Spatio-temporal prior shape constraint for level-set segmentation


   

Thimothée Bailloeul (LIAMA/ENSEEIHT)

   

Véronique Prinet (CASIA)

   

Bruno Serra (Alcatel Aliena Space)

   

Philippe Marthon (ENSEEIHT)


Abstract

This research investiguates change analysis between a digital map of buildings and more recent high resolution optical remote sensing data. The key idea is to use the specific geometrical information derived from the buildings symbolized in the map in order to ease their recognition in a panchromatic satellite image. This prior knowledge is embedded in active contours models as a shape constraint. The fine map-to-image matching achieved by the active contours increases the consistency between the map and the image, which attempts to solve the issue of exogenous variabilities between these two representations; it therefore makes the subsequent change detection more reliable.

Related publications

Partners

         
Paper
Timothée's PhD thesis
Presentation slides
PDF