Reliable image characteristic matching method based on physical positioning information

A technology of image features and physical positioning, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve problems such as mismatching and long time, achieve accurate matching, fast matching, and reduce the possibility of mismatching.

Inactive Publication Date: 2010-07-21
ZHEJIANG UNIV
View PDF2 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Such processing takes a long time
Moreover, global matching has the possibility of mis-matching, and the result requires manual intervention.

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
  • Reliable image characteristic matching method based on physical positioning information
  • Reliable image characteristic matching method based on physical positioning information
  • Reliable image characteristic matching method based on physical positioning information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] as attached Figure 4 As shown, a kind of image feature reliable matching technique based on physical location information of the present invention comprises the following steps:

[0037] (1) Obtain 20 initial images with at least two overlapping areas with two-dimensional physical information; when shooting different areas, the angle between the main optical axis of the camera and the initial panorama is 90 degrees, and the angle between the camera and the initial panorama The vertical distance between plots remains constant.

[0038] (2) Extract the SIFT feature points of each initial image; the SIFT feature point information of the initial image extracted finally includes the pixel-level position of the feature point on the initial image and a 128-dimensional feature vector. (if attached image 3 As shown, the pyramid model of the SIFT algorithm, the image layer on the left, the new image is obtained by downsampling (1 / 2 sampling) of the previous layer image, while...

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 reliable image characteristic matching method based on physical positioning information, successively comprising the following steps: obtaining a plurality of initial images provided with two-dimensional physical information, wherein an overlapping region exists between at least two initial images; extracting the SIFT characteristic point of each initial image; utilizing the two-dimensional physical information of the initial image to obtain the two-dimensional offset of the two initial images on a pixel level; determining the overlapping region of the two initial images; matching the characteristic points of the overlapping region of the two initial images; outputting the two-dimensional physical information of matched characteristic points; and repeating the steps to match the plurality of the initial images one by one. The invention only compares the local characteristic point information of the image, has high and accurate matching speed, greatly lowers the possibility of producing miss match and almost can obtain the effect of zero error.

Description

technical field [0001] The invention relates to the field of image processing and image matching, in particular to the splicing of panoramas. Background technique [0002] Image matching refers to identifying points with the same name between two or more images through a certain matching algorithm. The window center point corresponding to the maximum is used as the point with the same name. Its essence is the optimal search problem using matching criteria under the condition of primitive similarity. Image matching can be mainly divided into grayscale-based matching and feature-based matching. [0003] Scale-invariant feature transform (SIFT) is a computer vision algorithm used to detect and describe local features in images. It finds extreme points in the spatial scale and extracts their positions. , scale, and rotation invariants. This algorithm was published by David Lowe in 1999 and was summarized in 2004. Its applications include object recognition, robot map percept...

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): G06K9/64
Inventor 刁常宇沈武魁鲁东明
Owner ZHEJIANG UNIV
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