Talks and Poster Presentations (with Proceedings-Entry):
M. Ayromlou, M. Vincze, W. Ponweiser:
"Probabilistic Matching of Image- to Model-Features for Real-time Object Tracking";
Poster: IEEE 16th International Conference on Pattern Recognition (ICPR) 2002,
Quebec , Canada;
2002-08-11
- 2002-08-15; in: "Proceedings of ICPR '02, Vol. III",
(2002).
English abstract:
Background clutter produces a difficult problem for edge
matching within model-based object tracking approaches. The
solution of matching all possible candidate image features with
the model features is computationally infeasible for real-time
tracking. It is proposed to draw probabilistic samples of candidate
sets based on measures for local topological constraints.
Line features are constraint by parallel and junction constraints.
Continuous measures are used for evaluation of the match of
the features sets to avoid thresholds. This approach limits the
number of matchings and processing time increases linearly with
the number of features. Experiments show the correct selection
among multiple candidates for different scenarios.
Electronic version of the publication:
http://www.infa.tuwien.ac.at/groups/robtec/Veroeff/1267_ayromlou_m.pdf
Created from the Publication Database of the Vienna University of Technology.