Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Video character separation method and device

A character and video technology, applied in the field of communication, can solve the problems of poor video adaptability and the inability to separate characters and objects

Active Publication Date: 2015-06-03
HUAWEI TECH CO LTD
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, when using the existing technology to segment video characters, the number of components of the Gaussian mixture model is manually set, and the adaptability to various types of videos is not strong, and when using the opening and closing operation to optimize the object segmentation results, it is impossible to segment a complete character object

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
  • Video character separation method and device
  • Video character separation method and device
  • Video character separation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] Embodiments of the present invention provide a method for video character segmentation, such as figure 1 As shown, the method includes:

[0029] Step 101, performing face detection on the first frame of video image to be processed, to obtain the face area of ​​the person;

[0030] Here, only the first frame image among the video images to be processed is processed. If it is not the first frame video image, the video image can be quickly divided according to the correlation between adjacent video frames.

[0031] Step 102, acquiring foreground seed pixels and background seed pixels according to the face area of ​​the person;

[0032] Step 103, according to the foreground seed pixel and the background seed pixel, respectively calculate the probability that each pixel in the video image is foreground or background;

[0033] Step 104, constructing a graph according to the respective probabilities, and performing graph cutting to obtain person objects.

[0034] An embodim...

Embodiment 2

[0042] Embodiments of the present invention provide a method for video character segmentation, such as image 3 As shown, the method includes:

[0043] Step 301, judging whether the video frame image to be processed is the first frame;

[0044] The purpose of judging whether the current video frame image to be processed is the first frame is that when the current video frame image is not the first frame, the current frame image can be processed according to the result of the segmentation of the video character object of the previous frame, that is, according to the adjacent video frame The correlation of the image is processed, which can speed up the processing speed.

[0045] Step 302, when the video frame image to be processed is the first frame, face detection is performed on the first frame video image to be processed to obtain the face area of ​​the person;

[0046] Specifically, the AdaBoost algorithm is used for face detection. Adaboost is an iterative algorithm. Its ...

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 present invention relates to the technical field of communication. Disclosed are a video character separation method and device, applicable to separation of various video character objects and capable of separating a complete character object in real time. In the technical solution provided by the embodiments of the present invention, human face detection is performed on a first frame of video image to be processed, so as to obtain the character face area, foreground seed pixels and background seed pixels are obtained according to the character face area, the probability of each pixel being the foreground or the background in the video image is calculated respectively according to the foreground seed pixels and the background seed pixels, an image is constructed according to each probability, and image cutting is performed to obtain the character object. The solution provided by the embodiments of the present invention is applicable to video object separation.

Description

technical field [0001] The present invention relates to the field of communication technologies, in particular to a method and device for video character segmentation. Background technique [0002] Object segmentation technology refers to separating the object of interest to the user on the video or image from the background at the pixel level, and the segmented object can be synthesized into a new background. In the existing technology for automatic segmentation of human objects, a Gaussian mixture model is used to establish a background color model, and then the video frame image is subtracted from the established background color model, and threshold segmentation is performed to obtain a foreground object color model. Using the foreground / background color model and the color difference between adjacent pixels to construct a map, the automatic segmentation of human objects is realized through graph cutting, and the cut image is smoothed by morphological opening and closing...

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): G06T7/00G06T7/20G06K9/46
CPCG06V40/167
Inventor 刘志史冉丁保焱薛银珠杨胜
Owner HUAWEI TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com