Combining complementary edge, point and color cues in model-based tracking for highly dynamic scenes - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Combining complementary edge, point and color cues in model-based tracking for highly dynamic scenes

Abstract

This paper focuses on the issue of estimating the complete 3D pose of the camera with respect to a complex object, in a potentially highly dynamic scene, through model- based tracking. We propose to robustly combine complementary geometrical edge and point features with color based features in the minimization process. A Kalman filtering and pose pre- diction process is also suggested to handle potential large inter- frame motions. In order to deal with complex 3D models, our method takes advantage of hardware acceleration. Promising results, outperforming classical state-of-art approaches, have been obtained on various real and synthetic image sequences, with a focus on space robotics applications.
Fichier principal
Vignette du fichier
2014_icra_petit.pdf (591.33 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00949197 , version 1 (19-02-2014)

Identifiers

  • HAL Id : hal-00949197 , version 1

Cite

Antoine Petit, Eric Marchand, Keyvan Kanani. Combining complementary edge, point and color cues in model-based tracking for highly dynamic scenes. IEEE Int. Conf. on Robotics and Automation, ICRA'14, Jun 2014, Hong-Kong, Hong Kong SAR China. ⟨hal-00949197⟩
271 View
213 Download

Share

Gmail Facebook X LinkedIn More