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

HDR reconstructing algorithm based on histogram normalization and superpixel segmentation

A superpixel segmentation and normalization technology, applied in the field of HDR reconstruction algorithm, to achieve the effect of reducing the difficulty of motion detection, solving LDR image alignment and maximizing the preservation of image details

Active Publication Date: 2016-08-24
SHANDONG UNIV
View PDF3 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The method proposed by the present invention effectively solves the problems of LDR image alignment and maximum image detail retention under the premise of removing HDR image ghosts

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
  • HDR reconstructing algorithm based on histogram normalization and superpixel segmentation
  • HDR reconstructing algorithm based on histogram normalization and superpixel segmentation
  • HDR reconstructing algorithm based on histogram normalization and superpixel segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention is described in detail below in conjunction with accompanying drawing:

[0041] Such as figure 1 As shown, the algorithm proposed in this application mainly includes the following three parts. First, use the histogram matching algorithm to convert the selected reference image I r The histogram of is mapped to other images of the image sequence I i , and generate corresponding matching images respectively so obtained Exposure level and I i Consistent, while the content of the image is the same as the I r be consistent. In the second step, we adopted the literature (X.Ren and J.Malik, “Learning a classification model for segmentation,” in Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on. IEEE, 2003, pp.10–17.) The idea in the image is to combine the pixels of the image into superpixels by comparing the consistency of each pixel with its adjacent pixels, and adopt the literature (G.Mori, X.Ren, A.Efros, J.Malik et al...

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 an HDR reconstructing algorithm based on histogram normalization and superpixel segmentation. The method includes the steps of mapping a histogram of a referential image Ir onto another image Ii of an image sequence through a histogram matching algorithm, respectively generating a corresponding matching image I <M>, combining the pixels of the image into superpixels by comparing the consistency of each pixel point with adjacent pixels, obtaining the contours of moving objects in the image through a cutting algorithm, obtaining the absolute value of the difference between the matching image I <M> and the other image Ii, conducting superpixel segmentation, dividing the superpixels obtained through segmentation into static parts and dynamic parts, synthesizing the images Ii and I <M> into intermediate images I <L>, calculating the weight map of each intermediate image based on a gradient image quality evaluation system, and conducting weighted fusion to obtain a final image fusion result. Histogram matching of a referential image and other images in the input sequence is conducted instead of directly calculating the gradient information of the input image. In this way, more details in the image can be retained.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an HDR reconstruction algorithm based on histogram normalization and superpixel segmentation. Background technique [0002] Although image technology has developed rapidly in recent years, ordinary digital cameras still cannot capture images consistent with the real scene seen by human eyes. In order to solve this limitation, many researchers have devoted themselves to obtaining full-motion pictures in the real world, that is, high dynamic range (high dynamic range HDR) pictures. Among them, through multiple exposures, a certain dynamic range is captured each time, and different dynamic ranges of the same scene are fused to obtain an HDR picture. However, due to the presence of dynamic information and moving objects in the actual scene, ghosting or blurring will occur in direct image fusion images. Therefore, how to eliminate ghosting in sequential HDR images is an important res...

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): G06T5/50G06T7/20
CPCG06T5/50
Inventor 张伟胡胜男刘侃张伟东翁健王浩
Owner SHANDONG 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