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

Image splicing method based on edge classification information

An image stitching and information classification technology, applied in image enhancement, image analysis, image data processing and other directions, can solve the problems of time-consuming, difficult to apply, and poor real-time performance.

Inactive Publication Date: 2011-08-03
辽宁瑞科光电技术有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Due to the time-consuming feature extraction and multi-resolution analysis fusion calculation, the whole stitching process is very slow, and the real-time performance is too poor, so it is difficult to apply in practice.

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 splicing method based on edge classification information
  • Image splicing method based on edge classification information
  • Image splicing method based on edge classification information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The present invention is described in more detail below in conjunction with accompanying drawing example:

[0055] 1. First extract the edge class of the image, and proceed in the following two steps:

[0056] A) Divide the m×n image into M×M (M∈[4,16]) image sub-blocks, and use the following formula to calculate the geometric invariant moments of each image sub-block:

[0057] φ 1 (l,k)=η 20 +η 02 (1)

[0058] In the formula, l∈(0, m / M) and k∈(0, n / M) are the index values ​​of image sub-blocks, upq is the central moment of the image, defined as:

[0059] u pq = Σ j = 1 n Σ i = 1 m ( i - i c ) p ( ...

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 provides an image splicing method based on edge classification information, comprising the following steps of: (1) firstly extracting edge types of images; (2) extracting SIFT (Scale Invariant Feature Transform) features of the images from the obtained image edge types; (3) matching corresponding SIFT feature points in two superposed images by using a K-D (K-Dimensional) tree approximate nearest neighbor search method; (4) finding out two common boundary points P and Q of the two images to obtain the two points of P and Q, and taking a straight line through the P and Q as a seamfor splicing images; (5) transforming images to be spliced into a plurality of band pass signals by utilizing the wavelet transformation; (6) carrying out conversion coefficient fusion in each space;and (7) finally obtaining a seamless image mosaic through wavelet inverse transformation. The invention can short the classic SIFT feature extracting time by 20-50 percent and improve the processing speed by 25-40 percent. The invention has the effects of improving the performance of real time of the classic image splicing method and improving the image splicing quality at a certain extent.

Description

technical field [0001] The invention relates to an image stitching method, in particular to an image stitching method based on edge classification information and efficient stitching trace elimination. Background technique [0002] Image stitching is an important branch of computer vision, which is mainly to seamlessly stitch two or more images with overlapping areas to obtain a higher resolution or wide viewing angle image. The main applications are satellite remote sensing, seabed exploration, surface vegetation mapping, drone surveillance and search, robot vision, video surveillance, medical exploration, electronic image stabilization, and virtual reality, etc. [0003] Image mosaic technology mainly involves two key technologies of image registration and image fusion. Image registration mainly includes methods based on grayscale correlation, phase correlation, transformation model, and feature correlation; image fusion mainly includes median filter method, weighted aver...

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): G06T5/50G06T7/00G06V10/24
CPCG06K9/32G06V10/24
Inventor 付永庆宋宝森张林郭慧
Owner 辽宁瑞科光电技术有限公司
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