Efficient Sequential Correspondence Selection by Cosegmentation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F10%3A00168986" target="_blank" >RIV/68407700:21230/10:00168986 - isvavai.cz</a>

Výsledek na webu

<a href="http://doi.ieeecomputersociety.org/10.1109/TPAMI.2009.176" target="_blank" >http://doi.ieeecomputersociety.org/10.1109/TPAMI.2009.176</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TPAMI.2009.176" target="_blank" >10.1109/TPAMI.2009.176</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Efficient Sequential Correspondence Selection by Cosegmentation

Popis výsledku v původním jazyce

Object recognition and wide baseline stereo methods, correspondences of interest points (distinguished regions) are commonly established by matching compact descriptors such as SIFTs. We show that a subsequent cosegmentation process coupled with a quasi-optimal sequential decision process leads to a correspondence verification procedure that (i) has high precision (ii) has good recall and (iii) is fast. The sequential decision on the correctness of a correspondence is based on simple statistics of a modified dense stereo matching algorithm. The statistics are projected on a prominent discriminative direction by SVM. Wald's sequential probability ratio test is performed on the SVM projection computed on progressively larger cosegmented regions.We show experimentally that the proposed Sequential Correspondence Verification (SCV) algorithm significantly outperforms the correspondence selection method based on SIFT distance ratios.

Název v anglickém jazyce

Efficient Sequential Correspondence Selection by Cosegmentation

Popis výsledku anglicky

Object recognition and wide baseline stereo methods, correspondences of interest points (distinguished regions) are commonly established by matching compact descriptors such as SIFTs. We show that a subsequent cosegmentation process coupled with a quasi-optimal sequential decision process leads to a correspondence verification procedure that (i) has high precision (ii) has good recall and (iii) is fast. The sequential decision on the correctness of a correspondence is based on simple statistics of a modified dense stereo matching algorithm. The statistics are projected on a prominent discriminative direction by SVM. Wald's sequential probability ratio test is performed on the SVM projection computed on progressively larger cosegmented regions.We show experimentally that the proposed Sequential Correspondence Verification (SCV) algorithm significantly outperforms the correspondence selection method based on SIFT distance ratios.

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

2010

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE Transactions on Pattern Analysis and Machine Intelligence

ISSN

0162-8828

e-ISSN

—

Svazek periodika

32

Číslo periodika v rámci svazku

9

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

14

Strana od-do

1568-1581

Kód UT WoS článku

000279969000003

EID výsledku v databázi Scopus

—