Supercharge Your Innovation With Domain-Expert AI Agents!

Optimal method of ransac feature matching based on epipolar line interpolation image

An optimization method and feature matching technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of few high-quality matching of image feature points and low accuracy, and achieve the effect of excellent quality and high accuracy

Active Publication Date: 2017-09-29
NANJING UNIV OF POSTS & TELECOMM
View PDF2 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 solve the problem of few high-quality matches and low accuracy of ransac algorithm image feature points

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
  • Optimal method of ransac feature matching based on epipolar line interpolation image
  • Optimal method of ransac feature matching based on epipolar line interpolation image
  • Optimal method of ransac feature matching based on epipolar line interpolation image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] Such as figure 1 As shown, the specific process of applying the present invention to optimize the matching of image features is as follows:

[0037] Step 1: Find the fundamental matrix and obtain the high-quality matching set of the original algorithm. The detailed process is as follows figure 2 shown;

[0038] Step 1-1: Input two images image1 and image2 to be matched;

[0039] Step 1-2: Use the surf detector to detect the keypoints of the two images respectively, and use the surf descriptor to calculate the 64-dimensional descriptor of the keypoints;

[0040] Steps 1-3: Use the matcher to perform two-way matching on the descriptor. That is: find the two best matches of each feature point of image1 to image2, and then find the two best matches of each feature point of image2 in image1.

[0041] Steps 1-4: Perform ratio detection. That is: process two matching sets separately, and calculate the distance ratio of the two values ​​for the two matching values ​​in ea...

Embodiment 2

[0066] When the number of fixed polar lines is 2, the comparison between the present invention and the original method includes:

[0067] The results shown in Table 1 indicate the number of detected feature points and the final number of high-quality matches (the thickness is 0 means the original algorithm did not introduce epipolar lines).

[0068] It can be seen from Table 1 that in the case of the original algorithm without introducing epipolar lines, figure 1 with figure 2 The feature points of are 1478 and 1452 respectively, and the matching number is 15. When the epipolar line is inserted, as the thickness increases, the number of feature points and matching numbers both increase first and then decrease. When the thickness is 10, the high-quality matching can reach 22, which is 47% higher than the original algorithm.

[0069] Table 1: Comparison of high-quality matching results when the thickness of the inserted polar line is different

[0070]

[0071] Note: Th...

Embodiment 3

[0073] When the fixed epipolar line thickness is 5 pixels, the comparison between the present invention and the original method includes:

[0074] Table 2 shows the comparison of matching results under different conditions when the thickness of the fixed epipolar line is 5 pixels. It can be seen that the high-quality matches obtained by the original method (number=0) are 15, while the number of epipolar lines in the present invention is between 1 and 4. When the number of inserted epipolar lines is 4, the effect is the best. The premium hits can reach 23, a 53% improvement.

[0075] Table 2: Comparison of high-quality matching results when the number of inserted polar lines is different

[0076]

[0077] Note: The data fixedly inserts epipolar lines at a thickness of 5 pixels; number is the number of inserted epipolar lines; number = 0 indicates the matching result of the original method, that is, does not insert epipolar lines, and directly operates on the entire image. ...

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 method of matching and optimizing ransac features based on a polar-line insertion image. The method has the advantages of improving matching quality and increasing excellent matching quantity of feature points and solving problems that the image feature points of ransac algorithm has few excellent matching and low accuracy. The method comprises the steps: firstly, detecting, describing and matching feature points of the image to be matched, primarily screening matching collections according to rate and symmetry testing to remove error matching; secondly, utilizing the ransac algorithm to obtain an original excellent matching collection and a supported basic matrix; thirdly, utilizing the basic matrix to calculate the polar-lines of the feature matching points and choosing the obtained polar-lines so as to guarantee that the polar-lines are uniformly distributed on the image as possible; fourthly, processing the thickness and the quantity of the chosen polar-lines and then inserting into the image; and finally, obtaining excellent matching to the processed image based on the ransac algorithm. The method has good effect and is applicable to various images.

Description

technical field [0001] The invention relates to the technical field of computer image processing, in particular to a ransac feature point matching optimization method based on an epipolar line interpolation image. Background technique [0002] In computer vision, the concept of image matching is widely used in object recognition, visual tracking, 3D reconstruction and other problems. It relies on the idea of ​​first using a feature detector (the present invention uses a surf feature detector) to detect some special points on the image, then describing them, and finally using the described content to match the feature points, thereby realizing Image-to-image matching. [0003] Image matching can be roughly divided into matching based on pixel grayscale and matching based on image features, in which image features are further divided into region features, edge features and point features. Image matching technology based on feature points can meet the basic requirements of ef...

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 Patents(China)
IPC IPC(8): G06T7/32
CPCG06T7/30
Inventor 高志强陈洁密保秀
Owner NANJING UNIV OF POSTS & TELECOMM
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com