Universality of wavelet-based non-homogeneous hidden Markov chain model features for hyperspectral signatures

Feng, Siwei; Duarte, Marco F.; Parente, M.

doi:10.1109/cvprw.2015.7301379

Cited by 6 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Some recent research lines try to relieve the ill-posed nature of the unmixing problem by taking advantage of so-called semantic representations [13], [14], that is, modeling the structural patterns of the spectrum domain.…”

Section: B Current Limitations and Trendsmentioning

confidence: 99%

Hyperspectral Unmixing Based on Dual-Depth Sparse Probabilistic Latent Semantic Analysis

Fernández-Beltrán

Plaza

et al. 2018

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

This paper presents a novel approach for spectral unmixing of remotely sensed hyperspectral data. It exploits probabilistic latent topics in order to take advantage of the semantics pervading the latent topic space when identifying spectral signatures and estimating fractional abundances from hyperspectral images. Despite the contrasted potential of topic models to uncover image semantics, they have been merely used in hyperspectral unmixing as a straightforward data decomposition process. This limits their actual capabilities to provide semantic representations of spectral data. The proposed model, called Dual-dEpth probabilistic Semantic Analysis (DEpLSA), makes use of two different levels of topics to exploit the semantic patterns extracted from the initial spectral space in order to relieve the ill-posed nature of the unmixing problem. In other words, DEpLSA defines a first level of deep-topics to capture the semantic representations of the spectra, and a second level of restricted-topics to estimate endmembers and abundances over this semantic space. An experimental comparison in conducted using two standard topic models, and seven state-of-the-art unmixing methods available in the literature. Our experiments, conducted using four different hyperspectral images, reveal that the proposed approach is able to provide competitive advantages over available unmixing approaches.

show abstract

Section: B Current Limitations and Trendsmentioning

confidence: 99%

Hyperspectral Unmixing Based on Dual-Depth Sparse Probabilistic Latent Semantic Analysis

Fernández-Beltrán

Plaza

et al. 2018

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…In this section, we briefly describe the semantic representation of hyperspectral signals proposed in [32], [33], [35]. This representation is automatically generated by statistical analysis on the wavelet coefficients of the reflectance signals.…”

Section: Semantic Representation Of Hyperspectral Datamentioning

confidence: 99%

“…More recently, Feng et al [35] proposed a k-state mixture of Gaussian (k-MOG) NHMC model where the distribution of each wavelet coefficient is modeled as a k Gaussian mixture model, with each Gaussian having mean zero and different variance. In this model, we also consider that semantic information is encoded in a binary fashion, {Large (L), Small (S)}, although this is not encoded directly into the hidden states.…”

Section: B Statistical Modeling On Wavelet Coefficientsmentioning

confidence: 99%

“…We briefly review the k-MOG NHMC model proposed in [35]. Each wavelet coefficient w s,l is assumed to be generated from one of the k states denoted by S s,l ∈ {0, 1, .…”

Section: B Statistical Modeling On Wavelet Coefficientsmentioning

confidence: 99%

“…where n s is the number of scales. The training of the model is performed via an expectation maximization algorithm that maximizes the expected log likelihood on the probabilistic distribution of the latent variables and states given a training dataset of spectra [35]. After the model is trained, to obtain k-MOG NHMC feature labels, all hidden states associated with the (L) feature label are merged into one state and a Viterbi algorithm [45], [46] is used to estimate the most possible sequence of feature labels [35].…”

Section: B Statistical Modeling On Wavelet Coefficientsmentioning

confidence: 99%

See 2 more Smart Citations

Semisupervised Endmember Identification in Nonlinear Spectral Mixtures via Semantic Representation

Itoh

Feng

Duarte

et al. 2017

IEEE Trans. Geosci. Remote Sensing

Self Cite

View full text Add to dashboard Cite

This paper proposes a new hyperspectral unmixing method for nonlinearly mixed hyperspectral data using a semantic representation in a semi-supervised fashion, assuming the availability of a spectral reference library. Existing semisupervised unmixing algorithms select members from an endmember library that are present at each of the pixels; most such methods assume a linear mixing model. However, those methods will fail in the presence of nonlinear mixing among the observed spectra. To address this issue, we develop an endmember selection method using a recently proposed semantic spectral representation obtained via non-homogeneous hidden Markov chain (NHMC) model for a wavelet transform of the spectra. The semantic representation can encode spectrally discriminative features for any observed spectrum and, therefore, our proposed method can perform endmember selection without any assumption on the mixing model. Experimental results show that in the presence of sufficiently nonlinear mixing our proposed method outperforms dictionary-based sparse unmixing approaches based on linear models.

show abstract

Wavelet-Based Semantic Feature Representation for Hyperspectral Signature Discrimination

Feng

2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

Hyperspectral signature discrimination is a quantitative analysis approach for hyperspectral imagery which performs detection and classification of the constituent materials at the pixel level in the scene. However, the substantial volume of data in hyperspectral images poses challenges for practitioners in terms of computation and storage, making the management of acquired hyperspectral data difficult. One alternative to directly operating on raw data is to perform classification using extracted features from hyperspectral signatures, such as energy or shape information. Therefore, there is a need to design features that capture scientifically meaningful cues of the materials under study from hyperspectral signatures. The wavelet transform is widely recognized for its ability to highlight signal discontinuities, making it suitable for representing spectral fluctuations with semantic value. By appropriately modeling wavelet coefficients, it becomes possible to distinguish between fluctuations that have discriminatory value and those that do not. In this paper, we describe a technique that applies non-homogeneous hidden Markov chain (NHMC) models to hyperspectral signature discrimination. The basic idea is to use statistical models (such as NHMC) to characterize wavelet coefficients which capture the spectrum semantics (i.e., structural information) at multiple levels. Experimental results show that the approach based on NHMC models can outperform existing approaches relevant in classification tasks.INDEX TERMS Hyperspectral signature discrimination, non-homogeneous hidden Markov chain, semantic feature representation.

show abstract

Universality of wavelet-based non-homogeneous hidden Markov chain model features for hyperspectral signatures

Cited by 6 publications

References 19 publications

Hyperspectral Unmixing Based on Dual-Depth Sparse Probabilistic Latent Semantic Analysis

Hyperspectral Unmixing Based on Dual-Depth Sparse Probabilistic Latent Semantic Analysis

Semisupervised Endmember Identification in Nonlinear Spectral Mixtures via Semantic Representation

Wavelet-Based Semantic Feature Representation for Hyperspectral Signature Discrimination

Contact Info

Product

Resources

About