Live 3D shape reconstruction, recognition and registration

Carlos Hernández, Frank Perbet, Minh-Tri Pham, George Vogiatzis, Oliver J. Woodford, Atsuto Maki, Björn Stenger, Roberto Cipolla

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a video-based system which interactively captures the geometry of a 3D object in the form of a point cloud, then recognizes and registers known objects in this point cloud in a matter of seconds (fig. 1). In order to achieve interactive speed, we exploit both efficient inference algorithms and parallel computation, often on a GPU. The system can be broken down into two distinct phases: geometry capture, and object inference. We now discuss these in further detail.
Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Computer Vision
PublisherIEEE
Pages729
Number of pages1
ISBN (Print)978-1-4673-0062-9
DOIs
Publication statusPublished - 2011
EventIEEE International Conference on Computer Vision Workshops - Barcelona, Spain
Duration: 6 Nov 201113 Nov 2011

Conference

ConferenceIEEE International Conference on Computer Vision Workshops
Abbreviated titleICCV Workshops
CountrySpain
CityBarcelona
Period6/11/1113/11/11

Fingerprint

Geometry
Graphics processing unit

Cite this

Hernández, C., Perbet, F., Pham, M-T., Vogiatzis, G., Woodford, O. J., Maki, A., ... Cipolla, R. (2011). Live 3D shape reconstruction, recognition and registration. In Proceedings of the IEEE International Conference on Computer Vision (pp. 729). IEEE. https://doi.org/10.1109/ICCVW.2011.6130324
Hernández, Carlos ; Perbet, Frank ; Pham, Minh-Tri ; Vogiatzis, George ; Woodford, Oliver J. ; Maki, Atsuto ; Stenger, Björn ; Cipolla, Roberto. / Live 3D shape reconstruction, recognition and registration. Proceedings of the IEEE International Conference on Computer Vision. IEEE, 2011. pp. 729
@inproceedings{6832de0cbad24582a146b1937c44b633,
title = "Live 3D shape reconstruction, recognition and registration",
abstract = "We present a video-based system which interactively captures the geometry of a 3D object in the form of a point cloud, then recognizes and registers known objects in this point cloud in a matter of seconds (fig. 1). In order to achieve interactive speed, we exploit both efficient inference algorithms and parallel computation, often on a GPU. The system can be broken down into two distinct phases: geometry capture, and object inference. We now discuss these in further detail.",
author = "Carlos Hern{\'a}ndez and Frank Perbet and Minh-Tri Pham and George Vogiatzis and Woodford, {Oliver J.} and Atsuto Maki and Bj{\"o}rn Stenger and Roberto Cipolla",
year = "2011",
doi = "10.1109/ICCVW.2011.6130324",
language = "English",
isbn = "978-1-4673-0062-9",
pages = "729",
booktitle = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "IEEE",
address = "United States",

}

Hernández, C, Perbet, F, Pham, M-T, Vogiatzis, G, Woodford, OJ, Maki, A, Stenger, B & Cipolla, R 2011, Live 3D shape reconstruction, recognition and registration. in Proceedings of the IEEE International Conference on Computer Vision. IEEE, pp. 729, IEEE International Conference on Computer Vision Workshops, Barcelona, Spain, 6/11/11. https://doi.org/10.1109/ICCVW.2011.6130324

Live 3D shape reconstruction, recognition and registration. / Hernández, Carlos; Perbet, Frank; Pham, Minh-Tri; Vogiatzis, George; Woodford, Oliver J.; Maki, Atsuto; Stenger, Björn; Cipolla, Roberto.

Proceedings of the IEEE International Conference on Computer Vision. IEEE, 2011. p. 729.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Live 3D shape reconstruction, recognition and registration

AU - Hernández, Carlos

AU - Perbet, Frank

AU - Pham, Minh-Tri

AU - Vogiatzis, George

AU - Woodford, Oliver J.

AU - Maki, Atsuto

AU - Stenger, Björn

AU - Cipolla, Roberto

PY - 2011

Y1 - 2011

N2 - We present a video-based system which interactively captures the geometry of a 3D object in the form of a point cloud, then recognizes and registers known objects in this point cloud in a matter of seconds (fig. 1). In order to achieve interactive speed, we exploit both efficient inference algorithms and parallel computation, often on a GPU. The system can be broken down into two distinct phases: geometry capture, and object inference. We now discuss these in further detail.

AB - We present a video-based system which interactively captures the geometry of a 3D object in the form of a point cloud, then recognizes and registers known objects in this point cloud in a matter of seconds (fig. 1). In order to achieve interactive speed, we exploit both efficient inference algorithms and parallel computation, often on a GPU. The system can be broken down into two distinct phases: geometry capture, and object inference. We now discuss these in further detail.

UR - http://www.scopus.com/inward/record.url?scp=84856632972&partnerID=8YFLogxK

UR - http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6130324

U2 - 10.1109/ICCVW.2011.6130324

DO - 10.1109/ICCVW.2011.6130324

M3 - Conference contribution

AN - SCOPUS:84856632972

SN - 978-1-4673-0062-9

SP - 729

BT - Proceedings of the IEEE International Conference on Computer Vision

PB - IEEE

ER -

Hernández C, Perbet F, Pham M-T, Vogiatzis G, Woodford OJ, Maki A et al. Live 3D shape reconstruction, recognition and registration. In Proceedings of the IEEE International Conference on Computer Vision. IEEE. 2011. p. 729 https://doi.org/10.1109/ICCVW.2011.6130324