Real-time estimation of the 3D transformation between images with large viewpoint differences in cluttered environments

D.W.J.M. van de Wouw, M.A.R. Pieck, G. Dubbelman, P.H.N. de With

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademic

2 Citaten (Scopus)
126 Downloads (Pure)

Samenvatting

This work focuses on estimating an accurate 3D transformation in real time, which is used to register images acquired from different viewpoints. The main challenges are significant image appearance differences, which originate from lateral displacements and parallax, inconsistencies in our 3D model and achieving real-time execution. To this end, we propose a featurebased method using a single synthesized view, which can cope with significant image appearance differences. The 3D transformation is estimated using an EPnP refinement to minimize the influence of inconsistencies in the 3D model. We demonstrate that the proposed method achieves over 95% transformation accuracy for lateral displacements up to 350 cm, while still achieving 85% accuracy at displacements of 530 cm. Additionally, with a running time of 100 milliseconds, we achieve real-time execution as a result of efficiency optimizations and GPU implementations of time-critical components.
Originele taal-2Engels
TitelImage Processing: algorithms and systems XV
RedacteurenS.S. Agaian, K.O. Egiazarian, A.P. Gotchev
Plaats van productieSpringfield
UitgeverijSociety for Imaging Science and Technology
Pagina's109-116
Aantal pagina's8
DOI's
StatusGepubliceerd - feb 2017
EvenementIS&T International Symposium on Electronic Imaging Science and Technology, : Image Processing: Algorithms and Systems XV - Burlingame, Verenigde Staten van Amerika
Duur: 29 jan 20172 feb 2017

Congres

CongresIS&T International Symposium on Electronic Imaging Science and Technology,
LandVerenigde Staten van Amerika
StadBurlingame
Periode29/01/172/02/17

Vingerafdruk Duik in de onderzoeksthema's van 'Real-time estimation of the 3D transformation between images with large viewpoint differences in cluttered environments'. Samen vormen ze een unieke vingerafdruk.

  • Citeer dit

    van de Wouw, D. W. J. M., Pieck, M. A. R., Dubbelman, G., & de With, P. H. N. (2017). Real-time estimation of the 3D transformation between images with large viewpoint differences in cluttered environments. In S. S. Agaian, K. O. Egiazarian, & A. P. Gotchev (editors), Image Processing: algorithms and systems XV (blz. 109-116). Society for Imaging Science and Technology. https://doi.org/10.2352/ISSN.2470-1173.2017.13.IPAS-209