Wald's Sequential Analysis for Time-constrained Vision Problems

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F08%3A03151197" target="_blank" >RIV/68407700:21230/08:03151197 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Wald's Sequential Analysis for Time-constrained Vision Problems

Popis výsledku v původním jazyce

In detection and matching problems in computer vision, both classification errors and time to decision characterize the quality of an algorithmic solution. It is shown how to formalize such problems in the framework of sequential decision-making and derive quasi-optimal time-constrained solutions for three vision problems. The methodology is applied to face and interest point detection and to the RANSAC robust estimator. Error rates of the face detector proposed algorithm are comparable to the state-of-the-art methods. In the interest point application, the output of the Hessian-Laplace detector [Mikolajczyk-IJCV04] is approximated by a sequential WaldBoost classifier which is about five times faster than the original with comparable repeatability. A sequential strategy based on Wald's SPRT for evaluation of model quality in RANSAC leads to significant speed-up in geometric matching problems.

Název v anglickém jazyce

Wald's Sequential Analysis for Time-constrained Vision Problems

Popis výsledku anglicky

In detection and matching problems in computer vision, both classification errors and time to decision characterize the quality of an algorithmic solution. It is shown how to formalize such problems in the framework of sequential decision-making and derive quasi-optimal time-constrained solutions for three vision problems. The methodology is applied to face and interest point detection and to the RANSAC robust estimator. Error rates of the face detector proposed algorithm are comparable to the state-of-the-art methods. In the interest point application, the output of the Hessian-Laplace detector [Mikolajczyk-IJCV04] is approximated by a sequential WaldBoost classifier which is about five times faster than the original with comparable repeatability. A sequential strategy based on Wald's SPRT for evaluation of model quality in RANSAC leads to significant speed-up in geometric matching problems.

Druh

C - Kapitola v odborné knize

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

<a href="/cs/project/GA201%2F06%2F1821" target="_blank" >GA201/06/1821: Algoritmy rozpoznávání obrazu</a><br>

Návaznosti

R - Projekt Ramcoveho programu EK

Rok uplatnění

2008

Kód důvěrnosti údajů

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

Název knihy nebo sborníku

Unifying Perspectives in Computational and Robot Vision

ISBN

978-0-387-75521-2

Počet stran výsledku

21

Strana od-do

—

Počet stran knihy

212

Název nakladatele

Springer

Místo vydání

New York

Kód UT WoS kapitoly

—