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

Video stabilizing method based on local and bulk motion difference compensation

A technology of video stabilization and difference compensation, which is applied in the direction of TV, color TV, color TV parts, etc., and can solve the problems of low stabilization rate and high content loss

Active Publication Date: 2016-11-09
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF6 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to propose a video stabilization method based on local and overall motion difference compensation for the problems of low stabilization rate and excessive content loss in the existing video stabilization technology

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 stabilizing method based on local and bulk motion difference compensation
  • Video stabilizing method based on local and bulk motion difference compensation
  • Video stabilizing method based on local and bulk motion difference compensation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0095] Attached below figure 1 The embodiment of the method of the present invention is described in detail.

[0096] A video stabilization method based on local and overall motion difference compensation, the specific steps are as described in step 1 to step 11 in the main body of the invention;

[0097] Wherein, in step 1, the detection of the feature point p is realized by the feature point detection function GoodFeaturesToTrack() function in the computer vision library OpenCV function library, for the feature point The feature point tracking function calcOpticalFlowPyrLK () function in the computer vision library OpenCV function library is adopted to calculate; the value of video frame quantity N is 387 in the present embodiment;

[0098] In step 2, this embodiment divides the video frame t (the value range of t is 1 to 387) into 8*8=64 grids, that is, the value of M is 64, and the value of D is 8; there are 8 grids in one row Grid, then there are 9 grid corners in a ro...

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 stabilizing method based on local and bulk motion difference compensation. The method comprises the following steps: 1) acquiring motion tracks of feature points in adjacent video frames by an optical flow method, gridding the video frames, and calculating camera paths of grids and overall video frames according to a content saving constraint and a similarity invariant constraint; 2) calculating compensation matrixes between the overall camera paths and the grid camera paths, and calculating an optimized overall camera path according to constraints of path smoothening and overlapping; 3) calculating optimized grid camera paths according to compensation matrixes between the optimized overall camera path and the grid camera paths; and 4) solving deformation matrixes of the grids according to the non-optimized grid camera paths and the optimized grid camera paths, and deforming the grids to obtain stable video frames. Compared with an existing method, the video stabilizing method has the advantages that the number of paths needing to be optimized is reduced from the number of the grids to an overall path through the compensation matrixes, so that the calculation time is shortened, and the calculation efficiency is increased.

Description

technical field [0001] The invention relates to a video stabilization method, in particular to a video stabilization method based on local and overall motion difference compensation, and belongs to the technical fields of video signal processing and video motion compensation. Background technique [0002] With the popularity of digital cameras, people can shoot videos anytime and anywhere, which has led to a rapid and steady increase in the number of videos. However, different shooting environments and techniques produce quite different video effects. Especially for amateur video shooters, it is difficult to hold the camera steadily to shoot all the time, so the video will have obvious jitter, and sometimes it looks blurry. At present, some hardware devices have been used to eliminate video shaking during shooting, such as trolleys, cams, tripods, etc., but these devices need to be prepared in advance. If you shoot videos temporarily, you don’t have these devices. Therefor...

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): H04N5/232
CPCH04N23/683H04N23/68
Inventor 黄华黄建峰张磊
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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