Unlock instant, AI-driven research and patent intelligence for your innovation.

Image automatic registration and fast super-resolution fusion method based on edge features

A super-resolution, edge feature technology, applied in the field of image processing theory, can solve problems such as high algorithm complexity and slow speed

Inactive Publication Date: 2011-12-28
HOHAI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method overcomes the shortcomings of slow execution speed and high algorithm complexity in previous image fusion.

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 automatic registration and fast super-resolution fusion method based on edge features
  • Image automatic registration and fast super-resolution fusion method based on edge features
  • Image automatic registration and fast super-resolution fusion method based on edge features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] like figure 1 As shown, the computer simultaneously reads low-resolution multi-spectral color images and high-resolution grayscale images from USB, infrared and other interfaces. The low-resolution color image is recorded as M, which has three bands, respectively M 1 ,M 2 ,M 3 , record the high-resolution grayscale image as P, the obtained images M and P are temporarily stored in the buffer, first obtain the registration parameters of the images M and P, and then undergo HIS transformation and IHS inverse transformation to obtain super-resolution color images F, stored in the buffer, or directly output to the monitor, or remotely transmitted through the network interface.

[0069] like figure 2 Shown is the flow chart of the method of the present invention. The algorithm is executed. First, the grayscale image P is registered to the I component, and then the grayscale image after histogram registration and the I component are fused based on the fuzzy integral to ob...

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

An image automatic registration and fast super-resolution fusion method based on edge features, relating to the field of image processing, the present invention is characterized in that it has the following processing steps: (1) computer reads in two types of target images to be processed from interfaces such as USB to the buffer zone, one of which is a low-resolution multispectral image, and the other is a high-resolution grayscale image; (2) using wavelet transform and least squares fitting model to obtain the registration parameters of the two types of images; ( 3) Use the linear IHS transformation of the registered multispectral image to obtain the intensity component image, and then match the histogram of the high-resolution gray image to the intensity component; (4) replace the intensity with the high-resolution gray image after the histogram matching Component, linear IHS inverse transformation to realize image super-resolution fusion; (5) output super-resolution multi-spectral rate color image. The complexity and execution speed of the method provided by the invention are lower than those of the traditional method, occupy less computer system resources, and are convenient for execution on embedded devices.

Description

1. Technical field [0001] The invention relates to image processing theory, and realizes an image automatic registration and fast super-resolution fusion method based on edge features. 2. Background technology [0002] In applications such as video surveillance, resource exploration, on-line inspection of workpiece surface quality, and military reconnaissance, high-resolution images can often provide the required important details. In order to obtain high-resolution images, people first think of improving the performance of hardware equipment, but this will increase the manufacturing cost, and the existing manufacturing technology can basically achieve the maximum physical properties of existing materials, resolution The scale of improvement is also very limited. In summary, the method of obtaining high-resolution images by improving hardware performance cannot meet the needs of future development. [0003] At present, a method of using signal processing technology to obta...

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): G06T7/00G06T5/00
Inventor 徐立中凌静石爱业汤敏黄凤辰王慧斌马贞立
Owner HOHAI UNIV