Hyperspectral Image Classification via Multiple-Feature-Based Adaptive Sparse Representation

Fang, Leyuan; Wang, Cheng; Li, Shutao; Benediktsson, Jón Atli

doi:10.1109/tim.2017.2664480

Cited by 159 publications

(58 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [24], edge-preserving filtering was considered as a postprocessing technique to optimize the probabilistic results of an SVM. In [25]- [27], the spatial information within a neighboring region was incorporated into a sparse representation model. These sparse representation methods are based on the observation that hyperspectral pixels can usually be represented by a linear combination of a few common pixels from the same class.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning for Hyperspectral Image Classification: An Overview

Li¹,

Song²,

Fang³

et al. 2019

IEEE Trans. Geosci. Remote Sensing

Self Cite

1,331

452

View full text Add to dashboard Cite

Hyperspectral image (HSI) classification has become a hot topic in the field of remote sensing. In general, the complex characteristics of hyperspectral data make the accurate classification of such data challenging for traditional machine learning methods. In addition, hyperspectral imaging often deals with an inherently nonlinear relation between the captured spectral information and the corresponding materials. In recent years, deep learning has been recognized as a powerful feature-extraction tool to effectively address nonlinear problems and widely used in a number of image processing tasks. Motivated by those successful applications, deep learning has also been introduced to classify HSIs and demonstrated good performance. This survey paper presents a systematic review of deep learning-based HSI classification literatures and compares several strategies for this topic. Specifically, we first summarize the main challenges of HSI classification which cannot be effectively overcome by traditional machine learning methods, and also introduce the advantages of deep learning to handle these problems. Then, we build a framework which divides the corresponding works into spectralfeature networks, spatial-feature networks, and spectral-spatialfeature networks to systematically review the recent achievements in deep learning-based HSI classification. In addition, considering the fact that available training samples in the remote sensing field are usually very limited and training deep networks require a large number of samples, we include some strategies to improve classification performance, which can provide some guidelines for future studies on this topic. Finally, several representative deep learning-based classification methods are conducted on real HSIs in our experiments.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Learning for Hyperspectral Image Classification: An Overview

Li¹,

Song²,

Fang³

et al. 2019

IEEE Trans. Geosci. Remote Sensing

Self Cite

1,331

452

View full text Add to dashboard Cite

show abstract

“…proposed via the integration of contextual information from the neighborhood pixels. Better performance and promising results are shown by the proposed framework even when the quantity of initially labeled samples are trivial [62].…”

Section: E Small Number Of Labelled Samplesmentioning

confidence: 99%

Unfolding the Restrained Encountered in Hyperspectral Images

Kriti¹,

Garg²

2019

IJRTE

View full text Add to dashboard Cite

The content of the natural scenes needs to be interpreted which is the primary concern in computer vision. In the advancement of the systems focusing on the intelligent image understanding, the most powerful key is the degree to which meaningful information is extracted by the computer. Moreover with this advancement in the field of image processing, precise and huge information capturing images are desired. The hyperspectral images find its place in such fields of applications. For a single scene, the hyperspectral images (HSI) are composed of hundreds of channels of spectral data. For different materials, with the availability of detailed spectral information, hundreds of contracted bands are collected by hyperspectral sensors. However, with the dimensional complexity, its impact varies from field to field. We reiterate our main focus in this article on providing the various challenges existing relating to HSI and a case study of the current solutions provided for each. A clear depiction of the current issues and approaches in the field of compression as well as some general issues are also discussed towards the end section.Index Terms: hyperspectral imaging (HSI), hyperspectral sensors, multispectral imaging.

show abstract

“…ISOMAP characterizes the data distribution by geodesic distances instead of Euclidean distances, it seeks a lower-dimensional embedding which maintains geodesic distances between all points [19]. However, due to their nonlinear characteristic, they suffer from the problem of out-of-sample and cannot process the unknown samples [20][21][22]. To address this issue, many linear manifold learning methods were designed to obtain explicit feature mappings, which can map unknown samples into low-dimensional space [23,24].…”

Section: Introductionmentioning

confidence: 99%

Spatial-Spectral Multiple Manifold Discriminant Analysis for Dimensionality Reduction of Hyperspectral Imagery

et al. 2019

View full text Add to dashboard Cite

Hyperspectral images (HSI) possess abundant spectral bands and rich spatial information, which can be utilized to discriminate different types of land cover. However, the high dimensional characteristics of spatial-spectral information commonly cause the Hughes phenomena. Traditional feature learning methods can reduce the dimensionality of HSI data and preserve the useful intrinsic information but they ignore the multi-manifold structure in hyperspectral image. In this paper, a novel dimensionality reduction (DR) method called spatial-spectral multiple manifold discriminant analysis (SSMMDA) was proposed for HSI classification. At first, several subsets are obtained from HSI data according to the prior label information. Then, a spectral-domain intramanifold graph is constructed for each submanifold to preserve the local neighborhood structure, a spatial-domain intramanifold scatter matrix and a spatial-domain intermanifold scatter matrix are constructed for each sub-manifold to characterize the within-manifold compactness and the between-manifold separability, respectively. Finally, a spatial-spectral combined objective function is designed for each submanifold to obtain an optimal projection and the discriminative features on different submanifolds are fused to improve the classification performance of HSI data. SSMMDA can explore spatial-spectral combined information and reveal the intrinsic multi-manifold structure in HSI. Experiments on three public HSI data sets demonstrate that the proposed SSMMDA method can achieve better classification accuracies in comparison with many state-of-the-art methods.

show abstract

Hyperspectral Image Classification via Multiple-Feature-Based Adaptive Sparse Representation

Cited by 159 publications

References 47 publications

Deep Learning for Hyperspectral Image Classification: An Overview

Deep Learning for Hyperspectral Image Classification: An Overview

Unfolding the Restrained Encountered in Hyperspectral Images

Spatial-Spectral Multiple Manifold Discriminant Analysis for Dimensionality Reduction of Hyperspectral Imagery

Contact Info

Product

Resources

About