Community Research and Development Information Service - CORDIS


The process of updating existing land-cover databases is an issue of great concern for keeping existing and often expensive information valuable. Often, this problem is one of integrating appropriately multi-temporal data sets that are completely different in nature, as existing vector data has to be updated with image data. In this article, a methodology is proposed for the updating of land-cover databases by using texture information derived from very high-resolution panchromatic space-borne imagery. At a given scale the homogeneity of texture derived from newly acquired imagery is measured within the polygons to update by means of a knowledge-based segmentation approach. In a successive step, the new region contours are compared with the existing polygons. This basically transforms the change detection problem into one of image segmentation. Experimental results for the updating of urban-rural land-cover maps by IRS-1C panchromatic imagery indicate the usefulness of the direction taken.

Additional information

Authors: SMITS P C, JRC Ispra (IT);ANNONI A, JRC Ispra (IT)
Bibliographic Reference: Article: IEEE Transactions on Geoscience and Remote Sensing (1998)
Record Number: 199811173 / Last updated on: 1998-10-09
Original language: en
Available languages: en