Pose Error Correction For Visual Features Prediction

Nicolas Cazy 1 Claire Dune 2 Pierre-Brice Wieber 3, * Paolo Robuffo Giordano 1 François Chaumette 1
* Corresponding author
1 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
3 BIPOP - Modelling, Simulation, Control and Optimization of Non-Smooth Dynamical Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Predicting the behavior of visual features on the image plane over a future time horizon is an important possibility in many different control problems. For example when dealing with occlusions (or other constraints such as joint limits) in a classical visual servoing loop, or also in the more advanced model predictive control schemes recently proposed in the literature. Several possibilities have been proposed to perform the initial correction step for then propagating the visual features by exploiting the measurements currently available by the camera. But the predictions proposed so far are inaccurate in situations where the depths of the tracked points are not correctly estimated. We then propose in this paper a new correction strategy which tries to directly correct the relative pose between the camera and the target instead of only adjusting the error on the image plane. This correction is then analysed and compared by evaluating the corresponding improvements in the feature prediction phase.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/hal-01010772
Contributor : Eric Marchand <>
Submitted on : Friday, June 20, 2014 - 2:42:43 PM
Last modification on : Thursday, February 7, 2019 - 5:28:38 PM
Document(s) archivé(s) le : Saturday, September 20, 2014 - 11:00:12 AM

File

main.pdf
Files produced by the author(s)

Identifiers

Citation

Nicolas Cazy, Claire Dune, Pierre-Brice Wieber, Paolo Robuffo Giordano, François Chaumette. Pose Error Correction For Visual Features Prediction. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, IROS'14, Sep 2014, Chicago, United States. pp.791-796, ⟨10.1109/IROS.2014.6942649⟩. ⟨hal-01010772⟩

Share

Metrics

Record views

1477

Files downloads

267