Loading...
Please wait, while we are loading the content...
Similar Documents
Cross-view image geolocalization
| Content Provider | CiteSeerX |
|---|---|
| Author | Lin, Tsung-Yi Belongie, Serge Hays, James |
| Description | In: Proc. CVPR (2013 The recent availability of large amounts of geotagged im-agery has inspired a number of data driven solutions to the image geolocalization problem. Existing approaches predict the location of a query image by matching it to a database of georeferenced photographs. While there are many geotagged images available on photo sharing and street view sites, most are clustered around landmarks and urban areas. The vast majority of the Earth’s land area has no ground level reference photos available, which lim-its the applicability of all existing image geolocalization methods. On the other hand, there is no shortage of vi-sual and geographic data that densely covers the Earth – we examine overhead imagery and land cover survey data – but the relationship between this data and ground level query photographs is complex. In this paper, we introduce a cross-view feature translation approach to greatly extend the reach of image geolocalization methods. We can often localize a query even if it has no corresponding ground-level images in the database. A key idea is to learn the relationship between ground level appearance and over-head appearance and land cover attributes from sparsely available geotagged ground-level images. We perform ex-periments over a 1600 km2 region containing a variety of scenes and land cover types. For each query, our algorithm produces a probability density over the region of interest. 1. |
| File Format | |
| Language | English |
| Access Restriction | Open |
| Subject Keyword | Land Cover Survey Data Large Amount Cross-view Feature Translation Approach Image Geolocalization Method Ground Level Query Photograph Image Geolocalization Problem Geographic Data Km2 Region Land Cover Type Query Image Over-head Appearance Ground-level Image Ground Level Appearance Earth Land Area Street View Site Recent Availability Ground Level Reference Photo Vast Majority Many Geotagged Image Photo Sharing Land Cover Cross-view Image Geolocalization Key Idea Probability Density Urban Area Georeferenced Photograph Corresponding Ground-level Image Overhead Imagery |
| Content Type | Text |
| Resource Type | Article |
