Abstract | ||
---|---|---|
An algorithm is introduced for video object tracking and segmentation that automatically detects local deformations of a video object and adjusts the object contour to match the real object boundary without breaking the object into several pieces during tracking. An edge energy change ratio is defined for local deformation detection. The corresponding contour segment is then adjusted to the real object boundary based on a local affine correction. Incorporating this method into VSnakes, our general algorithm for video object tracking, resulted in improved performance. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1109/ICIP.2002.1040057 | ICIP (2) |
Keywords | Field | DocType |
video signal processing,vsnakes,video object tracking,local affine correction,image segmentation,segmentation,object boundary,contour segment,edge detection,tracking,local deformations,edge energy change ratio,object contour,radiology,generic algorithm,sun,biomedical engineering | Affine transformation,Object detection,Computer vision,3D single-object recognition,Pattern recognition,Segmentation,Edge detection,Computer science,Image segmentation,Video tracking,Artificial intelligence,Deformation (mechanics) | Conference |
Volume | ISSN | Citations |
2 | 1522-4880 | 1 |
PageRank | References | Authors |
0.38 | 2 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shijun Sun | 1 | 88 | 7.91 |
David R Haynor | 2 | 993 | 118.76 |
Yongmin Kim | 3 | 53 | 5.43 |