Image multi-scale fusion method, device, storage medium and terminal

A multi-scale fusion and image technology, applied in the field of image processing, can solve problems such as computational efficiency and robustness pain points, achieve the effect of improving image fusion speed and robustness, and reducing hardware requirements

Active Publication Date: 2019-01-29
SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
View PDF5 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the existing technology, not only extremely high requirements are put forward for the hardware, but also a great challenge for the software. Due to the need to comp

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 multi-scale fusion method, device, storage medium and terminal
  • Image multi-scale fusion method, device, storage medium and terminal
  • Image multi-scale fusion method, device, storage medium and terminal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] figure 1 It is a flow chart of the multi-scale image fusion method provided in Embodiment 1 of the present application. This embodiment is applicable to the situation of image or video acquisition, and the method can be executed by the image fusion device provided in the embodiment of the present application. The device can be composed of It can be realized by means of software and / or hardware, and can be integrated into an unstructured camera array image acquisition terminal.

[0066] Such as figure 1 As shown, the multi-scale fusion method of the image includes:

[0067] S110. Acquire one short-focus image and at least one long-focus image.

[0068] Wherein, the short-focus image and the long-focus image can be relative terms. For example, in a group of camera arrays, the image acquired by the camera with the shortest focal length can be used as the short-focus image, and the images acquired by other cameras can be used as the short-focus image. Telephoto images, i...

Embodiment 2

[0082] figure 2 It is a flow chart of the multi-scale image fusion method provided in Embodiment 2 of the present application. On the basis of the above-mentioned embodiments, this embodiment is specifically optimized as follows: said using a block matching algorithm to determine a short-focus reference block includes: using a block matching algorithm to perform block matching on the short-focus image and the telephoto image , to obtain a first response map; perform block matching on the structure edge map of the short focus image and the structure edge map of the telephoto image to obtain a second response map; combine the first response map and the second response Dot product on the map to locate the position corresponding to the telephoto image in the short-focus image; and the part corresponding to the telephoto image cut out from the short-focus image is determined as a short-focus reference block.

[0083] Such as figure 2 As shown, the multi-scale fusion method of t...

Embodiment 3

[0097] image 3 It is a flowchart of the multi-scale image fusion method provided in Embodiment 3 of the present application. On the basis of the above-mentioned embodiments, this embodiment is specifically optimized as: taking 4 pairs of matching points from the telephoto image and the short-focus reference block, including: segmenting the short-focus reference block according to a preset method , to obtain short-focus reference block sub-blocks as the search area; segment the telephoto image according to the preset method to obtain telephoto image sub-images, and select a preset area in the middle of each telephoto image sub-image as Template: matching the template with the search area to obtain 4 pairs of matching points.

[0098] Such as image 3 As shown, the multi-scale fusion method of the image includes:

[0099] S310. Acquire one short-focus image and at least one long-focus image.

[0100] S320. Using a block matching algorithm, determine a short-focus reference ...

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

Embodiments of the present application disclose a multi-scale image fusion method, apparatus, storage medium, and terminal. The method comprises the following steps of: acquiring a short focus image and at least one long focus image; a short-focus reference block is obtained by matching the short-focus image and the long-focus image with image block matching and structural edge block matching; selecting 4 pairs of matching points from the long-focus image and the short-focus reference block to determine a homography matrix of the long-focus image to the short-focus reference block; obtaining acoarsely aligned long focal image according to the homography matrix; the mesh control points of the coarsely aligned long focus image are fused by matching with the key points of the short focus reference block to obtain a fused image. By adopting the technical proposal provided by the application, the method can be integrated into an unstructured camera array for realizing the effects of reducing hardware requirements and improving image fusion speed and robustness.

Description

technical field [0001] The embodiments of the present application relate to the technical field of image processing, and in particular to a multi-scale image fusion method, device, storage medium, and terminal. Background technique [0002] With the development of science and technology, and the increase in the pixel requirements for images or videos at this stage, gigapixel images have become a demand in the industry. [0003] Gigapixel image technology uses a short-focus camera and multiple telephoto cameras to record scene images at the same time, and then replaces the image at the corresponding position of the short-focus camera with the image captured by the telephoto camera, so that the range can be obtained. The effect of large and clear images requires technical means related to positioning and image combination. In the existing technology, not only extremely high requirements are put forward for the hardware, but also a great challenge for the software. Due to the ...

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
IPC IPC(8): G06T5/50G06T7/33
CPCG06T5/50G06T7/344
Inventor 方璐戴琼海刘烨斌
Owner SHENZHEN GRADUATE SCHOOL TSINGHUA 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