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

doi:10.1109/ICCVW.2011.6130324

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

Computer Science Research Group

Research output: Chapter in Book/Published conference output › Conference publication

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 language	English
Title of host publication	Proceedings of the IEEE International Conference on Computer Vision
Publisher	IEEE
Pages	729
Number of pages	1
ISBN (Print)	978-1-4673-0062-9
DOIs	https://doi.org/10.1109/ICCVW.2011.6130324
Publication status	Published - 2011
Event	IEEE International Conference on Computer Vision Workshops - Barcelona, Spain Duration: 6 Nov 2011 → 13 Nov 2011

Conference

Conference	IEEE International Conference on Computer Vision Workshops
Abbreviated title	ICCV Workshops
Country/Territory	Spain
City	Barcelona
Period	6/11/11 → 13/11/11

Access to Document

10.1109/ICCVW.2011.6130324

Cite this

@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",

note = "IEEE International Conference on Computer Vision Workshops, ICCV Workshops ; Conference date: 06-11-2011 Through 13-11-2011",

}

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

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 publication

AN - SCOPUS:84856632972

SN - 978-1-4673-0062-9

SP - 729

BT - Proceedings of the IEEE International Conference on Computer Vision

PB - IEEE

T2 - IEEE International Conference on Computer Vision Workshops

Y2 - 6 November 2011 through 13 November 2011

ER -

Live 3D shape reconstruction, recognition and registration

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this