Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Head shoulder image reconstruction method based on model and object in low bit rate video call

A video call, low bit rate technology, applied in the field of video transmission, can solve problems such as the difficulty of 2D grid compatibility

Active Publication Date: 2015-11-11
TSINGHUA UNIV
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The 3D face model improves the reconstruction quality of the face area, but it is difficult to be compatible with the 2D grid, and the model also needs to be defined and initialized
Additionally, a coarse mesh cannot provide a satisfactory texture reconstruction without constantly updating the texture, causing the system to require a higher bitrate to transmit the image

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Head shoulder image reconstruction method based on model and object in low bit rate video call
  • Head shoulder image reconstruction method based on model and object in low bit rate video call
  • Head shoulder image reconstruction method based on model and object in low bit rate video call

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] A coding method based on models and objects in a low-bit-rate video call, characterized in that it includes: an active appearance AAM model training module, a head-and-shoulders grid initialization module, a low-bit-rate encoding transmission module and a decoding and restoring original video frame module, wherein :

[0068] The active appearance AAM model training module, its input information is a section of face video, and the output end is a low bit rate encoding module;

[0069] The head and shoulders grid initialization module, its input information is the first frame of the video, and the output end is a low bit rate encoding module;

[0070] Low bit rate encoding module, its input is the video frame of the sending end, the active appearance AAM model and grid initialization, the output terminal is connected to the channel, and the output is the active appearance AAM model parameters generated by the active appearance AAM model, which are generated by grid tracki...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a head shoulder image reconstruction method based on a model and an object in a low bit rate video call. The method is characterized in that with the combination of advantages of object-based coding and model-based coding, a low bit rate model-and-object-based hybrid coding method is provided; the method performs 2D deformable model automatic training of a face region and then coding; for a head shoulder region, a 2D grid formed based on a Delaunay algorithm is adopted, grid iteration is used to well match with a head image; then the image is subjected to JPEG2000 compression to obtain object texture, and an object grid and the object texture are sent to a reception end through a channel and then coding is shared. The method has the high coding efficiency via the grid segmentation and texture compression and achieves good user experience. According to the invention, transmission of head shoulder videos in the low bit rate is achieved, the experience effect after video image reconstruction is still good, and the utilization efficiency of communication resources improved.

Description

technical field [0001] The invention relates to the field of video transmission, in particular to an image reconstruction method for the head and shoulders part of human face video in multimedia communication under the condition of low bit rate. Combining the advantages of both object-based coding and model-based coding, a low-bit-rate hybrid coding method based on both object and model (Model-and-Object-based Coding, MOBC) is proposed, which realizes head-and-shoulder video in low-bit-rate Transmission, after reconstructing the video image, there is still a good experience effect, thereby improving the utilization of communication resources. Background technique [0002] In recent years, data flow based on multimedia services in wireless networks has increased rapidly, and multimedia communication applications such as video calls and video conferences have appeared in a large number of mobile devices. However, the traditional block-based hybrid video coding technology need...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T9/00G06T11/00
Inventor 陶晓明卢继川李扬葛宁陆建华
Owner TSINGHUA UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products