A General Destriping Framework for Remote Sensing Images Using Flatness Constraint

Naganuma, Kazuki; Ono, Shunsuke

doi:10.1109/tgrs.2022.3153995

Cited by 15 publications

(7 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fourth term controls the intensity of stripe noise L and the fourth constraint captures the vertical flatness property by imposing zero to the vertical gradient of L. The term and constraint accurately characterize stripe noise [47]. Therefore, our method can estimate abundance maps from HS images contaminated by mixed noise including dense stripe noise.…”

Section: Methodsmentioning

confidence: 99%

“…Regarding the second limitation in dealing with stripe noise, existing unmixing methods mainly deal with Gaussian noise and sparse noise. However, in addition to these noises, actual HS images are often contaminated with stripe noise, mainly due to external disturbances and calibration errors [45]- [47]. Since stripe noise is not Gaussian and is often not sparse [48], it cannot be handled by existing methods, leading to performance degradation in unmixing.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Toward Robust Hyperspectral Unmixing: Mixed Noise Modeling and Image-Domain Regularization

Naganuma,

Ono

2024

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

Self Cite

View full text Add to dashboard Cite

Hyperspectral (HS) unmixing is the process of decomposing an HS image into material-specific spectra (endmembers) and their spatial distributions (abundance maps). Existing unmixing methods have two limitations with respect to noise robustness. First, if the input HS image is highly noisy, even if the balance between sparse and piecewise-smooth regularizations for abundance maps is carefully adjusted, noise may remain in the estimated abundance maps or undesirable artifacts may appear. Second, existing methods do not explicitly account for the effects of stripe noise, which is common in HS measurements, in their formulations, resulting in significant degradation of unmixing performance when such noise is present in the input HS image. To overcome these limitations, we propose a new robust hyperspectral unmixing method based on constrained convex optimization. Our method employs, in addition to the two regularizations for the abundance maps, regularizations for the HS image reconstructed by mixing the estimated abundance maps and endmembers. This strategy makes the unmixing process much more robust in highly-noisy scenarios, under the assumption that the abundance maps used to reconstruct the HS image with desirable spatio-spectral structure are also expected to have desirable properties. Furthermore, our method is designed to accommodate a wider variety of noise including stripe noise. To solve the formulated optimization problem, we develop an efficient algorithm based on a preconditioned primal-dual splitting method, which can automatically determine appropriate stepsizes based on the problem structure. Experiments on synthetic and real HS images demonstrate the advantages of our method over existing methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Toward Robust Hyperspectral Unmixing: Mixed Noise Modeling and Image-Domain Regularization

Naganuma,

Ono

2024

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…to data fidelity based on the two observation models and our two assumptions, are imposed as hard constraints. Such a formulation using constraints instead of adding terms to the objective function has the advantage of simplifying parameter setting [37]- [42]: the appropriate parameters in the constraints do not depend on each other and can be determined independently for each constraint.…”

Section: B Contributions and Paper Organizationmentioning

confidence: 99%

“…The parameters η h and η l depend on the sparse noise intensity on the HR image and the LR images, respectively, i.e., r h and r l . Using constraints instead of adding terms to the objective function in this way simplifies the parameter setting [37]- [42]: we can determine the appropriate parameters for each constraint independently because they are decoupled. The detailed setting of these parameters is discussed in Sec.…”

Section: B Problem Formulationmentioning

confidence: 99%

Robust Spatiotemporal Fusion of Satellite Images: A Constrained Convex Optimization Approach

Isono,

Naganuma,

Ono

2024

IEEE Trans. Geosci. Remote Sensing

Self Cite

View full text Add to dashboard Cite

This paper proposes a novel spatiotemporal (ST) fusion framework for satellite images, named Robust Optimizationbased Spatiotemporal Fusion (ROSTF). ST fusion is a promising approach to resolve a trade-off between the temporal and spatial resolution of satellite images. Although many ST fusion methods have been proposed, most of them are not designed to explicitly account for noise in observed images, despite the inevitable influence of noise caused by the measurement equipment and environment. Our ROSTF addresses this challenge by formulating noise removal and ST fusion as a unified optimization problem. First, we define observation models for satellite images that may be contaminated with random noise, outliers, and/or missing values. Next, we introduce certain assumptions that naturally hold between the observed images and the target highresolution image. Then, based on these models and assumptions, we formulate the fusion problem as a constrained optimization problem and develop an efficient algorithm based on a preconditioned primal-dual splitting method for solving the problem. The performance of ROSTF was verified using simulated and real data. The results show that ROSTF performs comparably to several state-of-the-art ST fusion methods in noiseless cases and outperforms them in noisy cases.

show abstract

“…Specifically, the third term adjusts the sparsity of stripe noise, while the first constraint, called the flatness constraint, models the constant intensity. The advantages of such characterizations for stripe noise are described in [42]. • The second constraint serves as a data-fidelity to the given HS image, where the upper bound ε of the Frobenius norm is adjusted based on the intensity of Gaussian noise.…”

Section: A Problem Formulationmentioning

confidence: 99%

Robust Hyperspectral Anomaly Detection with Simultaneous Mixed Noise Removal via Constrained Convex Optimization

Sato

Ono

2023

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

A General Destriping Framework for Remote Sensing Images Using Flatness Constraint

Cited by 15 publications

References 64 publications

Toward Robust Hyperspectral Unmixing: Mixed Noise Modeling and Image-Domain Regularization

Toward Robust Hyperspectral Unmixing: Mixed Noise Modeling and Image-Domain Regularization

Robust Spatiotemporal Fusion of Satellite Images: A Constrained Convex Optimization Approach

Robust Hyperspectral Anomaly Detection with Simultaneous Mixed Noise Removal via Constrained Convex Optimization

Contact Info

Product

Resources

About