In this paper, we present a new framework for geo-locating an image utilizing a novel multiple nearest neighbor feature matching method using Generalized Minimum Clique Graphs (GMCP). First, we extract local features (e.g. SIFT) from the query image and retrieve a number of nearest neighbors for each query feature from the reference dataset. Next, we apply our GMCPbased feature matching to select a single nearest neighbor for each query feature such that all matches are globally consistent. Our approach to feature matching is based on the proposition that the first nearest neighbors are not necessarily the best choices for finding correspondences in image matching. Therefore, the proposed method considers multiple reference nearest neighbors as potential matches and selects the correct ones by enforcing consistency among their global features (e.g. GIST) using GMCP. In this context, we argue that using a robust distance function for finding the similarity between the global features is essential for the cases where the query matches multiple reference images with dissimilar global features. We evaluated the proposed framework on a new dataset of 102k street view images; the experiments show it outperforms the state of the art by 10%.
generalized graphs, Geo-location, image localization, Generalized Minimum Clique Problem (GMCP), Generalized Minimum Spanning Tree (GMST), feature matching, multiple nearest neighbor feature matching, feature correspondence
M. Shah, "Image Geo-localization Based on Multiple Nearest Neighbor Feature Matching Using Generalized Graphs," in IEEE Transactions on Pattern Analysis & Machine Intelligence.