A Data Dependent Multiscale Model for Hyperspectral Unmixing With Spectral Variability

Ricardo Augusto Borsoi, Tales Imbiriba, José Carlos Moreira Bermudez

Abstract

Spectral variability in hyperspectral images can result from factors including environmental, illumination, atmospheric and temporal changes. Its occurrence may lead to the propagation of significant estimation errors in the unmixing process. To address this issue, extended linear mixing models have been proposed which lead to large scale nonsmooth ill-posed inverse problems. Furthermore, the regularization strategies used to obtain meaningful results have introduced interdependencies among abundance solutions that further increase the complexity of the resulting optimization problem. In this paper we present a novel data dependent multiscale model for hyperspectral unmixing accounting for spectral variability. The new method incorporates spatial contextual information to the abundances in extended linear mixing models by using a multiscale transform based on superpixels. The proposed method results in a fast algorithm that solves the abundance estimation problem only once in each scale during each iteration. Simulation results using synthetic and real images compare the performances, both in accuracy and execution time, of the proposed algorithm and other state-of-the-art solutions.

Introduction

In hyperspectral imaging, each pixel typically contains a mixture of materials, such as soil, grass, or water. Hyperspectral Unmixing (HU) is the task of identifying these pure materials (endmembers) and their proportions (abundances) in every pixel. The classic Linear Mixing Model (LMM) assumes that a material's spectral signature is constant throughout the scene. However, in real-world scenarios, factors like changing illumination, topography, and atmospheric effects cause spectral variability. While newer models like the Extended Linear Mixing Model (ELMM) account for this, they often result in "ill-posed" inverse problems that are computationally grueling to solve, especially when trying to ensure that neighboring pixels have similar material proportions through spatial regularization.

Methodology

The proposed Multiscale Unmixing Algorithm Accounting for Spectral Variability (MUA-SV) introduces a multiscale spatial mixture model to address these challenges. Its core innovation lies in a data-dependent superpixel transform:

  1. Superpixel Decomposition: The algorithm uses the SLIC (Simple Linear Iterative Clustering) method to group similar pixels into "superpixels." This creates a transformation that respects the natural boundaries in the image.
  2. Multiscale Representation: The image is decomposed into two scales: a coarse scale representing averages within superpixels and a detail scale representing pixel-level variations.
  3. Separable Optimization: By assuming that residuals are uncorrelated across scales and that endmember signatures vary smoothly in space, the authors decouple the complex interdependencies between pixels.
  4. Fast Solver: This decoupling allows the abundance estimation to be solved independently for each pixel in both domains, turning a massive global optimization problem into many small, parallelizable ones.
Original hyperspectral image and its superpixel decomposition used for multiscale unmixing.

Experimental Setup

The researchers evaluated MUA-SV against three synthetic and two real-world datasets:

  • Synthetic (DC1, DC2, DC3): Designed to test the algorithm against different types of variability, including illumination changes based on the Hapke model and hilly terrain.
  • Houston Data Set: A 152×108 pixel subset of an urban hyperspectral image.
  • Cuprite Data Set: A 250×191 pixel subregion of the well-known mineralogical site in Nevada.

Results and Discussion

MUA-SV demonstrated a clear "win-win" in performance across both accuracy and efficiency:

  • Accuracy: It consistently achieved lower Mean Squared Error (MSE) for abundances compared to ELMM and PLMM across all noise levels (20dB to 40dB).
  • Speed: On the large Cuprite dataset, MUA-SV was approximately 5.5 times faster than ELMM and 80 times faster than PLMM.
  • Visual Quality: Qualitative results on the Houston and Cuprite images showed that MUA-SV produced cleaner, more homogeneous abundance maps that better delineated different materials without blurring sharp edges.

The efficiency of MUA-SV stems from the realization that because spectral variability is usually spatially smooth, it can be solved primarily at a coarse scale and then refined, rather than struggling with high-dimensional matrices at every single pixel from the start.

Conclusion

While MUA-SV offers significant improvements, it relies on the assumption that endmember signatures do not change abruptly between adjacent pixels. This might fail in extremely heterogeneous scenes. Additionally, performance is sensitive to the initial superpixel segmentation; overly large superpixels might group semantically different materials. Future work may extend this multiscale framework to more complex non-linear mixing models or other hyperspectral data processing tasks.

Summary updated

Abstract

Spectral variability in hyperspectral images can result from factors including environmental, illumination, atmospheric and temporal changes. Its occurrence may lead to the propagation of significant estimation errors in the unmixing process. To address this issue, extended linear mixing models have been proposed which lead to large scale nonsmooth ill-posed inverse problems. Furthermore, the regularization strategies used to obtain meaningful results have introduced interdependencies among abundance solutions that further increase the complexity of the resulting optimization problem. In this paper we present a novel data dependent multiscale model for hyperspectral unmixing accounting for spectral variability. The new method incorporates spatial contextual information to the abundances in extended linear mixing models by using a multiscale transform based on superpixels. The proposed method results in a fast algorithm that solves the abundance estimation problem only once in each scale during each iteration. Simulation results using synthetic and real images compare the performances, both in accuracy and execution time, of the proposed algorithm and other state-of-the-art solutions.
BibTeX
@article{borsoi2020data,
  author = {Ricardo Augusto Borsoi and Tales Imbiriba and José Carlos Moreira Bermudez},
  title = {{A Data Dependent Multiscale Model for Hyperspectral Unmixing With Spectral Variability}},
  journal = {IEEE Trans. Image Process.},
  year = {2020},
  url = {https://openreview.net/forum?id=z-nAeFhydQ},
}
Figure