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

Robust ghosting removal system and method based on wavelet transform

A wavelet transform and robust technology, applied in the field of image processing, can solve the problems of low efficiency and achieve the effect of reducing ghosting effect

Pending Publication Date: 2021-10-26
HANGZHOU DIANZI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This pre-registration requires an additional training dataset and is rather inefficient as the input images increase

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
  • Robust ghosting removal system and method based on wavelet transform
  • Robust ghosting removal system and method based on wavelet transform
  • Robust ghosting removal system and method based on wavelet transform

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0033] The present invention first carries out following definition and description:

[0034] Feature Maps: Feature maps are used to make non-linear regression complex attributes. Expand the original input value matrix into the form of polynomial expansion by looping. Doing so can obtain a more complex and reasonable objective function than linear regression.

[0035] LeakyReLU activation function: It is a variant of the classic ReLU activation function, the function output has a small slope for negative input. Since the derivative is always non-zero, this can reduce the appearance of silent ...

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 robust ghosting removal system and method based on wavelet transform. Multi-scale feature maps are extracted from low dynamic range image inputs and corresponding spatial attention maps are generated to guide non-reference image recognition misaligned portions to mitigate ghosting effects in the merge phase. And with the help of space attention mapping, the fusion module fuses feature mapping of the LDR image, and finally reconstructs high dynamic range output from different scales. The invention provides a novel cross-transform domain learning system structure which is composed of discrete wavelet transform and discrete cosine transform, that is, the discrete wavelet transform firstly decomposes characteristics into different frequency components, and then a learnable band-pass filter based on the discrete cosine transform is introduced to generate local characteristics consistent with the decomposed components.

Description

technical field [0001] The invention belongs to the technical field of image processing, is a wavelet transform-based deghosting method, and mainly relates to a discrete cosine transform domain learnable band-pass filter deghosting method. Background technique [0002] Reconstruction of high dynamic range (HDR) scenes from sensors with limited dynamic range is a fundamental problem in the fields of signal processing and computer vision. To overcome sensor limitations, a general approach is to capture multiple low dynamic range (LDR) images with different exposure times and then merge them into an HDR image. Estimating the camera response function and mapping the hue of an LDR image is another way to obtain an HDR image. While these algorithms certainly produce visually pleasing results, the scan information in those underexposed or overexposed areas can never be recovered. In recent years, multi-exposure image fusion has been well studied and widely used in commercial appl...

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 Applications(China)
IPC IPC(8): G06T5/00G06K9/46G06N3/04G06N3/08
CPCG06N3/08G06T2207/20064G06T2207/20081G06N3/048G06N3/045G06T5/80
Inventor 潘潇恺郑博仑颜成钢孙垚棋张继勇李宗鹏
Owner HANGZHOU DIANZI UNIV
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