This paper presents a new approach for the challenging problem of geo-locating an image using image matching in a structured database of city-wide reference images with known GPS coordinates. We cast the geo-localization as a clustering problem on local image features. Akin to existing approaches on the problem, our framework builds on low-level SIFT features which allow partial matching between images. For each local feature in the query image, we find its approximate nearest neighbors in the reference set. Next, we cluster the features from the reference images using Dominant Set clustering, which affords several advantages over existing approaches. First, it permits variable number of nodes in the cluster which we use to dynamically select the number of nearest neighbours (typically coming from multiple reference images) for each query feature based on its discrimination value. Second, as we also quantify in our experiments, this approach is several orders of magnitude faster than existing approaches. Thus, we obtain multiple clusters (different local maximizers) and obtain a robust final solution to the problem using multiple weaker solutions through constrained Dominant Set clustering on global image features, where we enforce the constraint that the query image must be included in the cluster. This second level of clustering also bypasses heuristic approaches to voting and selecting the reference image that matches to the query. We evaluated the proposed framework on data sets of 300k (new data set) and 102k street view images, and show that it outperforms the state of the art by up to 20 percent on average.

Large-scale Image Geo-Localization Using Dominant Sets / Zemene, E.; Tariku, Y.; Idrees, H.; Prati, A.; Pelillo, M.; Shah, M.. - In: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. - ISSN 0162-8828. - 41:1(2019), pp. 148-161. [10.1109/TPAMI.2017.2787132]

Large-scale Image Geo-Localization Using Dominant Sets

A. Prati
Writing – Review & Editing
;
2019-01-01

Abstract

This paper presents a new approach for the challenging problem of geo-locating an image using image matching in a structured database of city-wide reference images with known GPS coordinates. We cast the geo-localization as a clustering problem on local image features. Akin to existing approaches on the problem, our framework builds on low-level SIFT features which allow partial matching between images. For each local feature in the query image, we find its approximate nearest neighbors in the reference set. Next, we cluster the features from the reference images using Dominant Set clustering, which affords several advantages over existing approaches. First, it permits variable number of nodes in the cluster which we use to dynamically select the number of nearest neighbours (typically coming from multiple reference images) for each query feature based on its discrimination value. Second, as we also quantify in our experiments, this approach is several orders of magnitude faster than existing approaches. Thus, we obtain multiple clusters (different local maximizers) and obtain a robust final solution to the problem using multiple weaker solutions through constrained Dominant Set clustering on global image features, where we enforce the constraint that the query image must be included in the cluster. This second level of clustering also bypasses heuristic approaches to voting and selecting the reference image that matches to the query. We evaluated the proposed framework on data sets of 300k (new data set) and 102k street view images, and show that it outperforms the state of the art by up to 20 percent on average.
2019
Large-scale Image Geo-Localization Using Dominant Sets / Zemene, E.; Tariku, Y.; Idrees, H.; Prati, A.; Pelillo, M.; Shah, M.. - In: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. - ISSN 0162-8828. - 41:1(2019), pp. 148-161. [10.1109/TPAMI.2017.2787132]
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11381/2836127
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 29
  • ???jsp.display-item.citation.isi??? 22
social impact