About: Learning and Calibrating Per-Location Classifiers for Visual Place Recognition

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Learning and Calibrating Per-Location Classifiers for Visual Place Recognition Goto Sponge NotDistinct Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

Attributes	Values
rdf:type	skos:Concept http://linked.opendata.cz/ontology/domain/vavai/Vysledek
rdfs:seeAlso	http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Gronat_Learning_and_Calibrating_2013_CVPR_paper.pdf
Description	The aim of this work is to localize a query photograph by finding other images depicting the same place in a large geotagged image database. This is a challenging task due to changes in viewpoint, imaging conditions and the large size of the image database. The contribution of this work is two-fold. First, we cast the place recognition problem as a classification task and use the available geotags to train a classifier for each location in the database in a similar manner to per-exemplar SVMs in object recognition. Second, as only few positive training examples are available for each location, we propose a new approach to calibrate all the per-location SVM classifiers using only the negative examples. The calibration we propose relies on a significance measure essentially equivalent to the p-values classically used in statistical hypothesis testing. Experiments are performed on a database of 25,000 geotagged street view images of Pittsburgh and demonstrate improved place recognition accuracy of the proposed approach over the previous work. The aim of this work is to localize a query photograph by finding other images depicting the same place in a large geotagged image database. This is a challenging task due to changes in viewpoint, imaging conditions and the large size of the image database. The contribution of this work is two-fold. First, we cast the place recognition problem as a classification task and use the available geotags to train a classifier for each location in the database in a similar manner to per-exemplar SVMs in object recognition. Second, as only few positive training examples are available for each location, we propose a new approach to calibrate all the per-location SVM classifiers using only the negative examples. The calibration we propose relies on a significance measure essentially equivalent to the p-values classically used in statistical hypothesis testing. Experiments are performed on a database of 25,000 geotagged street view images of Pittsburgh and demonstrate improved place recognition accuracy of the proposed approach over the previous work. (en)
Title	Learning and Calibrating Per-Location Classifiers for Visual Place Recognition Learning and Calibrating Per-Location Classifiers for Visual Place Recognition (en)
skos:prefLabel	Learning and Calibrating Per-Location Classifiers for Visual Place Recognition Learning and Calibrating Per-Location Classifiers for Visual Place Recognition (en)
skos:notation	RIV/68407700:21230/13:00212089!RIV14-MSM-21230___
http://linked.open...avai/predkladatel	Fakulta elektrotechnická
http://linked.open...avai/riv/aktivita	P S
http://linked.open...avai/riv/aktivity	P(7E13015), S
http://linked.open...vai/riv/dodaniDat	2014
http://linked.open...aciTvurceVysledku	Gronát, Petr Pajdla, Tomáš
http://linked.open.../riv/druhVysledku	D - Článek ve sborníku
http://linked.open...iv/duvernostUdaju	S - Úplné a pravdivé údaje nepodléhající ochraně podle zvláštních právních předpisů
http://linked.open...titaPredkladatele	České vysoké učení technické v Praze / Fakulta elektrotechnická
http://linked.open...dnocenehoVysledku	84509
http://linked.open...ai/riv/idVysledku	RIV/68407700:21230/13:00212089
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	image based localization; SVM classifier; classifier calibration (en)
http://linked.open.../riv/klicoveSlovo	SVM classifier classifier calibration image based localization
http://linked.open...ontrolniKodProRIV	[784C0B0F35B8]
http://linked.open...v/mistoKonaniAkce	Portland
http://linked.open...i/riv/mistoVydani	Los Alamitos
http://linked.open...i/riv/nazevZdroje	CVPR 2013: IEEE Computer Society Conference on Computer Vision and Pattern Recognition
http://linked.open...in/vavai/riv/obor	JD
http://linked.open...ichTvurcuVysledku	2 (xsd:int)
http://linked.open...cetTvurcuVysledku	4 (xsd:int)
http://linked.open...vavai/riv/projekt	Planetary Robotics Data Exploitation
http://linked.open...UplatneniVysledku	2013
http://linked.open...iv/tvurceVysledku	Pajdla, Tomáš Gronát, Petr Šivic, J. Obozinski, G.
http://linked.open...vavai/riv/typAkce	WRD - Světová
http://linked.open.../riv/zahajeniAkce	2013-06-23 (xsd:date)
issn	1063-6919
number of pages	8 (xsd:int)
http://purl.org/ne...btex#hasPublisher	IEEE Computer Society
https://schema.org/isbn	978-0-7695-4989-7
http://localhost/t...ganizacniJednotka	21230

Faceted Search & Find service v1.16.118 as of Jun 21 2024

Alternative Linked Data Documents: ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 48 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software