A COMPARATIVE-STUDY OF THE ROBUSTNESS OF 2 POSE ESTIMATION TECHNIQUES

The paper presents an analysis of the stability of pose estimation. St ability is defined as sensitivity of the pose parameters towards noise in image features used for estimating pose. The specific emphasis of the analysis is on determining how the stability varies with viewpoint relative to an object and to understand the relationships between obj ect geometry, viewpoint, and pose stability. Two pose estimation techn iques are investigated. One uses a numerical scheme for finding pose p arameters; the other is based on closed form solutions. Both are ''pos e from trihedral vertices'' techniques, which provide the rotation par t of object pose based on orientations of three edge segments. The ana lysis is based on generalized sensitivity analysis propagating the unc ertainty in edge segment orientations to the resulting effect on the p ose parameters. It is shown that there is a precomputable, generic rel ationship between viewpoint and pose stability, and that there is a dr astic difference in stability over the range of viewpoints. This viewp oint variation is shared by the two investigated techniques. Additiona lly, the paper offers an explicit way to determine the most robust vie wpoints directly for any given vertex model. Experiments on real image s show that the results of the work can be used to compute the varianc e in pose parameters for any given pose. For the predicted instable vi ewpoints the variance in pose parameters is on the order of 20 (degree s squared), whereas the variance for robust viewpoints is on the order of 0.05 (degrees squared), i.e., two orders of magnitude difference.