Object-based video processing using forward-tracking 2-D mesh layers
First Claim
1. A method for mesh-based representation of the motion of different arbitrary shaped Video Objects, the method comprising the steps of:
- representing and processing each Video Object independently from other Video Objects with a given Alpha Plane of a Video Object Plane utilized in design of a mesh.
3 Assignments
0 Petitions
Accused Products
Abstract
The invented method involves the object-based processing of parts of video frames referred to as Video Object Planes using 2-D meshes, wherein the color and shape information associated with the Video Object Planes are assumed to be known at every frame and wherein each video object is processed independently. The invented method more particularly involves utilization of the Alpha Planes, which contain the shape information, in object-based design of an initial 2-D mesh, wherein an Alpha Plane is used to form a constraining polygonal mesh boundary, as well as in object-based tracking of mesh node points, wherein motion vectors of nodes on the mesh boundary are constrained so that these node points always lie along the Alpha Plane boundary, by means of restriction of the search space or back-projection, and mesh-based Video Object Plane mapping takes into account any differences between the mesh boundary and the Video Object Plane boundary. Such invented methods may be computer-implemented or computer-assisted, as by being coded as software within any coding system as memory-based instructions executed by a microprocessor, PC or mainframe computer, or may be implemented in hardware such as a state machine.
58 Citations
9 Claims
-
1. A method for mesh-based representation of the motion of different arbitrary shaped Video Objects, the method comprising the steps of:
representing and processing each Video Object independently from other Video Objects with a given Alpha Plane of a Video Object Plane utilized in design of a mesh.
-
2. A method for tracking the node points of an object-based mesh, the method comprising the steps of:
-
defining Video Object Plane boundaries by Alpha planes which are known at every frame; and constraining motion vectors of node points on a mesh boundary of the object-based mesh to lie along the Video Object Plane boundary at every frame.
-
-
3. An improved method for constraining mesh boundary nodes along a Video Object Plane boundary, the improvement comprising restricting search space for new node locations during motion vector estimation such that an order of the nodes along a polygonal mesh boundary is not allowed to change.
-
4. An improvement to video data compression methods for processing successive video frames to code video object plane shape, motion and texture where the processing includes block-based motion data processing, the improvements comprising:
- Replacing the existing block-based motion data processing by a layer of mesh-based motion data processing, wherein the mesh-based motion data processing is performed in accordance to mesh-based motion data processing criteria.
-
5. An improvement to video data compression methods for processing successive video frames to code video object plane shape, motion and texture where the processing includes block-based motion data processing, the improvement comprising:
- Adding a layer of mesh-based motion data processing to the existing block-based motion data processing, wherein the mesh-based motion data processing is performed in accordance to mesh-based motion data processing criteria; and
the block-based motion data processing is performed in accordance to block-based motion data processing criteria.
- Adding a layer of mesh-based motion data processing to the existing block-based motion data processing, wherein the mesh-based motion data processing is performed in accordance to mesh-based motion data processing criteria; and
-
6. A method for tracking of the node points along Video Object Plane boundaries for a case I, the method comprising the steps of:
-
assuming the Video Object Plane boundaries to be known at every frame; and constraining motion vectors of nodes along a boundary to lie along a same Video Object Plane boundary at a next frame by restricting search space.
-
-
7. In connection with a video coding method for tracking node points of a video object plane along the video object plane boundaries known at every frame, the improvement comprising:
constraining the motion vectors of nodes along the boundary to lie along the same video object plane boundary at the next frame, thereby restricting the search space in a predefined way. - View Dependent Claims (8)
-
9. An improvement to data compression methods for processing successive video frames to code video object plane motion and texture where the processing includes block-based motion data processing, the improvement comprising:
-
adding a layer of mesh-based motion data processing to the existing block-based motion data processing, wherein the mesh-based motion data processing distinguishes between a first case I whereby at least one video object plane is defined by chroma-key sequences; processing mesh-based motion data in accordance with mesh-based motion data processing criteria; and processing block-based motion data in accordance with predefined block-based motion data processing criteria.
-
Specification