Abstract | ||
---|---|---|
In this paper, we present a tracking initialization method that combines a rough extraction of moving objects and a refined segmentation of their contours. The extraction of moving objects is obtained with a classical global motion compensation. To obtain accurate contours of the objects, a spatial segmentation is performed with an original localized graph pyramid that focuses the segmentation process either on the object areas or on their borders. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1109/ICPR.2004.592 | ICPR (4) |
Keywords | Field | DocType |
localized pyramid,object extraction,rough extraction,spatial segmentation,object area,tracking initialization method,classical global motion compensation,segmentation process,original localized graph pyramid,accurate contour,refined segmentation,image segmentation,feature extraction,motion compensation,tracking | Computer vision,Scale-space segmentation,Pattern recognition,Segmentation,Computer science,Motion compensation,Segmentation-based object categorization,Feature extraction,Image segmentation,Artificial intelligence,Pyramid,Initialization | Conference |
ISSN | ISBN | Citations |
1051-4651 | 0-7695-2128-2 | 2 |
PageRank | References | Authors |
0.44 | 3 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jeremy Huart | 1 | 2 | 0.44 |
Guillaume Foret | 2 | 5 | 1.01 |
P. Bertolino | 3 | 48 | 8.45 |