Abstract | ||
---|---|---|
This paper describes an approach for generating binary partition tree [P. Salembier and L. Garrido, 2000] representations and video object segmentations using a novel region merging strategy based on motion similarity measures of multiple frames of an image sequence. The system operates over color-homogeneous regions, tracked across frames of a shot, representing an over-segmentation of the objects. A long-term motion similarity measure is introduced for region merging, offering accurate segmentation of objects and extending temporal consistency between the tracked partitions to hierarchical representations of every frame within the shot. Experimental results are presented, illustrating the usefulness of the approach. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/ICIP.2005.1530084 | Image Processing, 2005. ICIP 2005. IEEE International Conference |
Keywords | Field | DocType |
image colour analysis,image motion analysis,image representation,image segmentation,video signal processing,color-homogeneous regions,image sequence,motion similarity measure,motion-based binary partition tree approach,region merging strategy,video object segmentation | Computer vision,Scale-space segmentation,Motion field,Similarity measure,Pattern recognition,Range segmentation,Computer science,Segmentation-based object categorization,Image segmentation,Artificial intelligence,Motion estimation,Minimum spanning tree-based segmentation | Conference |
Volume | ISSN | ISBN |
2 | 1522-4880 | 0-7803-9134-9 |
Citations | PageRank | References |
4 | 0.52 | 8 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Camilo C. Dorea | 1 | 95 | 10.02 |
Montse Pardàs | 2 | 343 | 35.03 |
Ferran Marqués | 3 | 738 | 67.44 |