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

A Stereo High Dynamic Range Imaging Method Based on Generative Adversarial Networks

A technology with high dynamic range and imaging methods, which can be applied to biological neural network models, image communication, color TV components, etc., and can solve problems such as complex steps and insufficient imaging details

Active Publication Date: 2021-02-19
NINGBO UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a stereoscopic high dynamic range imaging method based on generative confrontation network to solve the problem of complex steps and insufficient imaging details in the existing high dynamic range imaging method proposed in the above-mentioned background technology

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 Stereo High Dynamic Range Imaging Method Based on Generative Adversarial Networks
  • A Stereo High Dynamic Range Imaging Method Based on Generative Adversarial Networks
  • A Stereo High Dynamic Range Imaging Method Based on Generative Adversarial Networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0052] The dynamic range of natural scenes is as high as 9 orders of magnitude, while the dynamic range of images captured by ordinary consumer cameras is less than 3 orders of magnitude, which will lead to whitening of the image in the bright area of ​​the scene, resulting in information loss. In addition, the existing stereoscopic imaging technology is getting worse The development is mature, and the organic combination of the stereo vision system and the hig...

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 stereoscopic high dynamic range imaging method based on generative confrontation network. Considering that stereoscopic high dynamic range imaging is a combination of stereoscopic imaging technology and high dynamic range imaging technology, it is assumed that the target viewpoint is the left viewpoint, and the left viewpoint belongs to Underexposure, the right viewpoint is overexposure, and its core is to generate a multi-exposure sequence of the left viewpoint; the generated left viewpoint overexposed image and the original left viewpoint underexposed image are composed of a multi-exposure sequence, and the constructed viewpoint fusion is used to generate an adversarial network to Complete the high dynamic range image fusion task; use three different exposure images to generate label images, so that the viewpoint fusion generation confrontation network can learn the conversion relationship between low-quality fusion images and high-quality fusion images; the advantage is that it can reduce the The complexity of multi-step processing, and reduce the accumulation of errors, but also improve the overall contrast and detail fidelity of the generated image.

Description

technical field [0001] The invention relates to the technical field of high dynamic range imaging, in particular to a three-dimensional high dynamic range imaging method based on a generative confrontation network. Background technique [0002] Most commercial cameras can only capture the limited dynamic range of natural scenes, which inevitably leads to underexposure in the dark areas of the scene and overexposure in the bright areas of the scene; High dynamic range (HDR) The emergence of imaging technology has effectively solved this problem. HDR imaging technology uses multiple exposure images of the same scene to estimate the camera response function (Camera response function, CRF), and then converts the multiple exposure images to the irradiation domain for fusion to obtain an image that reflects the dynamic range of the real scene. However, due to the time interval between each exposure of the camera when capturing multi-exposure images, for scenes with moving objects...

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): H04N5/235H04N5/355G06K9/62G06N3/04
CPCH04N23/741H04N25/57G06N3/045G06F18/253G06F18/214
Inventor 蒋刚毅陈晔曜陈恳郁梅
Owner NINGBO UNIV