 |
    |
Planar Structure Matching under Projective Uncertainty for Geolocation
Ang Li, Vlad I. Morariu, and Larry S. Davis
University of Maryland, College Park, USAangli@umiacs.umd.edu
morariu@umiacs.umd.edu
lsd@umiacs.umd.edu
Abstract. Image based geolocation aims to answer the question: where was this ground photograph taken? We present an approach to geolocalating a single image based on matching human delineated line segments in the ground image to automatically detected line segments in ortho images. Our approach is based on distance transform matching. By observing that the uncertainty of line segments is non-linearly amplified by projective transformations, we develop an uncertainty based representation and incorporate it into a geometric matching framework. We show that our approach is able to rule out a considerable portion of false candidate regions even in a database composed of geographic areas with similar visual appearances.
Keywords: uncertainty modeling, geometric matching, line segments
LNCS 8695, p. 265 ff.
lncs@springer.com
© Springer International Publishing Switzerland 2014