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.
In the framework of the European CAP (Common Agricultural Policy), the European Commission imposes on member states to prevent irregularities, and recommends the control with remote sensing (CwRS) of the declared crops and declared area of crop fields. In the framework of remote sensing procedure, the European Commission, by the way of his Joint Research Centre, advises the use of very high spatial resolution (VHR) satellite data. These data are extraordinary from the point of view of the spatial resolution but the use of these kinds of data involves some problems in the traditional per-pixel classification like the salt and pepper effect and the poor spectral resolution of the VHR data. The region-based classification could solve these problems and allows the use of other features on top of spectral features in the classification process. This study present the potential of the VHR data region-based classification to the classification of the agricultural and rural land cover in the framework of the remote sensing control of the European Union CAP.
Since 1999, very high spatial resolution satellite data (IKONOS, QuickBird, OrbView_3) represent the surface of the earth with more details. However, these data don't provide necessarily better land cover/use classification. These incongruous results of earlier studies were attributed to the increase of the internal variability within the homogenous land cover unit and the weakness of spectral resolution. To overcome these problems, a region based procedure can be used. The image segmentation before the classification is successful at removing much of the structural clutter and allows an easy use of spatial information for classification. This information, on top of spectral information, can be the surface, the perimeter, the compactness (area/perimeter2), the degree and kind of texture. In this study, a feature selection method is used to show which features are useful for which classes and the use of these features to improve the land cover/use classification of very high spatial resolution satellite image. The features selection is preceded by an analysis of visual interpretation parameters useful for the identification of each class of the legend, in order to guide the choice of the features whose combinations can be numerous.
Since 1999, very high spatial resolution data represent the surface of the earth with more details. However, information extraction by computer-assisted classification techniques proves to be very complex owing to the internal variability increase in land-cover units and to the weakness of spectral resolution. The increase in variability decreases the statistical separability of land-cover classes in the spectral space. Per pixel multispectral classification techniques are then insufficient for an extraction of complex categories and spectrally heterogeneous land-cover, like urban areas. Per region classification was proposed as an alternative approach. The first step of this approach is the segmentation. A large variety of segmentation algorithms were developed these last 20 years and a comparison of their implementation on very high spatial resolution images is necessary. For this study, four algorithms from the two main groups of segmentation algorithms (boundary-based and region-based algorithms) were selected. In order to compare the algorithms, an evaluation of each algorithm was carried out with empirical discrepancy evaluation methods. This evaluation is carried out with a visual segmentation of IKONOS panchromatic images.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.