Until now, interpretation of aerial photographs is a standard tool for monitoring land cover change where fine spatial
resolutions are required and this task is expensive and time-consuming. Though, from a spaceborne perspective, the
VHR satellite data are, since 1999, capable to meet the mapping and monitoring needs of municipal and regional
planning agencies. Indeed, these data from the sensors Ikonos, QuickBird, OrbView-3, and in near future, the Pléiades-
HR French sensors, have spatial resolution lower than 5 m in multispectral mode and lower than 1 m in panchromatic
mode. These new sources of data combine the advantages of satellite data (synoptic view, digital format suitable for
computer processing, quantitative land surface information at large spatial coverage and at frequent temporal intervals
...) with the very high spatial resolution.
In spite of these advantages, the use of VHR satellite data involves some problems in traditional per-pixel classification
often used in change detection techniques. There are still two occurring classification problems that can strongly
deteriorate the result of a per-pixel classification of the VHR satellite data: spectral variability and poor spectral
resolution. A solution to overcome these problems is the region-based classification that can be integrated in the
common change detection techniques. The segmentation, before classification, produces regions which are more
homogeneous in themselves than with nearby regions and represent discrete objects or areas in the image. Each image
region then becomes a unit analysis and makes it possible to avoid much of the structural clutter. Image segmentation
provides a logical transition from the units of pixels to larger units in maps more relevant to detect the changes in these.
In this context, this research project suggests to use region based classification of VHR satellite data in the change
detection processe for updates of vector database.