Research on Linear Features Change Detection Based on Remote Sensing Image and Vector Data

To prompt the present situation and utilized values of fundamental geo-information, this paper focuses on a change detection method based on remote sensing image and GIS vector for linear features. Firstly unilateral vector was taken as original value of linear features; then edge points were picked up by pyramid decomposition and multi-scale template matching, and Ziplock Snake method was adopted to further improve the extraction results; finally buffer zone was constructed to distinguish the changed part. This change detection method proves to have higher degree of automation and more precise, so long as the registration of remote sensing image and vector map is accurate.