Improving motion and orientation estimation using an equilibrated total least squares approach

This paper outlines the ubiquitous presence of generalized orientation (or subspace) estimationproblems in image analysis. We show the potential sources of bias in naive approaches to directional estimation problems, discuss countermeasures against this bias, and point out the direct relation to the Total Least Squares problem. An improved method (`equilibration') for a precise direct estimation of moving planes (8 parameter motion model) concludes this paper.

• Type: Conference
• Year: 2001
• Where: ICIP
• Authors: Matthias Mühlich, Rudolf Mester
• Keywords: Directional Estimation Problems, ICIP 2001, Image Processing, Precise Direct Estimation, Total Least Squares