Image Localization in Satellite Imagery with Feature-based Indexing

This paper presents a method to index ortho-map databases with image-based features and search a map database for regions that match query images of unknown scales and rotations. The proposed method uses image-based features to index the 2D map locations. Image feature extractors normally generate features with location, orientation, shape, and a descriptor for normalized image patch. In a map database, the geographical location, orientation and shape of the image features can be recovered with a reasonable local planarity assumptions. The paper makes use of a visual word based recognition scheme and extends it by adding geographical dimensions to the visual words and use them to index 2D locations in a map grid.An indexing-friendly scoring system is defined to measure the similarity of query and database images which represent unit tiles of the complete map. The implemented scoring algorithm can efficiently give the matching scores between a query image and all possible database images. Upon searching a new approximately orthogonal image, a set of scaling and rotations are first selected, and the visual words are transformed and matched against the database. The best locations along with scales and rotations are determined from the query results of the different set of transformed visual words. Experiments show a high success rate and high speed in searching map databases for aerial images from different datasets.