Abstract | ||
---|---|---|
Tracking of spatially extended targets with variable shape, pose and appearance is a highly challenging task. In this work we propose a novel tracking approach using an incrementally generated part-based description to obtain a specific representation of target structure. The hierarchical part-based representation is learned in a generative manner from a large set of simple local features. The spatial and temporal density of observed part combinations is estimated by performing statistics over temporally aggregated data. Detected stable combinations consisting of multiple simpler parts encompass local, specific structures, which can efficiently guide a spatio-temporal association step of coherently moving image regions, which are part of the same target. The concept of our approach is proved and evaluated in several experiments. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-540-89689-0_48 | SSPR/SPR |
Keywords | Field | DocType |
target structure,multiple simpler part,spatially extended target,part-based description,specific structure,specific representation,hierarchical representation,observed part combination,hierarchical part-based representation,novel tracking approach,simple local feature,tracking,spatial statistics | Spatial analysis,Computer vision,Pattern recognition,Artificial intelligence,Generative grammar,Mathematics | Conference |
Volume | ISSN | Citations |
5342 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 13 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nicole M. Artner | 1 | 78 | 9.04 |
Salvador B. Mármol | 2 | 3 | 0.75 |
Csaba Beleznai | 3 | 367 | 18.96 |
Walter G. Kropatsch | 4 | 896 | 152.91 |