Optical flow model-based intensive video satellite image matching method and system
A satellite image and dense matching technology, which is applied in the field of video satellite image dense matching method and system, can solve the problems of target information loss, difficulty of robust dense matching method, performance indicators to be improved, etc.
Active Publication Date: 2017-09-22
WUHAN UNIV
View PDF9 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Dense matching technology using video satellite images is a high-tech technology that requires high precision and real-time performance. Although people have achieved good results in its research, many performance indicators still need to be improved.
Projecting from 3D world space to 2D image space will cause loss of target information when the natural scene is constantly changing, so it is very difficult to design a robust dense matching method
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
specific Embodiment approach
[0074] Further illustrate the specific embodiment of the present invention below in conjunction with accompanying drawing, steps are as follows:
[0075] Step 1, use the SGM matching method to roughly match the video satellite images.
[0076] SGM (semi-global matching) is an image matching method produced in the field of computer vision. It uses mutual information to describe the complex correspondence between the same-named pixels to achieve image matching. The basic idea of SGM image matching is: first, perform pixel-by-pixel disparity calculation based on mutual information; then, approximate two-dimensional constraints with one-dimensional constraints in multiple directions.
[0077] This step further includes:
[0078] In step 1.1, the parallax image is obtained by calculating the pixel-by-pixel parallax of the video satellite image.
[0079] The disparity function d(p i ,p′ i , I L , I R ) is defined as follows:
[0080]
[0081] The disparity function repre...
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
Login to View More Abstract
The invention discloses an optical flow model-based intensive video satellite image matching method and system. The method comprises the following steps of: 1, roughly matching a video satellite image by adoption of an SGM matching method; 2, precisely matching the video satellite image by adoption of a PMVS matching method; and 3, refining a matching result obtained in the step 2 by adoption of an optical flow method. According to the method and system disclosed by the invention, two intensive matching methods such as SGM and PMVS are combined, and a manner of carrying out rough matching through the SGM method and then carrying out precise matching through the PMVS method, so that the advantages of the two methods are developed as much as possible, and the image data processing ability is improved from the aspects of precision and efficiency.
Description
technical field [0001] The invention relates to image dense matching technology, in particular to a video satellite image dense matching method and system based on an optical flow model. Background technique [0002] After more than 30 years of development, my country's aerospace technology has made great progress, and a system of earth observation remote sensing satellites consisting of resources, meteorology, ocean, environment, and national defense series has been formed. Especially under the impetus of the "High-resolution Earth Observation System" national science and technology major project construction, through innovations in platform sensor development, multi-satellite networking, ground data processing, etc., the spatial resolution and time resolution of my country's remote sensing satellites The rate and data quality have been greatly improved, providing information services and decision support for my country's modern agriculture, disaster prevention and reduction...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/46
CPCG06V20/40G06V10/443
Inventor 张过汪韬阳蒋永华江万寿蒋博洋
Owner WUHAN UNIV