Model-Guided Grouping for 3-D Motion Tracking

The objective of this paper is to develop a robust solution to the correspondence problem in model-based motion tracking even when the frame-to-frame motion is relatively fast. A new approach called Model-Guided Grouping, which is used to derive intermediate-level structures as our matching tokens, is introduced. The groupings are guided and derived locally, with the contemporary use of model structures, around the predicted model during the object tracking. We choose junctions and parallel pairs as our matching tokens, thus the information coded in these structures is relatively invariant in consecutive frames. The matching strategy is coarse-to-fine, and partial matching will also be allowed when occlusions are present. The method for evaluation of probability of accidental match based on junction groupings will be discussed. Systematic testing shows that matches based on these new methods improve correspondence reliability by about an order of magnitude over previous method based on matching individual line segments.