Abstract | ||
---|---|---|
Many vision problems require computing fast template motion in dynamic scenes. These problems can be formulated as exploration problems and thus can be expressed as a search into a state space based representation approach. However, these problems are hard to solve because they involve search through a high dimensional space. In this paper, we propose a heuristic algorithm through the space of transformations for computing target 2D motion. Three features are combined in order to compute efficient motion: (1) a quality of function match based on a holistic similarity measurement, (2) Kullback-Leibler measure as heuristic to guide the search process and (3) incorporation of target dynamics into the search process for computing the most promising search alternatives. The paper includes experimental evaluations that illustrate the efficiency and suitability for real-time vision based tasks. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1007/11558484_69 | ACIVS |
Keywords | Field | DocType |
real-time vision,promising search alternative,video stream,target dynamic,state space,high dimensional space,search process,efficient motion,heuristic algorithm,vision problem,template motion,kullback leibler | Computer vision,Incremental heuristic search,Heuristic,Min-conflicts algorithm,Computer science,Heuristic (computer science),Beam search,Artificial intelligence,High dimensional space,State space,Best-first search | Conference |
Volume | ISSN | ISBN |
3708 | 0302-9743 | 3-540-29032-X |
Citations | PageRank | References |
0 | 0.34 | 3 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Elena Sánchez-nielsen | 1 | 38 | 10.64 |
Mario Hernández-tejera | 2 | 28 | 6.32 |