A System For Urban Vegetation Segmentation Based On Satellite Photograph

With accelerate construction of ecological civilization, people pay more attention to the ecological and environmental problems of the city. A new topic has been born for that how to smoothly use existing resources to calculate forestry information, such as an area of vegetation, vegetation distribution and so on.Along with the rapid development of image processing technology, it will be used in the field of forestry information extraction to help the researcher and the public to obtain more comprehensive information of forestry and the development of forestry.In order to quickly and accurately get the vegetation information without high-resolution remote sensing image we develop this system. The Paper completed an urban vegetation segmentation system based on satellite map photograph. Based on Matlab, the K-means algorithm and color segmentation algorithm the system succeed in distinguishing the vegetation from the city satellite map photograph. And it uses texture segmentation algorithm based on entropy, further divided the vegetation into trees and grassland. By extracting the information image scale, the system can calculate the exact area of the vegetation region. The experiments data contains pure vegetation and the urban vegetation region. Experimental results are similar to commercial software. The system can process any region on the map and calculating the actual area of the vegetation region. The result of the system can be used in related fields of forestry.