Show simple item record

dc.creatorWorkman, S
dc.creatorSouvenir, R
dc.creatorJacobs, N
dc.date.accessioned2021-02-03T18:06:32Z
dc.date.available2021-02-03T18:06:32Z
dc.date.issued2015-02-17
dc.identifier.issn1550-5499
dc.identifier.doihttp://dx.doi.org/10.34944/dspace/5800
dc.identifier.otherBF1NZ (isidoc)
dc.identifier.urihttp://hdl.handle.net/20.500.12613/5818
dc.description.abstract© 2015 IEEE. We propose to use deep convolutional neural networks to address the problem of cross-view image geolocalization, in which the geolocation of a ground-level query image is estimated by matching to georeferenced aerial images. We use state-of-the-art feature representations for ground-level images and introduce a cross-view training approach for learning a joint semantic feature representation for aerial images. We also propose a network architecture that fuses features extracted from aerial images at multiple spatial scales. To support training these networks, we introduce a massive database that contains pairs of aerial and ground-level images from across the United States. Our methods significantly out-perform the state of the art on two benchmark datasets. We also show, qualitatively, that the proposed feature representations are discriminative at both local and continental spatial scales.
dc.format.extent3961-3969
dc.relation.haspartProceedings of the IEEE International Conference on Computer Vision
dc.relation.isreferencedbyIEEE
dc.subjectcs.CV
dc.subjectcs.CV
dc.titleWide-area image geolocalization with aerial reference imagery
dc.typeArticle
dc.type.genreConference Proceeding
dc.relation.doi10.1109/ICCV.2015.451
dc.ada.noteFor Americans with Disabilities Act (ADA) accommodation, including help with reading this content, please contact scholarshare@temple.edu
dc.creator.orcidSouvenir, Richard|0000-0002-6066-0946
dc.date.updated2021-02-03T18:06:28Z
refterms.dateFOA2021-02-03T18:06:33Z


Files in this item

Thumbnail
Name:
1510.03743v1.pdf
Size:
4.044Mb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record