Alexandre Carleer

Assessment of Very High Spatial Resolution Satellite Image Segmentations

Since 1999, very high spatial resolution satellite data represent the surface of the Earth with more detail. However, information extraction by per pixel multispectral classification techniques proves to be very complex owing to the internal variability increase in land-cover units and to the weakness of spectral resolution. Image segmentation before classification was proposed as an alternative approach, but a large variety of segmentation algorithms were developed during the last 20 years, and a comparison of their implementation on very high spatial resolution images is necessary. In this study, four algorithms from the two main groups of segmentation algorithms (boundarybased and region-based) were evaluated and compared. 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. The results show that the choice of parameters is very important and has a great influence on the segmentation results. The selected boundary-based algorithms are sensitive to the noise or texture. Better results are obtained with regionbased algorithms, but a problem with the transition zones between the contrasted objects can be present.

Exploitation of Very High Resolution Satellite Data for Tree Species Identification

With the emergence of very high spatial resolution satellite images, the spatial resolution gap which existed between satellite images and aerial photographs has decreased. A study of the potential of these images for tree species in “monoculture stands” identification was conducted. Two Ikonos images were acquired, one in June 2000 and the other in October 2000, for an 11- by 11-km area covering the Sonian Forest in the southeastern part of the Brussels-Capital region (Belgium). The two images were orthorectified using a digital elevation model and 1256 geodetic control points. The identification of the tree species was carried out utilizing a supervised maximum-likelihood classification on a pixel-by-pixel basis. Classifications were performed on the orthorectified data, NDVI transformed data, and principal components imagery. In order to decrease the intraclass variance, a mean filter was applied to all the spectral bands and neo-channels used in the classification process. Training and validation areas were selected and digitized using detailed geographical databases of the tree species. The selection of the relevant bands and neo-channels was carried out by successive addition of information in order to improve the classification results. Seven different tree species of one to two different age classes were identified with an overall accuracy of 86 percent. The seven identified tree species or species groups are Oaks (Quercus sp.), Beech (Fagus sylvatica L.), Purple Beech (Fagus sylvatica purpurea), Douglas Fir (Pseudotsuga menziesii (Mirb.) Franco), Scots Pine (Pinus sylvestris L.), Corsican Pine (Pinus nigra Arn. subsp. laricio (Poir.) Maire var. corsican), and Larch (Larix decidua Mill.).

Urban land cover multi-level region-based classification of VHR data by selecting relevant features

The limited spatial resolution of satellite images used to be a problem for the adequate definition of the urban environment. This problem was expected to be solved with the availability of very high spatial resolution satellite images (IKONOS, QuickBird, OrbView‐3). However, these space‐borne sensors are limited to four multi‐spectral bands and may have specific limitations as far as detailed urban area mapping is concerned. It is therefore essential to combine spectral information with other information, such as the features used in visual interpretation (e.g. the degree and kind of texture and the shape) transposed to digital analysis. In this study, a feature selection method is used to show which features are useful for particular land‐cover classes. These features are used to improve the land‐cover classification of very high spatial resolution satellite images of urban areas. The useful features are compared with a visual feature selection. The features are calculated after segmentation into regions that become analysis units and ease the feature calculation.

Comparison of very high spatial resolution satellite image segmentations

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.

Change detection for updates of vector database through region-based classification of VHR satellite data

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.

VHR image region-based classification potential in the framework of the control with remote sensing of the European CAP

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.