1998
DOI: 10.1109/5.687828
|View full text |Cite
|
Sign up to set email alerts
|

Two-dimensional mesh-based visual-object representation for interactive synthetic/natural digital video

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
28
0
6

Year Published

1999
1999
2021
2021

Publication Types

Select...
5
4

Relationship

1
8

Authors

Journals

citations
Cited by 77 publications
(34 citation statements)
references
References 46 publications
0
28
0
6
Order By: Relevance
“…Tekalp et al [9] describe 2D mesh-based modeling of video objects as a compact representation of motion and shape for interactive video manipulation, compression, and indexing. Li et al [10] propose to use affine motion models to estimate the motion of homogeneous regions.…”
Section: Introductionmentioning
confidence: 99%
“…Tekalp et al [9] describe 2D mesh-based modeling of video objects as a compact representation of motion and shape for interactive video manipulation, compression, and indexing. Li et al [10] propose to use affine motion models to estimate the motion of homogeneous regions.…”
Section: Introductionmentioning
confidence: 99%
“…Over the last ten years, mesh-based coding schemes have achieved excellent results in image coding [1]- [9]. Meshbased coding of image deals with dividing the image domain into a total of M non-overlapping mesh elements and then using a two-dimensional interpolation to reconstruct the intensity over each element.…”
Section: Introductionmentioning
confidence: 99%
“…The commonly used motion estimation technique in all standard video codecs is the block matching algorithm (BMA) where an MxN pixels sized block of the reference frame is searched in the current frame by minimizing the mean square error (MSE) over all positions within the search range [12]. Tekalp [1], [10] introduced a mesh-based motion model which is used the polygonal patches, triangles or quadrangles, for inter-frame coding instead of block matching model. Mesh-based modeling can deform the polygon patches by the movements of the nodes from the current frame into the reference frame and the texture inside each patch is warped using the affine transform.…”
Section: Introductionmentioning
confidence: 99%
“…The procedure consists of three steps: i) Approximation of the VOP contour by a polygon through selection of N b boundary node points; ii) selection of N i interior node points; and iii) Delaunay triangulation to define the mesh topology. There are various methods for approximation of arbitrary shaped contours by polygons [33] [35]. Interior node points may be selected to coincide with high-gradient points or corner points within the VOP boundary [33].…”
Section: Mesh Design For Intra Mopsmentioning
confidence: 99%