Urban change detection between heterogeneous images using the edge information

Change detection using the heterogeneous data such as aerial images, aerial LiDAR (Light Detection And Ranging), and satellite images needs to be developed to efficiently monitor the complicating land use change. We approached this problem not relying on the intensity value of the geospatial image, but by using RECC(Relative Edge Cross Correlation) which is based on the edge information over the urban and suburban area. The experiment was carried out for the aerial LiDAR data with high-resolution Kompsat-2 and -3 images. We derived the optimal window size and threshold value for RECC-based change detection, and then we observed the overall change detection accuracy of 80% by comparing the results to the manually acquired reference data.