Registering control point extracting method combining multi-scale SIFT and area invariant moment features

An extraction method and multi-scale technology, which is applied in the field of image processing and can solve the problem of not considering regional grayscale information.

Inactive Publication Date: 2010-05-26
HARBIN INST OF TECH
View PDF0 Cites 81 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the SIFT algorithm has shortcomings: because only local gradient information is used to describe the feature points, the simple difference method is used when calculating the local gradient, and the gray information of the area is not considered, so it is easily affected by noise and produces errors. There are many mismatches in

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
  • Registering control point extracting method combining multi-scale SIFT and area invariant moment features
  • Registering control point extracting method combining multi-scale SIFT and area invariant moment features
  • Registering control point extracting method combining multi-scale SIFT and area invariant moment features

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0025] Specific implementation mode one: this implementation mode is as follows figure 1 As shown, the steps of this embodiment are as follows:

[0026] Step 1. Extract all the key points of the two images to be registered respectively, and obtain the feature vector of each key point;

[0027] The extraction method of all key points in each image and the process of obtaining the feature vector are:

[0028] Step A. Perform continuous Gaussian filtering at different scales on each image to generate a Gaussian scale space; then subtract adjacent layers to obtain a Gaussian difference space; the steps for obtaining a Gaussian difference space are as follows:

[0029] The two-dimensional Gaussian function is defined as follows:

[0030] G ( x , y , σ ) = 1 2 π σ 2 ...

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 registering control point extracting method combining multi-scale SIFT and area invariant moment features, relating to the field of image processing. The invention solves the technical problems of how to extract stable and reliable feature points in the image registering process. The method comprises the following steps of: firstly, carrying out continuous filtering on images by utilizing Gauss kernel functions to generate the DOG scale-space by combining with a downsampling method, and seeking and calculating space and scale coordinates of a local extremum. Then, forming the feature vectors of a key point by utilizing directional gradient information, and obtaining an originally matching key point pair through the Euclidean distance; and then calculating local area HU invariant moment features by taking the originally selected key point as the center, and screening out a finally accurate and effective registering control point by combining with the Euclidean distance. The method combines the multi-scale features of an SIFT arithmetic and the image local area grayscale invariant moment features, thereby effectively improving the stability and the reliability of extracting multisensor image registering control point pairs.

Description

technical field [0001] The invention relates to an image registration control point extraction method, which belongs to the field of image processing. Background technique [0002] Image registration is the process of producing a spatially calibrated collection of images or images that match a certain scene. In many image processing applications, we need to comprehensively compare and analyze multiple observations of the same object. Applications such as urban evolution, flood monitoring, topographic map correction, and image-map matching in navigation guidance require the images used to be spatially co-registered. However, the actual situation is often not ideal. Therefore, multi-sensor image registration has become an indispensable and important link in remote sensing image applications. The registration control point extraction is the key technology in the process of image registration, and the calculation of the final registration result is completed on the basis of i...

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): G06T7/00
Inventor 谷延锋刘保学王晨张晔
Owner HARBIN INST OF TECH
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