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

Tekalp, A.M.; Beek, Peter van der; Toklu, C.; Günsel, Bilge

doi:10.1109/5.687828

Cited by 77 publications

(34 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Unclassified

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%

Rigid Part Decomposition in a Graph Pyramid

Artner

Ion

Kropatsch

2009

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

Abstract. This paper presents an approach to extract the rigid parts of an observed articulated object. First, a spatio-temporal filtering in a video selects interest points that correspond to rigid parts. This selection is driven by the spatial relationships and the movement of the interest points. Then, a graph pyramid is built, guided by the orientation changes of the object parts in the scene. This leads to a decomposition of the scene into its rigid parts. Each vertex in the top level of the pyramid represents one rigid part in the scene.

show abstract

Section: Introductionmentioning

confidence: 99%

Rigid Part Decomposition in a Graph Pyramid

Artner

Ion

Kropatsch

2009

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

show abstract

“…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%

Mesh-Based Video Coding For Low Bit-rate Communications

Kocharoen

Ahmed

Rajatheva

et al. 2006

IEEE Trans. Consumer Electron.

View full text Add to dashboard Cite

show abstract

“…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%

Face and 2-D mesh animation in MPEG-4

Tekalp

Östermann

2000

Signal Processing: Image Communication

147

View full text Add to dashboard Cite

This paper presents an overview of some of the synthetic visual objects supported by MPEG-4 version-1, namely animated faces and animated arbitrary 2-D uniform and Delaunay meshes. We discuss both specification and compression of face animation and 2D-mesh animation in MPEG-4. Face animation allows to animate a proprietary face model or a face model downloaded to the decoder. We also address integration of the face animation tool with the text-to-speech interface (TTSI), so that face animation can be driven by text input. IntroductionMPEG-4 is an object-based multimedia compression standard, which allows for encoding of different audiovisual objects (AVO) in the scene independently. The visual objects may have natural or synthetic content, including arbitrary shape video objects, special synthetic objects such as human face and body, and generic 2-D/3-D objects composed of primitives like rectangles, spheres, or indexed face sets, which define an object surface by means of vertices and surface patches. The synthetic visual objects are animated by transforms and special purpose animation techniques, such as face/body animation and 2D-mesh animation. MPEG-4 also provides synthetic audio tools such as structured audio tools and a text-to-speech interface (TTSI). This paper presents a detailed overview of synthetic visual objects supported by MPEG-4 version-1, namely animated faces and animated arbitrary 2-D uniform and Delaunay meshes. We also address integration of the face animation tool with the TTSI, so that face animation can be driven by text input. Body animation and 3-D mesh compression and animation will be supported in MPEG-4 version-2, and hence are not covered in this article.The representation of synthetic visual objects in MPEG-4 is based on the prior VRML standard [13][12][11] using nodes such as Transform, which defines rotation, scale or translation of an object, and IndexedFaceSet describing 3-D shape of an object by an indexed face set. However, MPEG-4 is the first international standard that specifies a compressed binary representation of animated synthetic audio-visual objects. It is important to note that MPEG-4 only specifies the decoding of compliant bit streams in an MPEG-4 terminal. The encoders do enjoy a large degree of freedom in how to generate MPEG-4 compliant bit streams. Decoded audio-visual objects can be composed into 2D and 3D scenes using the Binary Format for Scenes (BIFS) [13], which also allows implementation of animation of objects and their properties using the BIFS-Anim node. We recommend readers to refer to an accompanying article on BIFS for the details of implementation of BIFS-Anim. Compression of still textures (images) for mapping onto 2D or 3D meshes is also covered in another accompanying article. In the following, we cover the specification and compression of face animation and 2D-mesh animation in Sections 2 and 3, respectively. Face AnimationMPEG-4 foresees that talking heads will serve an important role in future customer service applications. For examp...

show abstract

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

Cited by 77 publications

References 46 publications

Rigid Part Decomposition in a Graph Pyramid

Rigid Part Decomposition in a Graph Pyramid

Mesh-Based Video Coding For Low Bit-rate Communications

Face and 2-D mesh animation in MPEG-4

Contact Info

Product

Resources

About