classifier for HSI. In this paper, we investigate the performance of four supervised learning algorithms, namely, Support Vector Machines SVM, Random Forest RF, K-Nearest Neighbors KNN and Linear Discriminant Analysis LDA with different kernels in terms of classification accuracies. The experiments have been performed on three real hyperspectral datasets taken from the NASA’s Airborne Visible/Infrared Imaging Spectrometer Sensor AVIRIS and the Reflective Optics System Imaging Spectrometer ROSIS sensors. The mutual information had been used to reduce the dimensionality of the used datasets for better classification efficiency. The extensive experiments demonstrate that the SVM classifier with RBF kernel and RF produced statistically better results and seems to be respectively the more suitable as supervised classifiers for the hyperspectral remote sensing images.

Noise Removal Based on Tensor Modelling for Hyperspectral Image Classification

With the current state-of-the-art computer aided manufacturing tools, the spatial resolution of hyperspectral sensors is becoming increasingly higher thus making it easy to obtain much more detailed information of the scene captured. However, the improvement of the spatial resolution also brings new challenging problems to address with signal dependent photon noise being one of them. Unlike the signal independent thermal noise, the variance of photon noise is dependent on the signal, therefore many denoising methods developed for the stationary noise cannot be applied directly to the photon noise. To make things worse, both photon and thermal noise coexist in the captured hyperspectral image (HSI), thus making it more difficult to whiten noise. In this paper, we propose a new denoising framework to cope with signal dependent nonwhite noise (SDNW), Pre-estimate—Whitening—Post-estimate (PWP) loop, to reduce both photon and thermal noise in HSI. Previously, we proposed a method based on multidimensional wavelet packet transform and multi-way Wiener filter which performs both white noise and spectral dimensionality reduction, referred to as MWPT-MWF, which was restricted to white noise. We get inspired from this MWPT-MWF to develop a new iterative method for reducing photon and thermal noise. Firstly, the hyperspectral noise parameters estimation (HYNPE) algorithm is used to estimate the noise parameters, the SD noise is converted to an additive white Gaussian noise by pre-whitening procedure and then the whitened HSI is denoised by the proposed method SDNW-MWPT-MWF. As comparative experiments, the Multiple Linear Regression (MLR) based denoising method and tensor-based Multiway Wiener Filter (MWF) are also used in the denoising framework. An HSI captured by Reflective Optics System Imaging Spectrometer (ROSIS) is used in the experiments and the denoising performances are assessed from various aspects: the noise whitening performance, the Signal-to-Noise Ratio (SNR), and the classification performance. The results on the real-world airborne hyperspectral image HYDICE (Hyperspectral Digital Imagery Collection Experiment) are also presented and analyzed. These experiments show that it is worth taking into account noise signal-dependency hypothesis for processing HYDICE and ROSIS HSIs.

Hyperspectral Image Spatial Super-Resolution via 3D Full Convolutional Neural Network

Hyperspectral images are well-known for their fine spectral resolution to discriminate different materials. However, their spatial resolution is relatively low due to the trade-off in imaging sensor technologies, resulting in limitations in their applications. Inspired by recent achievements in convolutional neural network (CNN) based super-resolution (SR) for natural images, a novel three-dimensional full CNN (3D-FCNN) is constructed for spatial SR of hyperspectral images in this paper. Specifically, 3D convolution is used to exploit both the spatial context of neighboring pixels and spectral correlation of neighboring bands, such that spectral distortion when directly applying traditional CNN based SR algorithms to hyperspectral images in band-wise manners is alleviated. Furthermore, a sensor-specific mode is designed for the proposed 3D-FCNN such that none of the samples from the target scene are required for training. Fine-tuning by a small number of training samples from the target scene can further improve the performance of such a sensor-specific method. Extensive experimental results on four benchmark datasets from two well-known hyperspectral sensors, namely hyperspectral digital imagery collection experiment (HYDICE) and reflective optics system imaging spectrometer (ROSIS) sensors, demonstrate that our proposed 3D-FCNN outperforms several existing SR methods by ensuring higher quality both in reconstruction and spectral fidelity.

Learning and Transferring Deep Joint Spectral–Spatial Features for Hyperspectral Classification

Feature extraction is of significance for hyperspectral image (HSI) classification. Compared with conventional hand-crafted feature extraction, deep learning can automatically learn features with discriminative information. However, two issues exist in applying deep learning to HSIs. One issue is how to jointly extract spectral features and spatial features, and the other one is how to train the deep model when training samples are scarce. In this paper, a deep convolutional neural network with two-branch architecture is proposed to extract the joint spectral–spatial features from HSIs. The two branches of the proposed network are devoted to features from the spectral domain as well as the spatial domain. The learned spectral features and spatial features are then concatenated and fed to fully connected layers to extract the joint spectral–spatial features for classification. When the training samples are limited, we investigate the transfer learning to improve the performance. Low and mid-layers of the network are pretrained and transferred from other data sources; only top layers are trained with limited training samples extracted from the target scene. Experiments on Airborne Visible/Infrared Imaging Spectrometer and Reflective Optics System Imaging Spectrometer data demonstrate that the learned deep joint spectral–spatial features are discriminative, and competitive classification results can be achieved when compared with state-of-the-art methods. The experiments also reveal that the transferred features boost the classification performance.

Learning Sensor-Specific Spatial-Spectral Features of Hyperspectral Images via Convolutional Neural Networks

Convolutional neural network (CNN) is well known for its capability of feature learning and has made revolutionary achievements in many applications, such as scene recognition and target detection. In this paper, its capability of feature learning in hyperspectral images is explored by constructing a five-layer CNN for classification (C-CNN). The proposed C-CNN is constructed by including recent advances in deep learning area, such as batch normalization, dropout, and parametric rectified linear unit (PReLU) activation function. In addition, both spatial context and spectral information are elegantly integrated into the C-CNN such that spatial-spectral features are learned for hyperspectral images. A companion feature-learning CNN (FL-CNN) is constructed by extracting fully connected feature layers in this C-CNN. Both supervised and unsupervised modes are designed for the proposed FL-CNN to learn sensor-specific spatial-spectral features. Extensive experimental results on four benchmark data sets from two well-known hyperspectral sensors, namely airborne visible/infrared imaging spectrometer (AVIRIS) and reflective optics system imaging spectrometer (ROSIS) sensors, demonstrate that our proposed C-CNN outperforms the state-of-the-art CNN-based classification methods, and its corresponding FL-CNN is very effective to extract sensor-specific spatial-spectral features for hyperspectral applications under both supervised and unsupervised modes.

Spectral-Spatial Response for Hyperspectral Image Classification

This paper presents a hierarchical deep framework called Spectral-Spatial Response (SSR) to jointly learn spectral and spatial features of Hyperspectral Images (HSIs) by iteratively abstracting neighboringregions. SSRformsadeeparchitectureandisabletolearndiscriminativespectral-spatial features of the input HSI at different scales. It includes several existing spectral-spatial-based methods as special scenarios within a single unified framework. Based on SSR, we further propose the Subspace Learning-based Networks (SLN) as an example of SSR for HSI classification. In SLN, the joint spectral and spatial features are learned using templates simply learned by Marginal Fisher Analysis (MFA) and Principal Component Analysis (PCA). An important contribution to the success of SLN is the exploitation of label information of training samples and the local spatial structure of HSI. Extensive experimental results on four challenging HSI datasets taken from the Airborne Visible-Infrared Imaging Spectrometer (AVIRIS) and Reflective Optics System Imaging Spectrometer (ROSIS) airborne sensors show the implementational simplicity of SLN and verify the superiority of SSR for HSI classification.

Locally adaptive linear mixture model-based super-resolution land-cover mapping based on a structure tensor

ABSTRACTSuper-resolution land-cover mapping (SRM) is a technique for generating land-cover thematic maps with a finer spatial resolution than the input image. Linear mixture model-based SRM (LSRM) is applied directly to a remotely sensed image and is composed of a spatial term that integrates the land-cover spatial pattern prior information, a spectral term that assumes that the spectral signature of each mixed pixel is composed of a weighted linear sum of endmember spectral signatures within that pixel and a balance parameter that defines the weight of the spatial term. The traditional LSRM adopts an isotropic spatial autocorrelation model in the land-cover spatial term for different classes and a fixed balance parameter for the entire image, and ignores the image local properties. The class boundaries are at risk of oversmoothing and may be imprecise, and the homogeneous regions may be unsmoothed and contain speckle-like artefacts in the result. This study proposes a locally adaptive LSRM (LA-LSRM) that integrates image local properties to predict fine spatial resolution pixel labels. The structure tensor is applied to detect the image local information. The LA-LSRM spatial term is locally adaptive and is composed of an anisotropic spatial autocorrelation model in which the spatial autocorrelation orientations of different classes may vary. The LA-LSRM balance parameter is locally adaptive to the different regions of the image. Such parameter obtains a relatively large value when the fine-resolution pixel is located in the homogeneous region to remove speckle-like artefacts and a relatively small value when the fine-resolution pixel is at the class boundary to preserve the edge. The LA-LSRM performance was assessed using a simulated multi-spectral image, an IKONOS multi-spectral image, a hyperspectral image produced by Airborne Visible/Infrared Imaging Spectrometer and a hyperspectral image produced by reflective optics system imaging spectrometer. Results show that the homogeneous regions were smoothed, the boundaries were better preserved and the overall accuracies were increased by LA-LSRM compared with traditional LSRM in all experiments.

Semisupervised Sparse Manifold Discriminative Analysis for Feature Extraction of Hyperspectral Images

The graph embedding (GE) framework is very useful to extract the discriminative features of hyperspectral images (HSIs) for classification. However, a major challenge of GE is how to select a proper neighborhood size for graph construction. To overcome this drawback, a new semisupervised discriminative learning algorithm, which is called the semisupervised sparse manifold discriminative analysis (S 3 MDA) method, was proposed by using manifold-based sparse representation (MSR) and GE. The proposed algorithm utilizes MSR to obtain the sparse coefficients of labeled and unlabeled samples. Then, it constructs a within-class graph and a between-class graph using the sparse coefficients of labeled samples, as well as an unsupervised graph with the sparse coefficients of unlabeled samples. Finally, it uses these graphs to obtain a projection matrix for feature extraction (FE) of HSI in a low-dimensional space. The S 3 MDA method not only inherits the merits of MSR to reveal the sparse manifold properties of data but also enhances interclass separability and intraclass compactness to improve the discriminating power for classification. Extensive experiments on two real HSI data sets obtained with a reflective optics system imaging spectrometer and an airborne visible/infrared imaging spectrometer show that the proposed algorithm is significantly superior to other state-of-the-art FE methods in terms of classification accuracy.

Hyperspectral image preprocessing with bilateral filter for improving the classification accuracy of support vector machines

Bilateral filter (BF) theory is applied to integrate spatial contextual information into the spectral domain for improving the accuracy of the support vector machine (SVM) classifier. The proposed classification framework is a two-stage process. First, an edge-preserved smoothing is carried out on a hyperspectral image (HSI). Then, the SVM multiclass classifier is applied on the smoothed HSI. One of the advantages of the BF-based implementation is that it considers the spatial as well as spectral closeness for smoothing the HSI. Therefore, the proposed method provides better smoothing in the homogeneous region and preserves the image details, which in turn improves the separability between the classes. The performance of the proposed method is tested using benchmark HSIs obtained from the airborne-visible-infrared-imaging-spectrometer (AVIRIS) and the reflective-optics-system-imaging-spectrometer (ROSIS) sensors. Experimental results demonstrate the effectiveness of the edge-preserved filtering in the classification of the HSI. Average accuracies (with 10% training samples) of the proposed classification framework are 99.04%, 98.11%, and 96.42% for AVIRIS–Salinas, ROSIS–Pavia University, and AVIRIS–Indian Pines images, respectively. Since the proposed method follows a combination of BF and the SVM formulations, it will be quite simple and practical to implement in real applications.

Spatial Regularized Local Manifold Learning for Classification of Hyperspectral Images

A spatial regularized local manifold learning (SR_LML) approach is investigated for dimensionality reduction (DR) of hyperspectral images, where the spatial regularizer constrains the spatial neighbors with high spectral similarity to have similar embedding coordinates. SR_LML requires the processed data to contain good spatial relations, but the requirement may not be satisfied. We solve the problem by dividing the image into small tiles and applying the SR_LML in each of them. In a tile, each pixel is spatially related to some other pixels, and thus good spatial relations of data can be guaranteed and the effect of the spatial regularizer can be maximized. Moreover, an alignment method is applied to merge all the resulted manifolds in different tiles to a globally consistent manifold. The SR_LML performed in small tiles in conjunction with alignment is denoted as SR_LML_TA; it is able to best use of the spatial relations of pixels in the image, and is suitable for large-scale remote sensing scenes. Experiments with airborne visible/infrared imaging spectrometer (AVIRIS), reflective optics system imaging spectrometer (ROSIS), and NSF-funded Center for Airborne Laser Mapping (NCALM) hyperspectral images demonstrated that the manifold coordinates of SR_LML_TA can provide good separation of classes that are difficult to distinguish. The classification results using 1NN classifier indicated SR_LML_TA significantly outperformed the spectral LML, and obtained higher accuracies than several spatial and spectral LML methods.

Spectral Similarity Assessment Based on a Spectrum Reflectance-Absorption Index and Simplified Curve Patterns for Hyperspectral Remote Sensing.

Hyperspectral images possess properties such as rich spectral information, narrow bandwidth, and large numbers of bands. Finding effective methods to retrieve land features from an image by using similarity assessment indices with specific spectral characteristics is an important research question. This paper reports a novel hyperspectral image similarity assessment index based on spectral curve patterns and a reflection-absorption index. First, some spectral reflection-absorption features are extracted to restrict the subsequent curve simplification. Then, the improved Douglas-Peucker algorithm is employed to simplify all spectral curves without setting the thresholds. Finally, the simplified curves with the feature points are matched, and the similarities among the spectral curves are calculated using the matched points. The Airborne Visible Infrared Imaging Spectrometer (AVIRIS) and Reflective Optics System Imaging Spectrometer (ROSIS) hyperspectral image datasets are then selected to test the effect of the proposed index. The practical experiments indicate that the proposed index can achieve higher precision and fewer points than the traditional spectral information divergence and spectral angle match.

Hyperspectral Image Classification Using Support Vector Machine in Ridgelet Domain

Classification of diverse classes available in the hyperspectral imagery is one of the recent research issues in remote sensing field. This work proposes a new technique that classifies hyperspectral images on ridgelet transformed domain. For hyperspectral image ridgelet coefficients are calculated. Co-occurrence features such as energy, entropy and contrast are extracted for the obtained ridgelet co-efficients and extracted features exhibit inter-pixel relationship. As stated in many literatures, the support vector machines (SVM) along with radial basis function kernel is used for classifying the classes which are non-linearly distributed in the hyperspectral scene. One-against-all binary hierarchical tree strategy is adopted while classifying images by SVM. Hyperspectral image captured over the North Western Indiana by airborne visible infra red imaging sensor (AVIRIS) and a subset of Pavia University data captured by reflective optics system imaging spectrometer (ROSIS) have been chosen for the experiment. The proposed algorithm produced the accuracies of 92.33 and 94.08 % for AVIRIS and ROSIS data sets respectively.

Dimensionality Reduction of Hyperspectral Images With Sparse Discriminant Embedding

Sparse manifold learning has drawn more and more attentions recently, and sparsity preserving projections (SPP) has been proposed, which inherits the advantages of sparse reconstruction. However, SPP only focuses on the sparse structure, ignoring the discriminant information of labeled samples. In this paper, we proposed a new supervised dimensionality reduction method, which is called sparse discriminant embedding (SDE), for hyperspectral image (HSI) classification. SDE utilizes the merits of both intermanifold structure and sparsity property. It not only preserves the sparse reconstructive relations through $\ell_{1} $ -graph but also enhances the intermanifold separability of data, and the discriminating power of SDE is further improved than SPP. Experiments on two real HSIs collected by the Airborne Visible/Infrared Imaging Spectrometer and Reflective Optics System Imaging Spectrometer sensors are performed to demonstrate the effectiveness of the proposed SDE method.

On combining multiscale deep learning features for the classification of hyperspectral remote sensing imagery

In recent years, satellite imagery has greatly improved in both spatial and spectral resolution. One of the major unsolved problems in highly developed remote sensing imagery is the manual selection and combination of appropriate features according to spectral and spatial properties. Deep learning framework can learn global and robust features from the training data set automatically, and it has achieved state-of-the-art classification accuracies over different image classification tasks. In this study, a technique is proposed which attempts to classify hyperspectral imagery by incorporating deep learning features. Firstly, deep learning features are extracted by multiscale convolutional auto-encoder. Then, based on the learned deep learning features, a logistic regression classifier is trained for classification. Finally, parameters of deep learning framework are analysed and the potential development is introduced. Experiments are conducted on the well-known Pavia data set which is acquired by the reflective optics system imaging spectrometer sensor. It is found that the deep learning-based method provides a more accurate classification result than the traditional ones.