Panorama to panorama matching for location recognition - Archive ouverte HAL Access content directly
Conference Papers Year :

Panorama to panorama matching for location recognition

(1) , (2) , (1) , (1) , (2)
1
2

Abstract

Location recognition is commonly treated as visual instance retrieval on "street view" imagery. The dataset items and queries are panoramic views, i.e.groups of images taken at a single location. This work introduces a novel panorama-to-panorama matching process, either by aggregating features of individual images in a group or by explicitly constructing a larger panorama. In either case, multiple views are used as queries. We reach near perfect location recognition on a standard benchmark with only four query views.
Fichier principal
Vignette du fichier
Iscen_icmr17.pdf (1.11 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01511793 , version 1 (21-04-2017)

Identifiers

Cite

Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Teddy Furon, Ondřej Chum. Panorama to panorama matching for location recognition. ACM International Conference on Multimedia Retrieval (ICMR) 2017, Jun 2017, Bucharest, Romania. ⟨10.1145/3078971.3079033⟩. ⟨hal-01511793⟩
398 View
543 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More