Check patentability & draft patents in minutes with Patsnap Eureka AI!

A homography-invariant image simulation method based on map-adaptive convolution

An image simulation and convolution technology, applied in the field of image simulation, can solve problems such as inability to construct image simulation methods, standard convolution does not obey the law of mapping distribution, etc.

Active Publication Date: 2020-08-11
SICHUAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the standard convolution does not obey the mapping distribution law, so the above conclusion does not hold
[0038] In summary, no homography-invariant image simulation method can be constructed by applying standard convolutions before or after resampling

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
  • A homography-invariant image simulation method based on map-adaptive convolution
  • A homography-invariant image simulation method based on map-adaptive convolution
  • A homography-invariant image simulation method based on map-adaptive convolution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0113] as attached Figure 9 As shown, for image simulation based on standard convolution and image simulation based on map-adapted convolution, we systematically compare the accuracy of the two simulation methods. Figure 10 We demonstrate the benefits of mapping-adapted convolutions in perspective-invariant matching methods.

[0114] Figure 9 Among them, the left image of (a) is the front view image of the object surface (64*64). (a) The right image is the blurred image after the standard Gaussian convolution is performed on the left image. This image is used as a reference image, and all simulated orthographic images are compared with this image to evaluate the simulation accuracy.

[0115] Figure 9 To compare the image simulation based on standard convolution (Equation (1.7)) and the image simulation based on mapping adaptive convolution (Equation (2.8)), consider that the optical center of the camera is located on the surface of a hemisphere, and the center of the he...

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 homography invariant image simulation method based on mapping adaptive convolution, which is a mapping adaptive convolution based on a transmutation integral formula. The method is a transmutation integral formula of standard convolution and is a natural method of standard convolution Extended, it is map-adaptive. The present invention aims at the original images acquired by cameras with different shooting orientations, and when these original images are used to simulate simulated images of specified shooting orientations, the image simulation method based on mapping adaptive convolution can obtain consistent simulated images and improve matching accuracy.

Description

technical field [0001] The invention relates to an image simulation method, in particular to a homography-invariant image simulation model and simulation method based on mapping adaptive convolution, and belongs to the technical field of image simulation. Background technique [0002] A smooth object surface can be a complex curved surface, and if a local surface is considered, the local surface can be approximated as a plane. For the original image with planar structure, after being imaged by the camera, its image is still a planar structure. Due to the difference in shooting orientation (external parameters) and internal structure (internal parameters) of the camera, the shape characteristics of its image structure will change significantly with the change of camera parameters. Therefore, the shape characteristics of the same plane preimage are significantly different in different images acquired by cameras with different parameters. Establishing accurate matching betwee...

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): G06T7/32G06T7/35
CPCG06T7/32G06T7/35
Inventor 李征徐文政
Owner SICHUAN UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com