Robust Estimation of Camera Rotation, Translation and Focal Length at High Outlier Rates

  • Authors:
  • Affiliations:
  • Venue:
  • CRV '04 Proceedings of the 1st Canadian Conference on Computer and Robot Vision
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

A new approach for robust estimation of camera rotation,translation and focal length at high outlier ratesfrom feature correspondences between two perspectiveviews is introduced. Many computer vision algorithmsuse RANSAC based methods to achieve robustness. One disadvantageof these methods is the required computational effortat high outlier rates. The proposed approach is based ona new evolutionary global optimization method called RepulsiveParticle Swarm Optimization (RPSO). It is shownthat the proposed approach requires less computational effortat high outlier rates compared to RANSAC based robustestimation.