Asymetric Gradient-based image alignement

Abstract : A new method for templet-based image alignement is presented in this paper. A gradient-based optimization of motion compensated error difference is addressed to solve the image alignement problem. Its novelty lies in the minimized error, which consider the bi-directional compensation of the reference template and the current image onto each other in a constrained asymmetrical fashion. The proposed approach is shown to be a generalization of previous state-of-the art gradient-based methods. An experimental evaluation is provided to show how the new method outperforms the former in presence of noisy images, and to give some insights into its properties.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00399614
Contributor : Yannick Berthoumieu <>
Submitted on : Saturday, June 27, 2009 - 8:56:20 AM
Last modification on : Wednesday, January 31, 2018 - 1:46:02 PM

Identifiers

Citation

Jean-Baptiste Authesserre, Rémi Mégret, Yannick Berthoumieu. Asymetric Gradient-based image alignement. ICASSP IEEE, Apr 2009, Taipei, Taiwan. pp.981-984, ⟨10.1109/ICASSP.2009.4959750⟩. ⟨hal-00399614⟩

Share

Metrics

Record views

162