Remote Sensing in Rio de Janeiro City

The city of Rio carried out a Land-cover forestclassification with visual interpretation using SPOT data. Thiswork produced a compatible thematic map in the scale 1:50,000. Thescale of these maps permit to have a global vision of the landchange cover but unfortunately do not correspond with the GIS ofthe city, which works with a scale of 1:10,000. The city searchedfor options to make this work automatically and quickly to getinformation for planning and to propose solutions. In order tosolve this problem high resolution satellite data and automaticclassification of Land-cover classes are needed. Consequently,images as IKONOS need to be used to produce a classification, witha scale corresponding to the GIS of the city. Pixel basedclassification with IKONOS data show some problems because thelevel of information in the data produce a lot of incorrectclassified pixels. The solution to perform this classification usesthe new approach that makes one pre-classification, whichtransforms the pixel information in objects as well as the featurein the vector representation. To carry out the segmentation andclassification processes, oriented objects analysis areused.

Klappentext
The city of Rio carried out a Land-cover forest classification with visual interpretation using SPOT data. This work produced a compatible thematic map in the scale 1:50,000. The scale of these maps permit to have a global vision of the land change cover but unfortunately do not correspond with the GIS of the city, which works with a scale of 1:10,000. The city searched for options to make this work automatically and quickly to get information for planning and to propose solutions. In order to solve this problem high resolution satellite data and automatic classification of Land-cover classes are needed. Consequently, images as IKONOS need to be used to produce a classification, with a scale corresponding to the GIS of the city. Pixel based classification with IKONOS data show some problems because the level of information in the data produce a lot of incorrect classified pixels. The solution to perform this classification uses the new approach that makes one pre-classification, which transforms the pixel information in objects as well as the feature in the vector representation. To carry out the segmentation and classification processes, oriented objects analysis are used.