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

Video global motion estimation method with sequential consistency constraint

A global motion and consistency technology, applied in computing, image data processing, instruments, etc., can solve problems such as salience, estimation error, simple background and foreground

Inactive Publication Date: 2015-03-11
DALIAN UNIV OF TECH
View PDF3 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in many videos such as sports videos in practice, there are often cases where the background is complex in most frames, while the background is simple and the foreground is prominent in a small number of frames.
At this time, most of the feature points in these few frames come from the foreground, that is, they belong to outliers. Only relying on the data between two frames usually judges outliers as inliers, resulting in estimation errors.

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 global motion estimation method with sequential consistency constraint
  • Video global motion estimation method with sequential consistency constraint
  • Video global motion estimation method with sequential consistency constraint

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Embodiment 1: The global motion parameter estimation situation of the video containing more foreground.

[0048] 1. Extract all key frames.

[0049] 2. Convert all the key frames to grayscale, the i-th frame is identified as I i .

[0050] (For all key frames, perform steps 3-5.)

[0051] 3. Extract feature points for the i-th frame. Create a checkerboard grid with 20 pixels as the pitch. Taking each intersection of the checkerboard grid as the center and taking 7 as the farthest distance, traverse each pixel p, and investigate whether it can be used as a feature point as described in Article 4 and Article 5 below.

[0052] 4. Set the pixels around point p to p j , First traverse j to find maxP, satisfy maxP=argmaxΣ(I i (p)-I i (p j )) 2 , And get maxPThre=maxΣ(I i (p)-I i (p j )) 2 As a metric to judge the quality of maxP points. Where I i (p) is the pixel value of point p in the i-th frame, I i (p j ) Is the pixel point p around the point p in the i-th frame j The pixel valu...

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 global motion estimation method with a sequential consistency constraint, and belongs to the field of a digital media technology. A locus-based method is employed, and by use of video interframe corresponding characteristic point data, the motion parameters of a camera are solved. According to the invention, the scheme is put forward for solving the limitation that a conventional model can only be solved when background characteristic points, i.e., inner points are greater than foreground characteristic points, i.e., outer points in terms of quantity, video multi-frame sequential consistency is taken as a constraint, the defects in the prior art are solved, and the method can be used for effectively processing a situation when the number of the inner points is smaller than the number of the outer points and can also be applied to a situation when the number of the inner points are greater than the number of the outer points.

Description

Technical field [0001] The invention relates to the field of digital media, and relates to a video global motion estimation method with time sequence consistency constraints. Background technique [0002] Video global motion estimation refers to the method of estimating the relative motion of a video sequence based on the image content, and is a key technology in the field of computer vision. The purpose of global motion estimation is to find out the motion law of the camera that causes global background motion between frames from the video sequence. Whether it is analyzing the camera motion law that causes scene changes or analyzing the motion of foreground objects, global motion estimation is a prerequisite for these processes. Therefore, global motion estimation has important applications in compression coding, video image stabilization, target tracking, and panorama synthesis. [0003] The video global motion estimation method has two categories: a method based on differentia...

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): G06T7/20
CPCG06T7/246G06T2207/10016
Inventor 李豪杰关岳王领
Owner DALIAN UNIV OF TECH
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