About: A Few Things One Should Know About Feature Extraction, Description and Matching

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

About: A Few Things One Should Know About Feature Extraction, Description and Matching 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
Description	We explore the computational bottlenecks of the affine feature extraction process and sho w how this process can be speeded up by 2-3 times with no or very modest loss of performance. With o ur improvements the speed of the Hessian-Affine and MSER detector is comparable with similarity-inva riant SURF and DoG-SIFT detectors. The improvements presented include a faster anisotropic patch ext raction algorithm which does not depend on the feature scale, a speed up of a feature dominant orien tation estimation and SIFT descriptor computation using a look-up table. In the second part of the paper we explore performance of the recently proposed first geometrically inconsistent nearest neighbour criterion and domination orientation generation process. We explore the computational bottlenecks of the affine feature extraction process and sho w how this process can be speeded up by 2-3 times with no or very modest loss of performance. With o ur improvements the speed of the Hessian-Affine and MSER detector is comparable with similarity-inva riant SURF and DoG-SIFT detectors. The improvements presented include a faster anisotropic patch ext raction algorithm which does not depend on the feature scale, a speed up of a feature dominant orien tation estimation and SIFT descriptor computation using a look-up table. In the second part of the paper we explore performance of the recently proposed first geometrically inconsistent nearest neighbour criterion and domination orientation generation process. (en)
Title	A Few Things One Should Know About Feature Extraction, Description and Matching A Few Things One Should Know About Feature Extraction, Description and Matching (en)
skos:prefLabel	A Few Things One Should Know About Feature Extraction, Description and Matching A Few Things One Should Know About Feature Extraction, Description and Matching (en)
skos:notation	RIV/68407700:21230/14:00217905!RIV15-MSM-21230___
http://linked.open...avai/riv/aktivita	P
http://linked.open...avai/riv/aktivity	P(7E11036), P(TE01020415)
http://linked.open...vai/riv/dodaniDat	2015
http://linked.open...aciTvurceVysledku	Lenc, Karel Matas, Jiří Mishkin, Dmytro
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	719
http://linked.open...ai/riv/idVysledku	RIV/68407700:21230/14:00217905
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	feature detectors; image matching; feature descriptors (en)
http://linked.open.../riv/klicoveSlovo	image matching feature descriptors feature detectors
http://linked.open...ontrolniKodProRIV	[D61F67586B82]
http://linked.open...v/mistoKonaniAkce	Krtiny
http://linked.open...i/riv/mistoVydani	Praha
http://linked.open...i/riv/nazevZdroje	CVWW2014: Proceedings of the 19th Computer Vision Winter Workshop
http://linked.open...in/vavai/riv/obor	JD
http://linked.open...ichTvurcuVysledku	3 (xsd:int)
http://linked.open...cetTvurcuVysledku	3 (xsd:int)
http://linked.open...vavai/riv/projekt	V3C - Visual Computing Competence Center Dextrous Assembler Robot Working with embodied INtelligence
http://linked.open...UplatneniVysledku	2014
http://linked.open...iv/tvurceVysledku	Matas, Jiří Mishkin, Dmytro Lenc, Karel
http://linked.open...vavai/riv/typAkce	EUR - Evropská
http://linked.open.../riv/zahajeniAkce	2014-02-03 (xsd:date)
number of pages	8 (xsd:int)
http://purl.org/ne...btex#hasPublisher	Czech Society for Cybernetics and Informatics
https://schema.org/isbn	978-80-260-5641-6
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