Change detection using the integration of remote sensing and GIS: A polygon based approach

A per polygon image analysis scheme for detecting the changes in land cover conditions within existing land use boundaries stored as vector polygons in a Geographic Information System (GIS) is described. The scheme consists of three main steps: integration of remotely sensed and geographic data, the statistical testing of the pixels, and the assessment of the results. Change detection in the image is facilitated by a geographic database which contains the land use polygons and the attributes associated with them. The imagery is analysed in a polygon specific manner. The scheme provides a means to analyze the remotely sensed data by spatially related information stored in a database and the manipulative processing operations which a GIS supports. The concept is demonstrated by an example on the monitoring of the development of tree plantations.