Mutual On-Line Learning for Detection and Tracking in High-Resolution Images

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F13%3A00239309" target="_blank" >RIV/68407700:21230/13:00239309 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-642-32350-8_15" target="_blank" >http://dx.doi.org/10.1007/978-3-642-32350-8_15</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-642-32350-8_15" target="_blank" >10.1007/978-3-642-32350-8_15</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Mutual On-Line Learning for Detection and Tracking in High-Resolution Images

Popis výsledku v původním jazyce

This paper addresses object detection and tracking in high-resolution omnidirectional images. The foreseen application is a visual subsystem of a rescue robot equipped with an omnidirectional camera, which demands real-time efficiency and robustness against changing viewpoint. Object detectors typically do not guarantee specific frame rate. The detection time may vastly depend on a scene complexity and image resolution. The adapted tracker can often help to overcome the situation, where the appearance of the object is far from the training set. On the other hand, once a tracker is lost, it almost never finds the object again. We propose a combined solution where a very efficient tracker (based on sequential linear predictors) incrementally accommodatesvarying appearance and speeds up the whole process. Next we propose to incrementally update the detector with examples collected by the tracker. We experimentally show that the performance of the combined algorithm, measured by a ratio b

Název v anglickém jazyce

Mutual On-Line Learning for Detection and Tracking in High-Resolution Images

Popis výsledku anglicky

This paper addresses object detection and tracking in high-resolution omnidirectional images. The foreseen application is a visual subsystem of a rescue robot equipped with an omnidirectional camera, which demands real-time efficiency and robustness against changing viewpoint. Object detectors typically do not guarantee specific frame rate. The detection time may vastly depend on a scene complexity and image resolution. The adapted tracker can often help to overcome the situation, where the appearance of the object is far from the training set. On the other hand, once a tracker is lost, it almost never finds the object again. We propose a combined solution where a very efficient tracker (based on sequential linear predictors) incrementally accommodatesvarying appearance and speeds up the whole process. Next we propose to incrementally update the detector with examples collected by the tracker. We experimentally show that the performance of the combined algorithm, measured by a ratio b

Druh

D - Stať ve sborníku

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)

Rok uplatnění

2013

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics. Theory and Applications (VISIGRAPP2011)

ISBN

978-3-642-32349-2

ISSN

1865-0929

e-ISSN

—

Počet stran výsledku

17

Strana od-do

240-256

Název nakladatele

Springer

Místo vydání

Heidelberg

Místo konání akce

Algarve

Datum konání akce

5. 3. 2011

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—