Uncertainties in segmentation and their visualisation

Abstract

This thesis focuses on uncertainties in remotely sensed image segmentation and their visualisation. The first part describes a visualisation tool, allowing interaction with the parameters of a fuzzy classification algorithm by visually adjusting fuzzy membership functions of classes in a 3D feature space plot. Its purpose is to improve insight into fuzzy classification of remotely sensed imagery and related uncertainty. Additionally, alpha-shapes are used to visualise irregular shaped class clusters.

The second part of the thesis describes segmentation techniques for identification of objects and quantification of their uncertainties. The Local Binary Pattern (LBP) operator is used to model texture. A multivariate extension of the standard univariate LBP operator is proposed to describe texture in multiple bands. Texture-based image segmentation, provides good results yielding valuable information about object uncertainty at transition zones.

Visualisation methods described in the first part and segmentation techniques described in the second part are combined and extended to visualise object uncertainty. An object is visualised in 3D feature space and in geographic space based on a user-defined uncertainty threshold. Isosurfaces provide a visualisation technique for fast interaction facilitating visualisation of the relation between uncertainty in the spatial extent of objects and their thematic uncertainty.