Qualitative Multi-Scale Feature Hierarchies for Object Tracking
2000 (English)In: Journal of Visual Communication and Image Representation, ISSN 1047-3203, E-ISSN 1095-9076, Vol. 11, 115-129 p.Article in journal (Refereed) Published
This 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.
Place, publisher, year, edition, pages
Elsevier, 2000. Vol. 11, 115-129 p.
object representation, tracking, feature detection, scale selection, motion, matching, shape analysis, applications, scale-space, multi-scale representation, computer vision
Computer Vision and Robotics (Autonomous Systems) Computer Science
IdentifiersURN: urn:nbn:se:kth:diva-40147DOI: 10.1006/jvci.1999.0438OAI: oai:DiVA.org:kth-40147DiVA: diva2:465689
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. QC 201112152011-12-152011-09-132013-04-24Bibliographically approved