next up previous contents
Next: Learning Control of Indoor Up: Computational Information Processing Previous: Modelling of Consumer Demand

Urban Area Classification Based on Aerial Photographs

Researchers:Jukka Heikkonen, Laura Sirro, Tommi Orpana and Jouko Lampinen


This study belongs to the project ``Data-fusion and neural networks in complex models'' financed by TEKES and participating enterprises.

Remote sensing technology offers the potential to economically gather land use/land cover information over extensive geographical areas. This technology is also fast and in principle repeatable on a relative short time scale, e.g. every few weeks. Therefore it is no wonder that remote sensing has been found to be a valuable tool in the collection of statistical data concerning the land cover/land use on the earth.

The aim of this study is to develop an approach for aerial photographs based land cover/land use classification of urban areas. The objectives of this study are closely related to the store's comsumer demand modelling: There are many cities where no recent information for modelling is available, e.g., on distribution of the population and the purchasing power. The aerial photographs should provide some information of this type. The goal is to classify the buildings in the image and then, based on the building types and areas, estimate the population and the purchasing power in different image areas. Also the most important traffic networks (roads, railways, etc.) are to be located. The information on population, purchasing power and traffic routes are then used for modelling the stores' consumer demand in each area of interest.


 
Figure 7
Figure 7: A typical urban area image to be classified.


next up previous contents
Next: Learning Control of Indoor Up: Computational Information Processing Previous: Modelling of Consumer Demand
www@lce.hut.fi