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

Filipe Condessa, Jose Bioucas-DIas, Jelena Kovacevic

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper 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 [1] by generalizing the vectorial total variation prior using a structure tensor prior constructed from a patch-based Jacobian [2]. 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.

Original languageEnglish (US)
Title of host publication2015 7th Workshop on Hyperspectral Image and Signal Processing
Subtitle of host publicationEvolution in Remote Sensing, WHISPERS 2015
PublisherIEEE Computer Society
ISBN (Electronic)9781467390156
DOIs
StatePublished - Jul 2 2015
Event7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2015 - Tokyo, Japan
Duration: Jun 2 2015Jun 5 2015

Publication series

NameWorkshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing
Volume2015-June
ISSN (Print)2158-6276

Other

Other7th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2015
CountryJapan
CityTokyo
Period6/2/156/5/15

Keywords

  • Constrained Split Augmented Lagrangian Shrinkage Algorithm (SALSA)
  • Image segmentation
  • hidden fields
  • structure tensor regularization

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint Dive into the research topics of 'SegSALSA-STR: A convex formulation to supervised hyperspectral image segmentation using hidden fields and structure tensor regularization'. Together they form a unique fingerprint.

Cite this