Learning the Shape of Image Moments for Optimal 3D Structure Estimation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2015

Learning the Shape of Image Moments for Optimal 3D Structure Estimation

Abstract

— The selection of a suitable set of visual features for an optimal performance of closed-loop visual control or Structure from Motion (SfM) schemes is still an open problem in the visual servoing community. For instance, when considering integral region-based features such as image moments, only heuristic, partial, or local results are currently available for guiding the selection of an appropriate moment set. The goal of this paper is to propose a novel learning strategy able to automatically optimize online the shape of a given class of image moments as a function of the observed scene for improving the SfM performance in estimating the scene structure. As case study, the problem of recovering the (unknown) 3D parameters of a planar scene from measured moments and known camera motion is considered. The reported simulation results fully confirm the soundness of the approach and its superior performance over more consolidated solutions in increasing the information gain during the estimation task.
Fichier principal
Vignette du fichier
2015_icra_robuffo.pdf (1.16 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01121630 , version 1 (02-03-2015)

Identifiers

  • HAL Id : hal-01121630 , version 1

Cite

Paolo Robuffo Giordano, Riccardo Spica, François Chaumette. Learning the Shape of Image Moments for Optimal 3D Structure Estimation. IEEE Int. Conf. on Robotics and Automation, ICRA'15, May 2015, Seattle, United States. ⟨hal-01121630⟩
353 View
208 Download

Share

Gmail Facebook X LinkedIn More