A Resource Allocation Framework for Adaptive Selection of Point Matching Strategies
(2013) Advanced Concepts for Intelligent Vision Systems — Location: Poznan, Poland (28.October.2013)
Files
Details
- Authors
- Abstract
- This paper investigates how to track an object based on the matching of points between pairs of consecutive video frames. The approach is especially relevant to support object tracking in close-view video shots, as for example encountered in the context of the Pan-Tilt- Zoom (PTZ) camera autotracking problem. In contrast to many earlier related works, we consider that the matching metric of a point should be adapted to the signal observed in its spatial neighborhood, and in- troduce a cost-benet framework to control this adaptation with respect to the global target displacement estimation objective. Hence, the pro- posed framework explicitly handles the trade-o between the point-level matching metric complexity, and the contribution brought by this metric to solve the target tracking problem. As a consequence, and in contrast with the common assumption that only specic points of interest should be investigated, our framework does not make any a priori assumption about the points that should be considered or ignored by the tracking process. Instead, it states that any point might help in the target dis- placement estimation, provided that the matching metric is well adapted. Measuring the contribution reliability of a point as the probability that it leads to a crorrect matching decision, we are able to dene a global successful target matching criterion. It is then possible to minimize the probability of incorrect matching over the set of possible (point,metric) combinations and to nd the optimal aggregation strategy. Our prelimi- nary results demonstrate both the eectiveness and the efficiency of our approach.
- Affiliations
Citations
De Neyer, Q., & De Vleeschouwer, C. (2013). A Resource Allocation Framework for Adaptive Selection of Point Matching Strategies. Lecture Notes in Computer Science, Vol. 8192. Published. Advanced Concepts for Intelligent Vision Systems, Poznan, Poland. https://doi.org/10.1007/978-3-319-02895-8_33