New method improves accuracy of hyperspectral image material detection
Interpretable Hyperspectral Unmixing Framework with Fixed Endmember Prior and Structured Residual Refinement
Computer Vision and Pattern Recognition
Summary
Hyperspectral images show many colors for each pixel, helping identify materials, but these pixels often mix several substances, making it hard to tell them apart. The authors introduce a step-by-step method that treats the known materials as fixed and better separates the mixture by adding a correction step for errors caused by lighting or sensor problems. Their approach improves the accuracy of separating materials without messing up the estimated amounts, making the results easier to understand. Tests on standard datasets showed much better image reconstruction and clearer recognition of materials.
What this means in practice
- •For remote sensing analysts: Produce more accurate material maps from satellite or aerial hyperspectral images under varying illumination and sensor conditions.
- •For environmental monitoring teams: Improve detection of natural materials and boundaries in hyperspectral data for better ecosystem assessment.
Authors
Ziyi Guan, Jianping Zhang, Qian Liu
Abstract
Hyperspectral unmixing decomposes mixed pixels into material endmembers and their abundances from contiguous spectral observations. In modular sensing pipelines, endmembers are often first identified and then treated as fixed during abundance estimation. When this fixed endmember prior is inaccurate, spatially structured mismatch arising from illumination changes, sensor artifacts, or material boundaries may be incorrectly captured by the abundance variables, leading to unstable decompositions. This study presents an interpretable stage-wise hyperspectral unmixing framework (I-HyperSU) under fixed endmember priors, which is explicitly decomposed into a fixed endmember matrix $\mathbf{A}$, an abundance block $\mathbf{X}$, and a structural residual refinement block $\mathbf{S}$. The X-block estimates abundances using FISTA with nonnegativity and sparsity enhancement, and a soft penalty that approximately enforces sum-to-one constraints. The S-block jointly applies low-rank SVD structural regularization and a lightweight deep image prior (DIP) to refine structured residuals. This staged design makes the interaction between abundance and residual components transparent and interpretable. Experiments on Samson, Urban, and Jasper Ridge datasets demonstrate that, under fixed and imperfect endmember priors, soft abundance relaxation consistently outperforms hard simplex projection. Under the default N-FINDR endmember prior, the proposed framework reduces the joint reconstruction error by 61.7\%--69.5\% compared with a fixed-$\mathbf{A}$ UCLS baseline, while keeping the abundance RMSE nearly unchanged, indicating that the residual refinement branch accounts for structured model mismatch without degrading the abundance estimates. For example, on Urban, the reconstruction SAM decreases from $5.99^\circ$ for the X-only model to $1.92^\circ$ for the full model.