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

Method and system for image registration

An image registration and image technology, applied in the field of image processing, can solve problems such as difficulty in obtaining key points, inapplicability to marine SAR images, noise sensitivity, etc.

Inactive Publication Date: 2014-01-01
INST OF ELECTRONICS CHINESE ACAD OF SCI
View PDF2 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the correlation peak method is easy to operate, but it is sensitive to noise and has high time complexity
Although the key point method is superior to the correlation peak method in terms of sensitivity and time complexity, it is not suitable for marine SAR images, because the key point features of marine SAR images are not obvious, which directly leads to the difficulty of key point acquisition.

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
  • Method and system for image registration
  • Method and system for image registration
  • Method and system for image registration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0105] Image 6 Schematic diagram of the signal flow for image registration, Figure 7 It is the marine SAR image pair to be registered in the first embodiment of the present invention. Such as Image 6 As shown, the registration of marine SAR images can be achieved through the following steps:

[0106] Step 1: Set the parameters to P=Q=2, C=1. The relative movement ranges of the main and auxiliary images are known to be: distance 20-40, azimuth 20-40, and the search window is 4×4. The original image is downsampled to 4 levels: level 0, level 1, level 2, and level 3.

[0107] Step 2: Recursively match the down-sampled image in the order of low resolution to high resolution until the best matching position of the original image is found. Among them, when the best matching position of the next level is at the edge of the search window of the upper level, the search window expansion process is required.

[0108] Specifically, the third-level image registration in the search window is ...

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 and system for image registration. Blocking is performed on images collected by multiple channels, and step-by-step downsampling is respectively performed on all image blocks; step-by-step recursion matching is performed on all image block sets obtained through the downsampling according to resolution ratios from low to high, and optimal matching positions of the original image blocks are obtained; according to the optimal matching positions of all the image blocks, corresponding relations of the main images and the auxiliary images are obtained, and the auxiliary images are moved to achieve the image registration. The amount of operations of the step-by-step recursion structure is small, and therefore the stable and efficient registration can also be performed on ocean SAR images which are not large in size and not obvious in local texture.

Description

Technical field [0001] The present invention relates to image processing technology, in particular to an image registration method and system. Background technique [0002] Synthetic Aperture Radar (SAR, Synthetic Aperture Radar), also known as microwave imaging radar, is one of many radars. It uses complex radar data post-processing methods to obtain extremely narrow effective radiation beams, which is extremely important for the generated radar images. High resolution. It is characterized by high resolution, can work around the clock, and can effectively identify camouflage and penetrating masks, such as identifying camouflaged missile silos and ground targets in areas covered by clouds and fog. [0003] Image registration refers to the process of matching two or more images of the same scene taken from different times, different sensors, or different perspectives. A single image has limitations in time and spatial resolution, and image registration can provide scene interpreta...

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 邓云凯王宇邵云峰陈润璞柳罡许丽颖李泓宇唐江文宋明聪李兴林袁志辉
Owner INST OF ELECTRONICS CHINESE ACAD OF SCI
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