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

Image point matching method for industrial digital photogrammetry

A technology of image point matching and point matching, which is applied in the field of image point matching for industrial digital photogrammetry, and can solve the problems of large error and large amount of calculation

Active Publication Date: 2010-09-29
THE PLA INFORMATION ENG UNIV
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0021] The purpose of the present invention is to provide an image point matching method for industrial digital photogrammetry that can realize fast and accurate image point matching, so as to solve the problems of large amount of calculation and large error in existing matching methods

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
  • Image point matching method for industrial digital photogrammetry
  • Image point matching method for industrial digital photogrammetry
  • Image point matching method for industrial digital photogrammetry

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] The image point matching method based on nuclear surface constraints of three photos, the flow chart of this method is as follows Figure 5 As shown, the specific steps are as follows:

[0052] (1) Transform the coordinates of all image points on the three photos into the object space coordinate system;

[0053] (2) Select a photo Each unmatched image point on the target image point is calculated as the target image point in the other two photos , Corresponding nuclear surface on , ;

[0054] (3) Set the distance threshold , calculate the image respectively , From each candidate image point to the corresponding nuclear surface , the distance ,like , then the corresponding candidate image point is marked as the initial matching image point, and the two images , The initial matching image point set on is denoted as the initial set , ;

[0055] (4) If the initial set , If at least one of them is empty, the matching of the target image p...

Embodiment 2

[0069] It can be seen from the aforementioned matching process that theoretically only two photos can be used for matching, but due to the interference of errors, it is necessary to use the third photo to eliminate the false matching caused by errors. How to select these three photos, that is, how to group all the photos, should consider the geometric relationship among the photos.

[0070] like Figure 7 Shown, the 3rd photo The reason why the mismatch is eliminated is that the nuclear surface and intersect, reflected in the photo above is the nuclear line and Intersect at the image point of the same name . If in nuclear surface Interference image points exist on , its in the photo image point of the same name on not on nuclear surface Therefore, there will be no mismatch. but if , , , The four points are coplanar, then the core plane and overlap, dot will be at the core inside, so that , All may be pixels with the same name, resul...

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 an image point matching method for industrial digital photogrammetry. In the method, distances from image points to be matched to corresponding epipolar planes are utilized as constraint conditions, and images are grouped according to known points. The method comprises the following steps of: firstly, sorting the images into a plurality of groups according to whether containing the same object points; then, combining and matching parts of each group of images with better calculated geometrical quality; and finally, reversely calculating same-name image points on other images by utilizing the object points. By using the method, the matching speed and the matching accuracy can be improved. Proved by tests, compared with an image point matching method based on epipolar constraint, the method has less computation and small error.

Description

technical field [0001] The invention relates to an image point matching method for industrial digital photogrammetry. Background technique [0002] Image point matching is to determine the corresponding image points of the same name corresponding to object space points on different photos, which is one of the key technologies to realize the automation of photogrammetry. When the reflective sign is used as the measurement point, the images of each sign have basically the same gray distribution law, so it is difficult to achieve automatic matching by using a matching algorithm based on gray level correlation. Therefore, in industrial digital photogrammetry, the automatic matching of image points can only be completed by using the spatial geometric relationship between the same-named image points. [0003] The epipolar constraint is an important constraint to solve the matching of photogrammetric image points with the same name. figure 1 Shown is a stereo pair, object space p...

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): G01C11/04G06T7/00
Inventor 李广云李宗春冯其强
Owner THE PLA INFORMATION ENG UNIV
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