Framework for automated reconstruction of 3D model from multiple 2D aerial images

Dzenan Lapandic, Jasmin Velagic, Haris Balta

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdragepeer review

Samenvatting

The paper considers a problem of 3D environment model reconstruction from a set of 2D images acquired by the Unmanned Aerial Vehicle (UAV) in near real-time. The designed framework combines the FAST (Features from Accelerated Segment Test) algorithm and optical flow approach for detection of interest image points and adjacent images reconstruction. The robust estimation of camera locations is performed using the image points tracking. The coordinates of 3D points and the projection matrix are computed simultaneously using Structure-from-Motion (SfM) algorithm, from which the 3D model of environment is generated. The designed framework is tested using real image data and video sequences captured with camera mounted on the UAV. The effectiveness and quality of the proposed framework are verified through analyses of accuracy of the 3D model reconstruction and its time execution.

Originele taal-2Engels
TitelProceedings of ELMAR 2017 59th International Symposium ELMAR
RedacteurenMario Mustra, Dijana Vitas, Branka Zovko-Cihlar
UitgeverijCroatian Society Electronics in Marine - ELMAR
Pagina's173-176
Aantal pagina's4
ISBN van elektronische versie9789531842303
DOI's
StatusGepubliceerd - 29 nov. 2017
Evenement59th International Symposium ELMAR, ELMAR 2017 - Zadar, Kroatië
Duur: 18 sep. 201720 sep. 2017

Publicatie series

NaamProceedings Elmar - International Symposium Electronics in Marine
Volume2017-September
ISSN van geprinte versie1334-2630

Congres

Congres59th International Symposium ELMAR, ELMAR 2017
Land/RegioKroatië
StadZadar
Periode18/09/1720/09/17

Vingerafdruk

Duik in de onderzoeksthema's van 'Framework for automated reconstruction of 3D model from multiple 2D aerial images'. Samen vormen ze een unieke vingerafdruk.

Citeer dit