Project

Kazuki Naganuma and Shunsuke Ono

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.

• 再構成画像への正則化を用いることによる高強度ノイズへのロバスト性の向上

• ストライプノイズを含めた複数のノイズを陽にモデル化し、混合ノイズを除去しながらミクセル分解

• 制約付き凸最適化による、パラメータ調整の簡略化

• 最適化アルゴリズムのステップサイズに対する自動決定法の導入で、実験的な調整を省略

[1] M.-D. Iordache, J. M. Bioucas-Dias, and A. Plaza, “Collaborative sparse regression for hyperspectral unmixing,” IEEE Trans. Geosci. Remote  Sens., vol. 52, no. 1, pp. 341–354, 2014.

[2] H. K. Aggarwal and A. Majumdar, “Hyperspectral unmixing in the presence of mixed noise using joint-sparsity and total variation,” IEEE J. Sel.  Top. Appl. Earth. Obs. Remote Sens., vol. 9, no. 9, pp. 4257–4266, 2016.

[3] J. Wang, T. Huang, J. Huang, H. Dou, L. Deng, and X. Zhao, “Row-sparsity spectral unmixing via total variation,” IEEE J. Sel. Top. Appl. Earth. Obs. Remote Sens., vol. 12, no. 12, pp. 5009–5022, 2019.

[4] X. Shen, H. Liu, X. Zhang, K. Qin, and X. Zhou, “Superpixel-guided local sparsity prior for hyperspectral sparse regression unmixing,” IEEE Geosci. Remote Sens. Lett., vol. 19, pp. 1–5, 2022, art no. 6015105.

[5] B. Rasti, B. Koirala, P. Scheunders, and P. Ghamisi, “UnDIP: Hyperspectral unmixing using deep image prior,” IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–15, 2022, art no. 5504615.

[6] d B. Zhang, “Endmember-guided unmixing network (EGU-Net): A general deep learning framework for self-supervised hyperspectral unmixing,” IEEE Trans. Neural Netw. Learn. Syst., vol. 33, no. 11, pp. 6518–6531, Nov. 2022.

[7] C. Deng, Y. Chen, S. Zhang, F. Li, P. Lai, D. Su, M. Hu, and S. Wang, “Robust dual spatial weighted sparse unmixing for remotely sensed hyperspectral imagery,” Remote Sens., vol. 15, no. 16, 2023.

[8] L. Wu, J. Huang, and M.-S. Guo, “Multidimensional low-rank representation for sparse hyperspectral unmixing,” IEEE Geosci. Remote Sens. Lett., vol. 20, pp. 1–5, Mar. 2023, art no. 5502805.

@misc{naganuma2023robust,

      title={Robust Constrained Hyperspectral Unmixing Using Reconstructed-Image Regularization}, 

      author={Kazuki Naganuma and Yuki Nagamatsu and Shunsuke Ono},

      year={2023},

      eprint={2302.08247},

      archivePrefix={arXiv},

      primaryClass={eess.IV}

}

• arXiv

• MATLAB code

• GitHub