Name
Abstract | ||
|---|---|---|
This paper proposes a new density matching method based on background mismatching for tracking of nonrigid moving objects. The new tracking method extends the idea behind the original density-matching tracker, which tracks an object by finding a contour in which the photometric density sampled from the enclosed region most closely matches a model density. This method can be quite sensitive to the initial curve placements and model density. The new method eliminates these sensitivities by adding a second term to the optimization: The mismatch between the model density and the density sampled from the background. By maximizing this term, the tracking algorithm becomes significantly more robust in practice. Furthermore, we show the enhanced ability of the algorithm to deal with target objects which possess smooth or diffuse boundaries. The tracker is in the form of a partial differential equation, and is implemented using the level-set framework. Experiments on synthesized images and real video sequences show our proposed methods are effective and robust; the results are compared with several existing methods. |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1109/TPAMI.2005.31 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
optimisation,statistical distributions,image matching,video sequences,tracking algorithm,background mismatch,improving performance,new density,model density,photometric density sampling,background mismatching,density matching method,index terms- active contours,photometric density,nonrigid moving object tracking,partial differential equation,diffuse boundary,existing method,optimization,tracking,image sequences,pdes.,object detection,original density-matching tracker,partial differential equations,density matching,level set methods,distribution tracking,index terms—active contours,level set method,new method,new tracking method,level set,probability distribution,indexing terms,active contour | Active contour model,Computer vision,Object detection,Pattern recognition,Image matching,Level set method,Computer science,Photometry (optics),Probability distribution,Artificial intelligence,Partial differential equation,Image sequence | Journal |
Volume | Issue | ISSN |
27 | 2 | 0162-8828 |
Citations | PageRank | References |
36 | 1.74 | 18 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Tao Zhang | 1 | 38 | 2.10 |
| Daniel Freedman | 2 | 517 | 27.79 |