Camera Tracking and Autocalibration for Detecting and Correcting Camera De-Calibration
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F09%3A00166010" target="_blank" >RIV/68407700:21230/09:00166010 - isvavai.cz</a>
Výsledek na webu
—
DOI - Digital Object Identifier
—
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Camera Tracking and Autocalibration for Detecting and Correcting Camera De-Calibration
Popis výsledku v původním jazyce
In this report, we present several contributions to the dynamic 3D scene analysis supported by image and video processing from omnidirectional video data acquired by the AWEAR 2.0 platform. First, we summarize the upgrades of our structure from motion (SfM) pipelines for the autocalibration of the AWEAR 2.0 camera platform. Next, we examine several examples of detecting abnormal situations using statistics resulted from camera tracking: (i) feature detection, (ii) sequential matching, and (iii) stereo matching on the top of SfM. Finally, we demonstrate the detection and classification of abnormal situations, and correction of the contaminated camera calibrations according to the abnormal events on real video sequences.
Název v anglickém jazyce
Camera Tracking and Autocalibration for Detecting and Correcting Camera De-Calibration
Popis výsledku anglicky
In this report, we present several contributions to the dynamic 3D scene analysis supported by image and video processing from omnidirectional video data acquired by the AWEAR 2.0 platform. First, we summarize the upgrades of our structure from motion (SfM) pipelines for the autocalibration of the AWEAR 2.0 camera platform. Next, we examine several examples of detecting abnormal situations using statistics resulted from camera tracking: (i) feature detection, (ii) sequential matching, and (iii) stereo matching on the top of SfM. Finally, we demonstrate the detection and classification of abnormal situations, and correction of the contaminated camera calibrations according to the abnormal events on real video sequences.
Klasifikace
Druh
O - Ostatní výsledky
CEP obor
JD - Využití počítačů, robotika a její aplikace
OECD FORD obor
—
Návaznosti výsledku
Projekt
—
Návaznosti
R - Projekt Ramcoveho programu EK
Ostatní
Rok uplatnění
2009
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů