Global vector acquisition method based on probability statistics and image gradient information

A technology of image gradient and gradient information, applied in image communication, digital video signal modification, electrical components, etc., can solve problems such as affecting the accuracy of the algorithm and limiting the speed of algorithm implementation, and achieves reduction of computing time, easy real-time implementation, and reduced computing. The effect of complexity

Active Publication Date: 2016-01-20
西安佳数智华信息科技有限公司
View PDF8 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the algorithm needs to manually select different templates for implementation in the matching process. This step limits the implementation speed of the algorithm in the application of different scenarios. At the same time, the selection of different templates will also greatly affect the accuracy of the algorithm.

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 vector acquisition method based on probability statistics and image gradient information
  • Global vector acquisition method based on probability statistics and image gradient information
  • Global vector acquisition method based on probability statistics and image gradient information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] refer to figure 1 , the implementation steps of the present invention are as follows:

[0032] Step 1, obtain the block to be matched.

[0033] The specific implementation of this step is as follows:

[0034] 1a) Use the gradient operator to perform two-dimensional convolution processing on the image to be matched:

[0035] Use the horizontal gradient operator Dv and the vertical gradient operator Dh to perform two-dimensional convolution processing on the image to be matched, and obtain the horizontal gradient information matrix Mat Dv (x,y), and the longitudinal gradient information matrix Mat Dh (x,y), where the value of Dv is [1,-1; 0,0], and the value of Dh is [1,0;-1,0], which can be adjusted according to the actual situation;

[0036] 2a) Calculate the gradient information matrix Mat g (x,y):

[0037] For the horizontal and vertical gradient information matrix obtained in step (1a), calculate the gradient information matrix Mat g (x,y):

[0038] Matt g (...

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 global vector acquisition method based on probability statistics and image gradient information. The method is mainly used for solving a problem that global vector solution is inaccurate, long in operation time, and liable to matching distortion in a two-image matching process, and comprises steps of: 1) performing two-dimensional convolution on images to be processed by using a transverse gradient operator and a longitudinal gradient operator; 2) computing a gradient information matrix; 3) performing macro-block partition on the gradient information matrix and obtaining the gradient sum of the macro-blocks; 4) ordering the gradient sum of the macro-blocks and determining a macro-block to be matched in the vicinity of a maximum value; 5) processing the macro-block to be matched by using a full search method; and 6) determining a global motion vector by using a local motion vector probability distribution function. By using image grey information and a local motion vector probability density function, the method improves global vector precision, is low in operation complexity, good in parallelism, and easy to implement, and can be used for digital image and video processing in image matching processes of electronic image stabilization and video compression.

Description

technical field [0001] The invention belongs to the technical field of digital image processing, in particular to a global vector acquisition method, which can be used to complete processes such as electronic image stabilization and video compression in a non-stationary state. Background technique [0002] With the development and popularization of digital image technology, the processing of a single image can no longer meet the growing needs of people, and the processing of continuous image sequences and video processing are increasing. For example, in the field of electronic image stabilization, people use electronic image stabilization technology to obtain stable and clear high-quality video; in the field of video compression, people use more efficient compression algorithms to produce clear videos with smaller capacity. [0003] Among the above-mentioned various technologies, the key link lies in the accurate matching between two images, so as to find the relevant inform...

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): H04N19/527H04N19/176
Inventor 焦阳牛毅任琼巍柳林石光明
Owner 西安佳数智华信息科技有限公司
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