SegSALSA-STR: A convex formulation to supervised hyperspectral image segmentation using hidden fields and structure tensor regularization

TL;DR

This paper introduces a convex, supervised hyperspectral image segmentation method called SegSALSA-STR, which leverages hidden fields and structure tensor regularization to improve efficiency and avoid NP-hard optimization issues.

Contribution

It extends the SegSALSA algorithm by incorporating a structure tensor prior, resulting in a convex, time-efficient, and parallelizable segmentation approach for hyperspectral images.

Findings

Convex formulation avoids NP-hard segmentation problems.

Algorithm is time-efficient and highly parallelizable.

Validated on real hyperspectral images with promising results.

Abstract

We present a supervised hyperspectral image segmentation algorithm based on a convex formulation of a marginal maximum a posteriori segmentation with hidden fields and structure tensor regularization: Segmentation via the Constraint Split Augmented Lagrangian Shrinkage by Structure Tensor Regularization (SegSALSA-STR). This formulation avoids the generally discrete nature of segmentation problems and the inherent NP-hardness of the integer optimization associated. We extend the Segmentation via the Constraint Split Augmented Lagrangian Shrinkage (SegSALSA) algorithm by generalizing the vectorial total variation prior using a structure tensor prior constructed from a patch-based Jacobian. The resulting algorithm is convex, time-efficient and highly parallelizable. This shows the potential of combining hidden fields with convex optimization through the inclusion of different regularizers. The SegSALSA-STR algorithm is validated in the segmentation of real hyperspectral images.