nextuppreviouscontents
Next:Content-based Image Retrieval Up:Computer Vision Previous:Interactive Model Recognition from

Pose Estimation: Known Objects in Unstructured Environments

F. Callari, G. Soucy, F.P. Ferrie (McGill), D. Baird, D. Lamb (Hymarc Ltd.)

This project focuses on investigating methods for pose and point estimation (PPE) on complex, rigid, known, non-cooperative 3-D objects from range images. The ``point'' estimation issue is remarked and studied alongside the ``pose'' estimation one (in itself a classic problem of computer vision), in that it is the goal of the project to build a system able to make confident assertions about the position in 3-D space of particular ``relevant'' points on the objects at hand. This goal stems from one possible application of this research, namely manipulation and docking operations of space station structures in space. Our proposed solution is a Bayesian inference scheme, based on several layers of information processing. Starting from range images of the objects, a chain of shape analysis processes produces first a segmentation of large, reliable features on the objects, whose shape is modelled by geometric primitives (superellipsoids in the proposed test-bed solution). The shape parameters are used for part recognition (via a Bayesian discriminative classifier) and for placing ``landmark'' points upon the parts themselves. Eventually, the landmarks are used to estimate the target point position. Uncertainty in the modelization process is carried along, and expressed in the form of posterior probability distributions about the target. This effectively quantifies the confidence degree in the estimation. Extensive tests of the above sketched technique on test objects have given promising results about the practical feasibility of the proposed methodology. More details are available on line:
http://www.cim.mcgill.ca/~ apl/Papers/callari-landmark-identification.ps.gz
 


Annual Report

Fri Nov 26 23:00:32 GMT 1999