Point and line feature-based observer design on SL(3) for Homography estimation and its application to image stabilization - Archive ouverte HAL Access content directly
Reports (Research Report) Year : 2017

Point and line feature-based observer design on SL(3) for Homography estimation and its application to image stabilization

Abstract

This paper presents a new algorithm for online estimation of a sequence of homographies applicable to image sequences obtained from robotic vehicles equipped with a monocular camera. The approach taken exploits the underlying Special Linear group SL(3) structure of the set of homographies along with gyrometer measurements and direct point-and line-feature correspondences between images to develop temporal filter for the homography estimate. Theoretical analysis and experimental results are provided to demonstrate the robustness of the proposed algorithm. The experimental results show excellent performance even in the case of very fast camera motion (relative to frame rate), and in presence of severe occlusion, specular reflection, image blur, and light saturation.
Fichier principal
Vignette du fichier
Rapport.pdf (4.41 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01628175 , version 1 (02-11-2017)
hal-01628175 , version 2 (21-09-2018)

Identifiers

  • HAL Id : hal-01628175 , version 2

Cite

Minh-Duc Hua, Jochen Trumpf, Tarek Hamel, Robert Mahony, Pascal Morin. Point and line feature-based observer design on SL(3) for Homography estimation and its application to image stabilization. [Research Report] I3S, Université Côte d'Azur; CNRS, University of Nice Sophia Antipolis, I3S, UMR 7271, COATI, Inria, 06900 Sophia Antipolis, France. 2017. ⟨hal-01628175v2⟩
508 View
460 Download

Share

Gmail Facebook X LinkedIn More