Hyperspectral Nonlinear Unmixing by Using Plug-and-Play Prior for Abundance Maps

Wang, Zhicheng; Zhuang, Lina; Gao, Lianru; Marinoni, Andrea; Zhang, Bing; Ng, Michael K.

doi:10.3390/rs12244117

Cited by 12 publications

(5 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By selecting different pattern switch matrices, the denoising operator can be used to penalize the reconstructed hyperspectral image or estimated abundances. The work of [29] proposes a nonlinear unmixing method with prior information provided by denoisers. However, the denoisers used in these methods are traditional denoising methods or deep denoisers trained on grayscale or RGB images, which may not be optimal for hyperspectral images.…”

Section: A Regularization Designmentioning

confidence: 99%

Hyperspectral Unmixing Powered by Deep Image Priors and Denoising Regularization

Zhao

Chen

2022

IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

Spectral unmixing has been extensively studied with a variety of methods and used in many applications. Recently, data-driven techniques with deep learning methods have obtained great attention to spectral unmixing for its superior learning ability to automatically learn the structure information. In particular, autoencoder based architectures are elaborately designed to solve blind unmixing and model complex nonlinear mixtures. Nevertheless, these methods perform unmixing task as blackboxes and lack of interpretability. On the other hand, conventional unmixing methods carefully design the regularizer to add explicit information, in which algorithms such as plug-and-play (PnP) strategies utilize off-the-shelf denoisers to plug powerful priors. In this paper, we propose a generic unmixing framework to integrate the autoencoder network with regularization by denoising (RED), named AE-RED. More specially, we decompose the unmixing optimized problem into two subproblems. The first one is solved using deep autoencoders to implicitly regularize the estimates and model the mixture mechanism. The second one leverages the denoiser to bring in the explicit information. In this way, both the characteristics of the deep autoencoder based unmixing methods and priors provided by denoisers are merged into our well-designed framework to enhance the unmixing performance. Experiment results on both synthetic and real data sets show the superiority of our proposed framework compared with state-of-the-art unmixing approaches.

show abstract

Section: A Regularization Designmentioning

confidence: 99%

Hyperspectral Unmixing Powered by Deep Image Priors and Denoising Regularization

Zhao

Chen

2022

IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium

View full text Add to dashboard Cite

show abstract

“…Hyperspectral imaging technology can produce images in hundreds of bands. Each pixel is a continuous spectral curve and can be used to describe the subtle spectral characteristics of different objects [1][2][3][4]. As an important part of hyperspectral image (HSI) processing, hyperspectral anomaly detection (HAD) can detect anomaly targets in the scene without using any prior spectral information, which is different from hyperspectral target detection [5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Frequency‐to‐spectrum mapping GAN for semisupervised hyperspectral anomaly detection

Wang

Gao

et al. 2023

CAAI Trans on Intel Tech

Self Cite

View full text Add to dashboard Cite

Most unsupervised or semisupervised hyperspectral anomaly detection (HAD) methods train background reconstruction models in the original spectral domain. However, due to the noise and spatial resolution limitations, there may be a lack of discrimination between backgrounds and anomalies. This makes it easy for the autoencoder to capture the low‐level features shared between the two, thereby increasing the difficulty of separating anomalies from the backgrounds, which runs counter to the purpose of HAD. To this end, the authors map the original spectrums to the fractional Fourier domain (FrFD) and reformulate it as a mapping task in which restoration errors are employed to distinguish background and anomaly. This study proposes a novel frequency‐to‐spectrum mapping generative adversarial network for HAD. Specifically, the depth separable features of backgrounds and anomalies are enhanced in the FrFD. Due to the semisupervised approach, FTSGAN needs to learn the embedded features of the backgrounds, thus mapping and restoring them from the FrFD to the original spectral domain. This strategy effectively prevents the model from focussing on the numerical equivalence of input and output, and restricts the ability of FTSGAN to restore anomalies. The comparison and analysis of the experiments verify that the proposed method is competitive.

show abstract

“…The existing spectral decomposition models include linear unmixing (LU) [6] and non-linear unmixing (NLU) [7][8][9]. Compared with NLU, LU has been widely used in the HU field because of its simple and efficient process implementation and clear physical significance [10].…”

Section: Introductionmentioning

confidence: 99%

Robust linear unmixing with enhanced constraint of classification for hyperspectral remote sensing imagery

Chi

Shang

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Although hyperspectral data, especially spaceborne images, are rich in spectral information, their spatial resolution is usually low due to the limitation of sensor design and other factors. Therefore, for the application of hyperspectral images, unmixing technology is a key processing technology, such as linear mixing model and its derived algorithms have made a certain progress. However, a real scene often contains both pure and mixed pixels. The existing methods usually ignore the consideration and analysis of this situation in the process of model design and simulation experiment. In this context, this paper proposes a robust linear unmixing model with the enhanced constraint of classification for hyperspectral image. In general, it designs a framework combining unmixing and classification. In the task for real scene data, endmembers are extracted first, and then the hard classification term constructed after the expansion of endmembers (training samples) based on similarity is introduced to provide the sparsity constraint of the overall model, so as to realize relatively complete adjustment and effective image unmixing under complex conditions. Considering the scene with different distributions, the simulation experiment designs several groups of data tests, including different proportions of pure and mixing pixels. The unmixing results of three simulated datasets and two real datasets show that the unmixing results of this method are better than those of the other six comparison methods. This model improves the accuracy of unmixing and realizes effective unmixing.

show abstract

Hyperspectral Nonlinear Unmixing by Using Plug-and-Play Prior for Abundance Maps

Cited by 12 publications

References 52 publications

Hyperspectral Unmixing Powered by Deep Image Priors and Denoising Regularization

Hyperspectral Unmixing Powered by Deep Image Priors and Denoising Regularization

Frequency‐to‐spectrum mapping GAN for semisupervised hyperspectral anomaly detection

Robust linear unmixing with enhanced constraint of classification for hyperspectral remote sensing imagery

Contact Info

Product

Resources

About