Deep Learning in Hyperspectral Unmixing: A Review

Bhatt, Jignesh S.; Joshi, Manjunath V.

doi:10.1109/igarss39084.2020.9324546

Cited by 65 publications

(32 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MSE between the reconstructed and original spectrum is defined as follows: (25) Using the chain rule again, the gradients of MSE with respect to , , and can be computed as…”

Section: Loss Functionmentioning

confidence: 99%

“…Recently, with advances in machine learning and the emergence of deep learning techniques, some networks [25], [26] based on simplified physical theory have been adopted to address the issues posed by blind unmixing of hyperspectral data. As described in [27], [28], spectral-spatial features were obtained from a continuous spectral sequence using a convolutional neural network (CNN) in the process of hyperspectral unmixing.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Residual Dense Autoencoder Network for Nonlinear Hyperspectral Unmixing

Yang

Chen

Wang

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Hyperspectral unmixing is a popular research topic in hyperspectral processing, aiming at obtaining the ground features contained in the mixed pixels and their proportion. Recently, nonlinear mixing models have received particular attention in hyperspectral decomposition since the linear mixing model cannot suitably apply in the situation that exists in multiple scattering. In this study, we constructed a residual dense autoencoder network (RDAE) for nonlinear hyperspectral unmixing in multiple scattering scenarios. First, an encoder was built based on the residual dense network (RDN) and attention layer. The RDN is employed to characterize multi-scale representations, which are further transformed with the attention layer to estimate the abundance maps. Second, we designed a decoder based on the unfolding of a generalized bilinear model to extract endmembers and estimate their second-order scattering interactions. Comparative experiments between the RDAE and six other state-of-the-art methods under synthetic and real hyperspectral datasets demonstrate that the proposed method achieved a better performance in terms of endmember extraction and abundance estimation.

show abstract

“…The MSE between the reconstructed and original spectrum is defined as follows: (25) Using the chain rule again, the gradients of MSE with respect to , , and can be computed as…”

Section: Loss Functionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Residual Dense Autoencoder Network for Nonlinear Hyperspectral Unmixing

Yang

Chen

Wang

et al. 2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…There have also been reviews published on DL in remote sensing in general and for hyperspectral imaging, such as [28,29]. The only review paper focusing on DL for spectral unmixing is [30]. The work [2] is a good review of interpretable hyperspectral artificial intelligence.…”

Section: Introductionmentioning

confidence: 99%

Blind Hyperspectral Unmixing Using Autoencoders: A Critical Comparison

Palsson

Sveinsson

Ulfarsson

2022

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

“…Hence, several materials may be present within each pixel, and quantifying the fractional abundance of a given material in an HSI pixel helps us to understand their actual mixture better. Given high intra-class variability and inter-class similarities [ 28 ], developing effective algorithms for this task, referred to as hyperspectral unmixing [ 29 ], is another important area in the field. Note that gathering ground-truth data for automated hyperspectral unmixing is affected by the very same challenges as in the case of segmentation tasks (unmixing is commonly considered to be a more challenging problem).…”

Section: Introductionmentioning

confidence: 99%

Recent Advances in Multi- and Hyperspectral Image Analysis

Nalepa

2021

Sensors

View full text Add to dashboard Cite

Current advancements in sensor technology bring new possibilities in multi- and hyperspectral imaging. Real-life use cases which can benefit from such imagery span across various domains, including precision agriculture, chemistry, biology, medicine, land cover applications, management of natural resources, detecting natural disasters, and more. To extract value from such highly dimensional data capturing up to hundreds of spectral bands in the electromagnetic spectrum, researchers have been developing a range of image processing and machine learning analysis pipelines to process these kind of data as efficiently as possible. To this end, multi- or hyperspectral analysis has bloomed and has become an exciting research area which can enable the faster adoption of this technology in practice, also when such algorithms are deployed in hardware-constrained and extreme execution environments; e.g., on-board imaging satellites.

show abstract

Deep Learning in Hyperspectral Unmixing: A Review

Cited by 65 publications

References 20 publications

Residual Dense Autoencoder Network for Nonlinear Hyperspectral Unmixing

Residual Dense Autoencoder Network for Nonlinear Hyperspectral Unmixing

Blind Hyperspectral Unmixing Using Autoencoders: A Critical Comparison

Recent Advances in Multi- and Hyperspectral Image Analysis

Contact Info

Product

Resources

About