Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Image corner point matching method based on self-adaptive threshold and RANSAC

An adaptive threshold and corner matching technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problem of difficulty in estimating the threshold size.

Inactive Publication Date: 2018-07-27
CENTRAL SOUTH UNIVERSITY OF FORESTRY AND TECHNOLOGY
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This algorithm improves the Harris corner response, but there is still the problem that the threshold value is difficult to estimate due to manual selection of the threshold.

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 corner point matching method based on self-adaptive threshold and RANSAC
  • Image corner point matching method based on self-adaptive threshold and RANSAC
  • Image corner point matching method based on self-adaptive threshold and RANSAC

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] Embodiment 1: The inventive method is described in detail below:

[0069] Harris corner detection principle

[0070] Harris corner detection algorithm is developed on the basis of Moravec algorithm, which was proposed by Harris C and Stephens MJ. Harris improved the Moravec corner detection algorithm by using differential operations and autocorrelation matrices. For an image I(x, y), a small window centered on a certain pixel (x, y) moves u in the x direction and v in the y direction, and the gray intensity change given by Harris is as in the formula (1 ) as shown in:

[0071] E(x,y)=∑w(x,y)[f(x+u,y+v)-f(x,y)] 2 (1)

[0072] Among them, f(x, y) represents the gray value at point (x, y), and f represents the gray function formula (1) is the definition of the Harris algorithm, Harris represents the gray intensity change when the window moves, f is a symbol that facilitates the embodiment of program code. w (x, y) is a Gaussian filter, as shown in formula (2). Acco...

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 an image corner point matching method based on a self-adaptive threshold and RANSAC. The image corner matching method comprises the following steps: firstly, pre-screening corner points by adopting a way of suppressing a non-maximum value by means of self-adaptation; secondly, performing secondary screening on the corner points by adopting an Forstner operator; then, performing coarse matching on detected Harris corner points by adopting a normalized cross-correlation matching algorithm; and finally, accurately matching images by using a random sampling unification algorithm. An experimental result proves that by adopting the improved method, the time required for detecting the corner points and matching the images is shortened, and the matching accuracy of the images can be effectively improved. The image corner point matching method based on the self-adaptive threshold and the RANSAC has the advantages of high processing efficiency and high matching accuracy.

Description

technical field [0001] The invention relates to an image corner point matching method based on adaptive threshold and RANSAC. Background technique [0002] Image registration is the process of matching and superimposing two or more images acquired at different times, with different sensors (imaging devices) or under different conditions (weather, illuminance, camera position and angle, etc.). It is widely used in remote sensing data analysis, computer vision, image processing and other fields. Image registration can be divided into two categories: patch matching based methods and feature matching based methods. Li et al. proposed a matching method based on block matching, which uses the entire image information to obtain high matching accuracy, but there are problems such as large amount of calculation and time-consuming based on block matching. Zhou proposed a registration method based on local features. Compared with the registration method based on global features propo...

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): G06T7/32
CPCG06T2207/20004G06T7/32
Inventor 秦姣华李浩向旭宇钟少宏马文涛
Owner CENTRAL SOUTH UNIVERSITY OF FORESTRY AND TECHNOLOGY
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
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