Incremental learning and validation of sequential predictors in video browsing application

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F10%3A00175502" target="_blank" >RIV/68407700:21230/10:00175502 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Incremental learning and validation of sequential predictors in video browsing application

Popis výsledku v původním jazyce

Loss-of-track detection (tracking validation) and automatic tracker adaptation to new object appearances are attractive topics in computer vision. We apply very efficient learnable sequential predictors in order to address both issues. Validation is doneby clustering of the sequential predictor responses. No aditional object model for validation is needed. The paper also proposes an incremental learning procedure that accommodates changing object appearance, which mainly improves the recall of the tracker/detector. Exemplars for the incremental learning are collected automatically, no user interaction is required. The aditional training examples are selected automatically using the tracker stability computed for each potential aditional training example. Coupled with a sparsely applied SIFT or SURF based detector the method is employed for object localization in videos. Our Matlab implementation scans videosequences up to eight times faster than the actual frame rate. A standard-lengt

Název v anglickém jazyce

Incremental learning and validation of sequential predictors in video browsing application

Popis výsledku anglicky

Loss-of-track detection (tracking validation) and automatic tracker adaptation to new object appearances are attractive topics in computer vision. We apply very efficient learnable sequential predictors in order to address both issues. Validation is doneby clustering of the sequential predictor responses. No aditional object model for validation is needed. The paper also proposes an incremental learning procedure that accommodates changing object appearance, which mainly improves the recall of the tracker/detector. Exemplars for the incremental learning are collected automatically, no user interaction is required. The aditional training examples are selected automatically using the tracker stability computed for each potential aditional training example. Coupled with a sparsely applied SIFT or SURF based detector the method is employed for object localization in videos. Our Matlab implementation scans videosequences up to eight times faster than the actual frame rate. A standard-lengt

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

<a href="/cs/project/GAP103%2F10%2F1585" target="_blank" >GAP103/10/1585: Pokročilé prediktory pro detekci a sledování objektů ve videu</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2010

Kód důvěrnosti údajů

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

Název statě ve sborníku

VISIGRAPP 2010: International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

ISBN

978-989-674-028-3

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

—

Název nakladatele

Institute for Systems and Technologies of Information, Control and Communication

Místo vydání

Setúbal

Místo konání akce

Angers

Datum konání akce

17. 5. 2010

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—