Using multiple hypothesis in model-based tracking

Céline Teulière 1, 2 E. Marchand 2 Laurent Eck 1
2 Lagadic - Visual servoing in robotics, computer vision, and augmented reality
CRISAM - Inria Sophia Antipolis - Méditerranée , Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : Classic registration methods for model-based tracking try to align the projected edges of a 3D model with the edges of the image. However, wrong matches at low level can make these methods fail. This paper presents a new approach allowing to retrieve multiple hypothesis on the camera pose from multiple low-level hypothesis. These hypothesis are integrated into a particle filtering framework to guide the particle set toward the peaks of the distribution. Experiments on simulated and real video sequences show the improvement in robustness of the resulting tracker.
Keywords : tracking
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [16 references]  Display  Hide  Download

https://hal.inria.fr/inria-00544795
Contributor : Eric Marchand <>
Submitted on : Thursday, December 9, 2010 - 12:18:59 AM
Last modification on : Thursday, February 7, 2019 - 2:37:06 PM
Document(s) archivé(s) le : Thursday, March 10, 2011 - 1:08:42 PM

File

2010_icra_teuliere.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00544795, version 1

Citation

Céline Teulière, E. Marchand, Laurent Eck. Using multiple hypothesis in model-based tracking. IEEE Int. Conf. on Robotics and Automation, ICRA'10, 2010, Anchorage, Alaska, United States. pp.4559-4565. ⟨inria-00544795⟩

Share

Metrics

Record views

369

Files downloads

196