We present a novel method for automatically geo-tagging photographs of man-made environments via detection and matching of repeated patterns. Highly repetitive environments introduce numerous correspondence ambiguities and are problematic for traditional wide-baseline matching methods. Our method exploits the highly repetitive nature of urban environments, detecting multiple perspectively distorted periodic 2D patterns in an image and matching them to a 3D database of textured facades by reasoning about the underlying canonical forms of each pattern. Multiple 2D-to-3D pattern correspondences enable robust recovery of camera orientation and location. We demonstrate the success of this method in a large urban environment.

Text Reference

Grant Schindler, Panchapagesan Krishnamurthy, Roberto Lublinerman, Yanxi Liu and Frank Dellaert, "Detecting and Matching Repeated Patterns for Automatic Geo-tagging in Urban Environments," Computer Vision and Pattern Recognition (CVPR), June, 2008

BibTeX Reference

@inproceedings{Schindler_CVPR_2008,
    author = "Grant Schindler, Panchapagesan Krishnamurthy, Roberto Lublinerman, Yanxi Liu and Frank Dellaert",
    title = "Detecting and Matching Repeated Patterns for Automatic Geo-tagging in Urban Environments",
    booktitle = "Computer Vision and Pattern Recognition (CVPR)",
    month = "June",
    year = "2008",
}