Aerial image registration based on joint feature-spatial spaces, curve and template matching

Image registration has wide applications in remote sensing, medicine, cartography, and computer vision. This paper describes a method for aerial image registration, which is based on joint feature-spatial spaces, curve matching, and template matching. The entire algorithm consists of (i) segmentation and region representation, (ii) region matching based on joint featurespatial space, (iii) transformation model estimation based on curve matching and template matching, and (iv) image transformation. Experiment results show the effectiveness of this algorithm.