Band-Specified Virtual Dimensionality for Band Selection: An Orthogonal Subspace Projection Approach

With the advancement in technology, hyperspectral images have potential applications in the field of remote sensing due to their high spectral resolution. Despite the hyperspectral image providing abundant information, its analysis suffers from the problem of high dimensionality. Hence, Dimensionality Reduction (DR) is an essential task in all hyperspectral image analysis. Band Selection, which is one of the DR techniques, is still a challenging issue even though many algorithms have been developed. To provide remedy for this issue, this paper explores a novel approach for band selection using K-means clustering on statistical feature in hyperspectral images. The proposed method of clustering based band selection for DR is simple and accurate. A reliable estimate of number of bands to be selected is provided by Virtual Dimensionality (VD). Informative bands preserving maximum information are selected based on the statistical feature, the variance using K-means Clustering technique. Further, our proposed work involves the utilization of the effectiveness of Simplex Growing Algorithm (SGA) on endmember extraction in association with clustering based band selection. Using Fully Constrained Least Squares (FCLS) method, abundance fraction is estimated based on endmember signatures, which are derived using Endmember Extraction Algorithm (EEA). The proposed work is investigated and compared with that of N-FINDR and Vertex Component Analysis (VCA) algorithms. The performance of the proposed algorithm is evaluated using Root Mean Square Error (RMSE), Spectral Angle Distance (SAD) and computation time. Experimental results show that the proposed clustering based band selection with SGA endmember extraction algorithm reduces the average SAD by 8 to 10 % and the average RMSE by nearly 1 %, compared to that of N-FINDR and VCA algorithms. In terms of computation time, the proposed band selection based DR with SGA algorithm is seven times faster than conventional transform based DR with SGA algorithm.

Band selection is a great challenging task in the classification of hyperspectral remotely sensed images HSI. This is resulting from its high spectral resolution, the many class outputs and the limited number of training samples. For this purpose, this paper introduces a new filter approach for dimension reduction and classification of hyperspectral images using information theoretic (normalized mutual information) and support vector machines SVM. This method consists to select a minimal subset of the most informative and relevant bands from the input datasets for better classification efficiency. We applied our proposed algorithm on two well-known benchmark datasets gathered by the NASA's AVIRIS sensor over Indiana and Salinas valley in USA. The experimental results were assessed based on different evaluation metrics widely used in this area. The comparison with the state of the art methods proves that our method could produce good performance with reduced number of selected bands in a good timing. Keywords: Dimension reduction, Hyperspectral images, Band selection, Normalized mutual information, Classification, Support vector machines

One of the primary goals of imaging spectrometry in Earth remote sensing applications is to determine identities and abundances of surface materials. In a recent study, an orthogonal subspace projection (OSP) was proposed for image classification. However, it was developed for an a priori linear spectral mixture model which did not take advantage of a posteriori knowledge of observations. In this paper, an a posterior least squares orthogonal subspace projection (LSOSP) derived from OSP is presented on the basis of an a posteriori model so that the abundances of signatures can be estimated through observations rather than assumed to be known as in the a priori model. In order to evaluate the OSP and LSOSP approaches, a Neyman-Pearson detection theory is developed where a receiver operating characteristic (ROC) curve is used for performance analysis. In particular, a locally optimal Neyman-Pearson's detector is also designed for the case where the global abundance is very small with energy close to zero a case to which both LSOSP and OSP cannot be applied. It is shown through computer simulations that the presented LSOSP approach significantly improves the performance of OSP.

Band clustering has been widely used for hyperspectral band selection (BS). However, selecting an appropriate band to represent a band cluster is a key issue. Density peak clustering (DPC) provides an effective means for this purpose, referred to as DPC-based BS (DPC-BS). It uses two indicators, cluster density and cluster distance, to rank all bands for BS. This paper reinterprets cluster density and cluster distance as band local density (BLD) and band distance (BD) and also introduces a new concept called band prominence value (BPV) as a third indicator. Combining BLD and BD with BPV derives new band prioritization criteria for BS, which can extend the currently used DPC-BS to a new DPC-BS method referred to as band density prominence clustering (BDPC). By taking advantage of the three key indicators of BDPC, i.e., cut-off band distance bc, k nearest neighboring-band local density, and BPV, two versions of BDPC can be derived called bc-BDPC and k-BDPC, both of which are quite different from existing DPC-based BS methods in three aspects. One is that the parameter bc of bc-BDPC and the parameter k of k-BDPC can be automatically determined by the number of clusters and virtual dimensionality (VD), respectively. Another is that instead of using Euclidean distance, a spectral discrimination measure is used to calculate BD as well as inter-band correlation. The most important and significant aspect is a novel idea that combines BPV with BLD and BD to derive new band prioritization criteria for BS. Extensive experiments demonstrate that BDPC generally performs better than DPC-BS as well as many current state-of-the art BS methods.

An orthogonal subspace projection (OSP) method using linear mixture modeling was recently explored in hyperspectral image classification and has shown promise in signature detection, discrimination, and classification. In this paper, the OSP is revisited and extended by three unconstrained least squares subspace projection approaches, called signature space OSP, target signature space OSP, and oblique subspace projection, where the abundances of spectral signatures are not known a priori but need to be estimated, a situation to which the OSP cannot be directly applied. The proposed three subspace projection methods can be used not only to estimate signature abundance, but also to classify a target signature at subpixel scale so as to achieve subpixel detection. As a result, they can be viewed as a posteriori OSP as opposed to OSP, which can be thought of as a priori OSP. In order to evaluate these three approaches, their associated least squares estimation errors are cast as a signal detection problem ill the framework of the Neyman-Pearson detection theory so that the effectiveness of their generated classifiers can be measured by receiver operating characteristics (ROC) analysis. All results are demonstrated by computer simulations and Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) data.

Estimating the number of spectral signal sources, denoted by p, in hyperspectral imagery is very challenging due to the fact that many unknown material substances can be uncovered by very high spectral resolution hyperspectral sensors. This paper investigates a recent approach, called maximum orthogonal complement algorithm (MOCA), for this purpose. The MOCA was originally developed by Kuybeda et al. for estimating the rank of a rare vector space in a highdimensional noisy data space. Interestingly, the idea of the MOCA is essentially derived from the automatic target generation process (ATGP) developed by Ren and Chang. By appropriately interpreting the MOCA in context of the ATGP a potentially useful technique, called maximum orthogonal subspace projection (MOSP) can be further developed where determining a stopping rule for the ATGP turns out to be equivalent to estimating the rank of a rare vector space by the MOCA and the number of targets determined by the stopping rule for the ATGP to generate is the desired value of the parameter p. Furthermore, a Neyman-Pearson detector version of MOCA, NPD-MOCA can be also derived by the MOSP as opposed to the MOCA considered as a Bayes detector. Surprisingly, the MOCA-NPD has very similar design rationale to that of a technique referred to as Harsanyi-Farrand-Chang method that was developed to estimate the virtual dimensionality (VD) which is defined as the p.

In this work, we propose a new semisupervised active learning approach for hyperspectral image classification. The proposed method aims at improving machine generalization by using pseudolabeled samples, both confident and informative, which are automatically and actively selected, via semisupervised learning. The learning is performed under two assumptions: a local one for the labeling via a superpixel-based constraint dedicated to the spatial homogeneity and adaptivity into the pseudolabels, and a global one modeling the data density by a multinomial logistic regressor with a Markov random field regularizer. Furthermore, we propose a density-peak-based augmentation strategy for pseudolabels, due to the fact that the samples without manual labels in their superpixel neighborhoods are out of reach for the automatic sampling. Three real hyperspectral datasets were used in our experiments to evaluate the effectiveness of the proposed superpixel-based semisupervised learning approach. The obtained results indicate that the proposed approach can greatly improve the potential for semisupervised learning in hyperspectral image classification.

Band selection (BS), which selects a subset of original bands that contain the most useful information about objects, is an important technique to reduce the dimensionality of hyperspectral data. Dimensionality reduction before hyperspectral data classification can reduce redundancy information and even improve classification accuracy. We propose BS algorithms based on an ant colony optimization (ACO) in conjunction with objective functions such as the supervised Jeffries–Matusita distance and unsupervised simplex volume. Moreover, we propose to use a small number of selected pixels for BS in order to reduce computational cost in the unsupervised BS. In this experiment, the proposed algorithms were applied to three airborne hyperspectral datasets including urban scenes, and the results demonstrated that the ACO-based BS could find a better combination of bands than the widely used sequential forward search-based BS. It was acceptable to use a few pixels to achieve comparable BS performance with our method.

Hyperspectral remote sensing sensors have the ability to capture a wide range of spectrum of ground objects with hundreds to thousands of bands. The obtained hyperspectral images contain more detailed spectral information than conventional panchromatic or color images. However, redundant and noisy data could also be introduced into the images and may impair further processing of the data. Removing the redundancy and noisy bands becomes one of the most important preprocessing steps of hyperspectral imaging. As a feature selection method, an attention mechanism has been successfully used in computer vision and natural language processing to enable algorithms to concentrate on the most significant data. In this article, we propose a band attention network for hyperspectral image classification. This network can automatically learn to attend to the desired band set that maximizes the classification accuracy. With careful design, the band attention framework can undertake both band weighting and band selection tasks. When working in the band weighting mode, the proposed band attention framework can learn a band weighting vector that models the relationship between all the bands. For band selection, our network can be adapted as two different types of band selection networks that select the significant bands and discard the useless bands. In both tasks, the attention and classification can be learned end to end. The experimental results prove the effectiveness and advantages of the proposed work.

A novel dependency definition exploiting boundary samples in rough set theory for hyperspectral band selection

Different crops, as well as the same crop at different growth stages, display distinct spectral and spatial characteristics in hyperspectral images (HSIs) due to variations in their chemical composition and structural features. However, the narrow bandwidth and closely spaced spectral channels of HSIs result in significant data redundancy, posing challenges to crop identification and classification. Therefore, the dimensionality reduction in HSIs is crucial. Band selection as a widely used method for reducing dimensionality has been extensively applied in research on crop identification and mapping. In this paper, a crop superpixel-based affinity propagation (CS-AP) band selection method is proposed for crop identification and mapping in agriculture using HSIs. The approach begins by gathering crop superpixels; then, a spectral band selection criterion is developed by analyzing the variations in the spectral and spatial characteristics of crop superpixels. Finally, crop identification bands are determined through an efficient clustering approach, AP. Two typical agricultural hyperspectral data sets, the Salinas Valley data set and the Indian Pines data set, are selected for validation, each containing 16 crop classes, respectively. The experimental results show that the proposed CS-AP method achieves a mapping accuracy of 92.4% for the Salinas Valley data set and 88.6% for the Indian Pines data set. When compared to using all bands, two unsupervised band selection techniques, and three semi-supervised band selection techniques, the proposed method outperforms others with an improvement of 3.1% and 4.3% for the Salinas Valley and Indian Pines data sets, respectively. Indicate that the proposed CS-AP method achieves superior mapping accuracy by selecting fewer bands with greater crop identification capability compared to the other band selection methods. This research’s significant results demonstrate the potential of this approach in precision agriculture, offering a more cost-effective and timely solution for large-scale crop mapping and monitoring in the future.

Recently, there have been continuous advancements in hyperspectral image classification (HSIC) approaches based on deep learning mechanisms. Nonetheless, information redundancy, high complexity and ineffective descriptions remain primary obstacles to present HSIC networks. In order to overcome these issues, an optimization-enabled deep convolutional neural network (Deep CNN) for HSIC is proposed in this work. Here, band selection, feature extraction, as well as classification are important tasks in processing these images. The band selection is performed by utilizing the double exponential smoothing-artificial flora optimization (DES-AFO) algorithm, which is the combination of double exponential smoothing (DES) and artificial flora optimization (AFO) for HSIC. There is a requirement for extracting competent features from hyperspectral imaging (HSI) to enhance the classifier’s accuracy. Here, the feature extraction is done by empirical wavelet transform and a convolutional neural network (CNN). As the next process, HSIC takes place using the Deep CNN, and it is trained by DES-AFO. The wide experimental outcomes on HSI show that the proposed mechanism has noteworthy benefits estimated with the conventional mechanisms concerning accuracy and TPR. Here, analysis states that the proposed mechanism obtained better accuracy and TPR values of 0.930, as well as 0.965.

Constrained energy minimization (CEM) has shown effective in hyperspectral target detection. It linearly constrains a desired target signature while minimizing interfering effects caused by other unknown signatures. This paper explores this idea for band selection and develops a new approach to band selection, referred to as constrained band selection (CBS) for hyperspectral imagery. It interprets a band image as a desired target signature vector while considering other band images as unknown signature vectors. As a result, the proposed CBS using the concept of the CEM to linearly constrain a band image, while also minimizing band correlation or dependence provided by other band images, is referred to as CEM-CBS. Four different criteria referred to as Band Correlation Minimization (BCM), Band Correlation Constraint (BCC), Band Dependence Constraint (BDC), and Band Dependence Minimization (BDM) are derived for CEM-CBS.. Since dimensionality resulting from conversion of a band image to a vector may be huge, the CEM-CBS is further reinterpreted as linearly constrained minimum variance (LCMV)-based CBS by constraining a band image as a matrix where the same four criteria, BCM, BCC, BDC, and BDM, can be also used for LCMV-CBS. In order to determine the number of bands required to select p, a recently developed concept, called virtual dimensionality, is used to estimate the p. Once the p is determined, a set of p desired bands can be selected by the CEM/LCMV-CBS. Finally, experiments are conducted to substantiate the proposed CEM/LCMV-CBS four criteria, BCM, BCC, BDC, and BDM, in comparison with variance-based band selection, information divergence-based band selection, and uniform band selection.

Band selection for hyperspectral images is an effective technique to mitigate the curse of dimensionality. A variety of band selection methods have been suggested in the past. This paper presents a novel band prioritization based on impurity function (IF) for the band selection of hyperspectral images. The proposed IF band selection (IFBS) is incorporated with particle swarm optimization (PSO) band selection which has been developed to effectively group highly correlated bands of hyperspectral images into high corrected modules. It uses a particle swarm optimization scheme, which is a well-known method to solve the optimization problems, to develop an effective feature extraction algorithm for hyperspectral imagery. After PSO method is applied to the band reduction of hyperspectral images, the proposed IFBS is applied to enhance the efficiency of band selection. The propose method is evaluated by MODIS/ASTER airborne simulator (MASTER) for land cover classification during the Pacrim II campaign. The performance of IFBS is validated by the supervised k-nearest neighbor (KNN) classifier. Experimental results demonstrate that the proposed IFBS approach is an effective method for dimensionality reduction and feature extraction. Compared to other band selection methods, IFBS can effectively select the most significant bands for the image classification of hyperspectral images.

Hyperspectral remote sensing offers a powerful tool in many different application contexts. The imbalance between the high dimensionality of the data and the limited availability of training samples calls for the need to perform dimensionality reduction in practice. Among traditional dimensionality reduction techniques, feature extraction is one of the most widely used approaches due to its flexibility to transform the original spectral information into a subspace. In turn, band selection is important when the application requires preserving the original spectral information (especially the physically meaningful information) for the interpretation of the hyperspectral scene. In the case of hyperspectral image classification, both techniques need to discard most of the original features/bands in order to perform the classification using a feature set with much lower dimensionality. However, the discriminative information that allows a classifier to provide good performance is usually classdependent and the relevant information may live in weak features/bands that are usually discarded or lost through subspace transformation or band selection. As a result, in practice, it is challenging to use either feature extraction or band selection for classification purposes. Relevant lines of attack to address this problem have focused on multiple feature selection aiming at a suitable fusion of diverse features in order to provide relevant information to the classifier. In this paper, we present a new dimensionality reduction technique, called multiple criteria-based spectral partitioning, which is embedded in an ensemble learning framework to perform advanced hyperspectral image classification. Driven by the use of a multiple band priority criteria that is derived from classic band selection techniques, we obtain multiple spectral partitions from the original hyperspectral data that correspond to several band subgroups with much lower spectral dimensionality as compared with the original band set. An ensemble learning technique is then used to fuse the information from multiple features, taking advantage of the relevant information provided by each classifier. Our experimental results with two real hyperspectral images, collected by the reflective optics system imaging spectrometer (ROSIS) over the University of Pavia in Italy and the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) over the Salinas scene, reveal that our presented method, driven by multiple band priority criteria, is able to obtain better classification results compared with classic band selection techniques. This paper also discusses several possibilities for computationally efficient implementation of the proposed technique using various high-performance computing architectures.