Qualitative Multi-Scale Feature Hierarchies for Object TrackingLars Bretzner and Tony LindebergJournal of Visual Communication and Image Representation, 11, 115-129, 2000.Technical report ISRN KTH/NA/P--99/09--SE Earlier version presented in M. Nielsen, P. Johansen, O. F. Olsen and J. Weickert (eds.) Proc. 2nd International Conference on Scale-Space Theories in Computer Vision, (Corfu, Greece), September 26-27, 1999. Springer Lecture Notes in Computer Science, vol 1682, pp. 117--128. AbstractThis paper shows how the performance of feature trackers can be improved by building a view-based object representation consisting of qualitative relations between image structures at different scales. The idea is to track all image features individually, and to use the qualitative feature relations for resolving ambiguous matches and for introducing feature hypotheses whenever image features are mismatched or lost. Compared to more traditional work on view-based object tracking, this methodology has the ability to handle semi-rigid objects and partial occlusions. Compared to trackers based on three-dimensional object models, this approach is much simpler and of a more generic nature. A hands-on example is presented showing how an integrated application system can be constructed from conceptually very simple operations.Keywords: object representation, tracking, feature detection, scale selection, motion, matching, shape analysis, applications, scale-space, multi-scale representation, computer vision PDF: (320 kb) Background and related material: (The feature tracker with automatic scale selection that this work builds upon) (Geometric framework underlying the 3-D hand mouse) (General scale selection principle for feature detection) (Review paper on principles for automatic scale selection) (Monograph on scale-space theory)
Responsible for this page:
Tony Lindeberg
|