In this paper we demonstrate how the interaction between innovative methods in the field of computer vision and methods for multi-spectral image classification can help in extracting detailed land-cover / land-use information from Very High Resolution (VHR) satellite imagery. We introduce the novel concept of "geometric activity images", which we define as images encoding the strength of the relationship between a pixel and surrounding features detected through dedicated computer vision methods. These geometric activity images are used as alternatives to more traditional texture images that better describe the geometry of man-made structures and that can be included as additional information in a non-parametric supervised classification framework. We present a number of findings resulting from the integration of geometric activity images and multi-spectral bands in an artificial neural network classification. The geometric activity images we use result from the use of a ridge detector for straight line detection, calculated for different window sizes and for all multi-spectral bands and band-ratio images in a VHR scene. A selection of the most relevant bands to use for classification is carried out using band selection based on a genetic algorithm. Sensitivity analysis is used to assess the importance of each input variable. An application of the proposed methods to part of a Quickbird image taken over the suburban fringe of the city of Ghent (Belgium) shows that we are able to identify roads with much higher accuracy than when using more traditional multi-spectral image classification techniques.
Very High Resolution (VHR) satellite imagery offers a great potential for extracting land-use and land-cover related information for urban areas, but do they meet the requirements of present day urban planners? Assessing user needs for urban land use/land cover data, and investigating the potential of VHR data to better meet these needs is therefore essential. These two parts lead to an interactive definition of remote sensing products in Belgium. This paper presents the background of our analysis (previous surveys at European and French level), the methods that we use to assess the urban users needs (questionnaire and survey), how these can be met by VHR data (classification results) and some preliminary results of the Belgian survey obtained for both the Walloon and Brussels region. Among these results, the survey reports the preference on ortho-rectified aerial photographs when this product is available, a scarce use of remote sensing data explained by spatial resolution and cost reasons, and the lack of awareness of the new VHR images capabilities. As results for the ongoing survey become complete, we hope to better understand what data products derived from VHR imagery can potentially be of interest to users of LU/LC data in Belgium. This will enable us to propose image processing methods that better fulfil the needs of local and regional authorities in Belgium.