Face image sequence generation method and device based on feature tracking

A sequence generation device and technology of face images, which are used in image data processing, graphic image conversion, instruments, etc., can solve the problem of large amount of data transmitted in face video sequences, and achieve the effect of reducing the amount of information and reducing the traffic burden.

Active Publication Date: 2016-06-15
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF10 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to overcome the defects of the existing human face video sequence transmission technology, solve the problem of large amount of transmission data of the human face video sequence under the condition of low network bandwidth, and propose a method and device for generating a human face image sequence based on feature tracking , to reduce the user's traffic burden and the unnecessary network load of the entire network

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
  • Face image sequence generation method and device based on feature tracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] Considering that in the actual video chat scene, the face is basically in the state of facing the camera directly, and the spatial movement of the head during the whole process will not be particularly obvious, a face image sequence based on feature tracking proposed by the present invention The specific technical details of the generation method are described as follows:

[0025] 1. The sending end of the face video data detects the specific coordinate information of the face feature points in each frame of the image by tracking the face image sequence frames collected by the camera in real time.

[0026] The feature point extraction adopts the active shape model ASM (ActiveShapeModel), which uses a series of training sample images, describes the shape information of the sample with a set of feature points, and then aligns all samples in the same coordinate system, using principal component analysis (PCA) Establish a statistical model of the shape of the object, and fi...

Embodiment 2

[0037] Based on a method for generating a face image sequence based on feature tracking described in Embodiment 1, the present invention also implements a device for generating a face image sequence based on feature tracking, including a sending end module and a receiving end module, specifically described as follows:

[0038] Sending module:

[0039] Contains two mutually independent units: face feature point detection unit and feature point sending unit, both of which share a sending data queue (need to adopt synchronous mode), through this queue to ensure the sequence relationship of processing image frames.

[0040] The face feature point detection unit is responsible for locating the feature points of the frameless face image captured by the camera, and the technology adopted is technical detail 1 described in embodiment 1. Add the difference coordinate information of the obtained feature points to the end of the sending data queue.

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 relates to a face image sequence generation method and device based on feature tracking, and belongs to the technical field of computer graph and image processing and pattern recognition. The method comprises the steps: collecting a face image sequence frame through a real-time tracking camera; detecting the specific coordinate information of face feature points in each image frame; enabling a feature point change value with the difference between the feature point data of the current image frame and the feature point data of an initial image being greater than a preset change threshold value T to be transmitted to a receiving side through a network; enabling a receiving end to carrying out the texture redrawing of the face image according to the stored initial face image and the face feature point information through the received change value of the image feature point, and generating a real-time human face image corresponding to a transmitting end. Compared with the prior art, the method greatly reduces the transmission amount of each human face image, and effectively reduces the flow burden of a user and the unnecessary network load of the whole network.

Description

technical field [0001] The invention belongs to the technical field of computer graphics and image processing and pattern recognition, and relates to methods for face feature point detection, face feature point deformation, grid generation and face texture mapping in videos, and in particular to a face image based on feature tracking Sequence generation method and device. Background technique [0002] With the explosive development of the Internet and social networking sites, more attention has been paid to the interaction between people through video, whether through PC clients or through mobile device terminals (mobile phones, tablet computers) and other hardware products with cameras. Almost all video communication between users can be realized. The software products mainly include Skype (Microsoft), QQ (Tecent), Facetime (Apple), etc. When transmitting these video streaming data, each frame of image captured by the camera in real time at the sending end will be sent to ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T3/40G06K9/00
CPCG06T3/40G06V40/166G06V40/171G06V10/25G06V10/751
Inventor 宋红王新磊
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap