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

Global motion estimation method and device of image sequence

A global motion and image sequence technology, applied in the field of image processing, can solve the problem that the grayscale projection method cannot obtain accurate global motion estimation, etc.

Active Publication Date: 2016-03-23
LUOYANG INST OF ELECTRO OPTICAL EQUIP OF AVIC
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method and device for global motion estimation of an image sequence to solve the problem that the grayscale projection method cannot obtain accurate global motion estimation when the local moving pixels of the image account for a relatively large proportion

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
  • Global motion estimation method and device of image sequence
  • Global motion estimation method and device of image sequence
  • Global motion estimation method and device of image sequence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0059] An embodiment of a global motion estimation method for an image sequence of the present invention

[0060] On the basis of the gray projection algorithm, the estimation method of the present invention evenly divides the gray projection in the row and column directions into blocks, sorts the matching errors of each block at a certain offset position in the row or column direction, Then according to the proportion of local motion in the image, discard the poorly matched blocks, and use the matching error sum of the remaining blocks as the matching metric at this position to calculate the offset position of the minimum matching metric, which is the global motion the estimated results. The following is an example of two consecutive frames of images A and B collected. The dimensions of images A and B are both M×N (height×width), and the r...

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 global motion estimation method and device of an image sequence, and belongs to the technical field of computer vision. The global motion estimation method comprises the following steps: collecting two continuous frames of images to serve as target images, and carrying out row direction and line direction gray projection on the two frames of sequence images; carrying out even partitioning on the row direction and line direction gray projection, calculating the matching error of each block under a certain deviation position in the line or row direction, abandoning the block with poor matching according to a proportion of local motion in the image, and taking the sum of the matching errors of residual blocks as a matching metric under the position; and calculating a deviation position with the minimum matching metric, wherein the deviation position is an estimation result of global motion. According to the possible proportion of the local motion in the image, the line or row with poor gray projection matching is abandoned, the robustness of the method on local motion is guaranteed, and influence on global motion estimation by the local motion can be effectively avoided.

Description

technical field [0001] The invention relates to an image sequence global motion estimation method and device, belonging to the technical field of image processing. Background technique [0002] Image motion estimation has a wide range of applications in the field of image processing, such as in video coding, image correction, etc. Motion estimation refers to the analysis of position differences between related scenes of two or more images to obtain the motion vector of the camera or the object being photographed. Global motion refers to the motion of the image scene between image frames, usually formed by camera motion, while the motion of objects relative to the scene between image frames is called local motion. Global motion estimation techniques are widely used in motion-based image segmentation, image stitching, and video compression. [0003] At present, common global motion estimation methods include algorithms such as block matching, feature matching, and gray-scale...

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): G06T7/20
CPCG06T2207/10016G06T2207/20021
Inventor 揭斐然
Owner LUOYANG INST OF ELECTRO OPTICAL EQUIP OF AVIC
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