Region-matching-based fast electronic image stabilization method

A technology of area matching and fast electronics, which is applied in the direction of TV, electrical components, image communication, etc., can solve problems such as the inability to guarantee the unity of real-time performance and performance, the influence of motion vector of image acquisition equipment, and video shape distortion, etc., to achieve superior performance, Accurate and stable, optimized distortion effect

Inactive Publication Date: 2017-01-25
SHANDONG UNIV
View PDF8 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The third is that when detecting the motion vector of the camera, there will be background noise, such as the movement or movement of small objects in the foreground, the shaking of branches and leaves in the background, the movement of the target itself, and the entry of foreign objects into the field of view, etc. will affect the motion of the image acquisition device

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
  • Region-matching-based fast electronic image stabilization method
  • Region-matching-based fast electronic image stabilization method
  • Region-matching-based fast electronic image stabilization method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] A fast electronic image stabilization method based on region matching, the present embodiment selects a video for a section of 10s / 298 frames, and the specific steps include:

[0061] (1) read out the video image frame, select the first secondary image frame as a reference frame, and the rest as image frames to be processed;

[0062] (2) Use the MSER maximum extremum stable region algorithm to extract the MSER feature region of the current image frame, sort all the extracted MSER feature regions according to the area from large to small, select the top 3 MSER feature regions, and compare the current frame with Perform area matching on the reference frame to obtain the matching score of the current frame, and the corresponding MSER feature area is used as the feature point extraction area. According to this method, the matching scores of all frames in the video are counted, and a curve is drawn. The abscissa of the curve is the frame of the current image frame The ordina...

Embodiment 2

[0071] A fast electronic image stabilization method based on area matching according to Embodiment 1, the difference is that,

[0072] In the step (2), the calculation formula of the matching score is as shown in formula (I):

[0073] D ( i ) = Σ m = 1 M Σ n = 1 N [ S i ( m , n ) * T ( m , n ) ] - - - ( I )

[0074] In formula (I), D(i) is the matching score between the i-th sub-image frame and the reference frame, S i (m,n) is the gray value at the reference frame coordinates (m,n), T(m,n) is the gray value at the current frame coordinates (m,n), and the coo...

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 region-matching-based fast electronic image stabilization method, which specifically comprises the following steps: (1) reading video image frames, and selecting a first frame of an image as a reference frame; (2) sequentially performing region matching on current frames and the reference frame to obtain matching scores by adopting an MSER (maximally stable extremal region) algorithm, performing wavelet transformation, sequencing the obtained matching scores from high to low scores, and selecting regions corresponding to the first n matching scores; (3) performing region labeling on the regions corresponding to the selected first n matching scores, performing FAST characteristic point detection on the labeled regions, and extracting characteristic points; (4) performing characteristic point matching, and estimating a motion parameter; (5) performing reverse motion compensation on the image. According to the method, an image sequence is stabilized by virtue of an image stabilization algorithm, so that the method has the advantages of fastness, high accuracy, low power consumption and the like.

Description

technical field [0001] The invention relates to a fast electronic image stabilization method based on area matching, which belongs to the technical field of digital image processing. Background technique [0002] In recent years, with the vigorous development of computers and related technologies, the technology has been updated in real time, and many methods that originally required related mechanical equipment and mechanical technology can be directly replaced by low-cost and high-efficiency electronic software and hardware. The development of image stabilization technology has gone through three stages from mechanical to optical, and then to the current electronic image stabilization technology. Electronic image stabilization technology uses digital image processing technology to estimate the motion of a series of images in the video, and then perform reverse motion Compensation is a technique to remove abnormal shifts in an image such as jitter, rotation, etc. [0003] ...

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): H04N5/21H04N5/14
CPCH04N5/145H04N5/21
Inventor 杨明强郑庆河张庆锐
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap