A Novel Vector Road Maps to Remotely Sensed Image Conflation Approach

As the availability of vari. The process of integrating geospatial data from different sources is a challenging task in the Remote Sensing (RS) and Global Positioning System (GPS) technologies. Vector road maps do not line up with the corresponding image. The proposed approach provides a method for vector-to-image conflation. Road intersection and termination points are extracted from both the image and the road map. An iterative relaxation algorithm was used for point matching based on the relative distance information between points. A rubber-sheeting transformation subdivides the map areas into pieces and applies local adjustments on each single piece, preserving topology in the process. At the end of rubber-sheeting novel transform, there may be some misalignment occurred in the road segments. With the end points of each road in correct position, snake correction moves intermediate road points toward the road image. Finally a better road map is created with positional accuracy. This process is used in map updation.