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

Video figure decoration method and device based on self-adaptive tracking frame segmentation

An adaptive tracking and tracking frame technology, applied in the field of image processing, can solve problems such as background blur, poor video display effect, and unclear picture

Active Publication Date: 2018-06-15
BEIJING QIHOO TECH CO LTD
View PDF20 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method can beautify the characters to a certain extent, the display effect of the processed video is not good, the video picture is not clear enough, and the background is relatively blurred, lacking in authenticity

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 figure decoration method and device based on self-adaptive tracking frame segmentation
  • Video figure decoration method and device based on self-adaptive tracking frame segmentation
  • Video figure decoration method and device based on self-adaptive tracking frame segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0124]Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0125] Because in the process of video shooting or video recording, the number of specific objects such as the human body that is photographed or recorded may change, for example, a new video character is added in the frame image, the present invention divides every n frames in the video Each group of frame images obtained is processed, so as to more accurately perform scene segmentation processing on the frame images in the video, w...

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 discloses a video figure decoration method and device based on self-adaptive tracking frame segmentation. The method comprises the following steps: obtaining the tracking frame corresponding to the t-th frame of image according to the tracking frame corresponding to the t-1st frame of image, and performing the scene segmentation on the t-th frame of image by using the tracking frame;determining a second foreground image of the t-th frame image according to the segmentation result, and determining at least one to-be-decorated area; and adding a beautifying effect on at least oneto-be-decorated area, so as to obtain the processed t-th frame of image. According to the scheme, the to-be-decorated area can be quickly and accurately determined according to the segmentation resultof the frame image of the video, and the beautifying effect is added to the to-be-decorated area, and compared with the prior art, the video is processed in a fuzzy processing mode, so that the beautifying effect can be accurately added to the person in the video, the processed video image is clear, and the video data display effect is improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a video character dressing method, device, computing device and computer storage medium based on adaptive tracking frame segmentation. Background technique [0002] With the continuous development of image processing functions, users have higher and higher requirements for video effects, hoping to beautify the characters in the video to make the characters look more beautiful. In the prior art, when beautifying the characters in the video, most of the frame images of the video are processed by blurring to realize the beautification of the characters, such as removing dark spots and dark circles on the face of the characters, and brightening the skin color. Although this method can beautify the characters to a certain extent, the display effect of the video obtained after processing is not good, the picture of the video is not clear enough, and the background is r...

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): G06T7/11G06T7/194G06T5/00G06T5/50
CPCG06T5/50G06T7/11G06T7/194G06T2207/10016G06T2207/20221G06T2207/30196G06T5/94
Inventor 赵鑫邱学侃颜水成
Owner BEIJING QIHOO 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