A multi-exposure image fusion method based on high-order singular value decomposition

A high-order singular value and image fusion technology, applied in the field of image fusion, can solve the problems of unsatisfactory removal of artifacts, poor image contrast and saturation, easy distortion of image color, etc.

Active Publication Date: 2021-03-09
杭州电子科技大学上虞科学与工程研究院有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In A. Goshtasby, "Fusion of multi-exposure images," Image and Vision Computing, vol.23, pp.611–618, 2005. (multi-exposure image fusion) using a block-level fusion method, the image is divided into uniform block and use the minimum average method to fuse the best image block, but the contrast and saturation of the image fused by this method are poor
In B.Gu, W.Li, J.Wong, M.Zhu, and M.Wang, “Gradient field multi-exposure images fusion for high dynamic rangeimage visualization,” J.Vis.Commun.Imag.Represent., vol.23 , no.4, pp.604–610, May2012. (Gradient field multi-exposure image fusion for high dynamic range image visualization) proposed an iterative method to modify the gradient field, using twice average filtering and multi-scale nonlinearity Compression method, which obtains the result by solving the Poisson equation and then linearly stretching to the common range, but this method is prone to artifacts
In S.Raman and S.Chaudhuri, "Bilateral filter based compositing for variable exposure photography," inProc.Eurographics, 2009, pp.1–4. (Bilateral filter based compositing for variable exposure photography) proposed a An effective scene synthesis method using an edge-preserving filter, such as a bilateral filter, since there is no restriction on the global brightness consistency, the color of the image fused by this method is prone to distortion, and the overall tone of the image is dark
In K.Ma, H.Li, Z.Wang and D.Meng, “Robust Multi-Exposure Image Fusion: A Structural PatchDecomposition Approach,” IEEE Trans.Image Process., vol.26, no.5, pp.2519- 2532, May 2017. (Multi-exposure image fusion: a structural block decomposition method) proposed to fuse multi-exposure images using structural block decomposition, but this method is not easy to obtain texture information, and the effect of removing artifacts cannot satisfactory

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 multi-exposure image fusion method based on high-order singular value decomposition
  • A multi-exposure image fusion method based on high-order singular value decomposition
  • A multi-exposure image fusion method based on high-order singular value decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0049] A multi-exposure image fusion method based on high-order singular value decomposition proposed by the present invention, its overall realization block diagram is as follows figure 1 As shown, it includes the following steps:

[0050] Step 1: Select D different exposure images with a width of M and a height of N; then convert each exposure image from the RGB color space to the YCbCr color space to obtain the brightness channel (Y) image of each exposure image, the first The chroma channel (Cb) image and the second chroma channel (Cr) image, the luminance channel image, the first chroma channel image, and the second chroma channel image of the dth exposure image are correspondingly marked as Y d , Cb d 、Cr d ; Wherein, D is a positive integer, D>1, such as D=100, d is a positive integer, the initial value of d is 1, 1≤d≤D.

[0051] St...

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 multi-exposure image fusion method based on high-order singular value decomposition, which divides the brightness channel image of the exposure image into overlapping brightness blocks, and uses high-order singular value decomposition to obtain the kernel tensor and the third mode of the brightness block factor matrix, and then obtain the characteristic coefficient and activity level measure of the luma block, obtain the fused luma block according to the first and second mode factor matrices, characteristic coefficients and activity level measure of the luma block, and perform linear transformation on the obtained luma channel image , to obtain the fused brightness channel image; by calculating the fusion coefficient of the pixels in the first chroma channel image of the exposure image, the fused first chroma channel image is obtained; by calculating the second chroma channel image of the exposure image The fusion coefficient of the pixels in the method is used to obtain the fused second chroma channel image; the fused image is obtained according to the fused images of the three channels; the advantage is that better detail texture and rich color information can be obtained.

Description

technical field [0001] The invention relates to an image fusion technology, in particular to a multi-exposure image fusion method based on high-order singular value decomposition. Background technique [0002] The process of combining information from two or more images of the same scene into one more informative image is called image fusion. Multi-Exposure Image Fusion (MEF) is one of the classic applications of image fusion. Due to the limited dynamic range of digital cameras, images of natural scenes generally have a larger dynamic range than images captured by digital cameras. The high dynamic range (High Dynamic Range, HDR) imaging technology estimates the camera response function (Camera Response Function, CRF) from multiple low dynamic range (Low Dynamic Range, LDR) images, and then uses the inverse operation of the camera response function to reconstruct the high Dynamic range images. Since most of the standard displays currently in use are low dynamic range, afte...

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 & AuthorityPatents(China)
IPC IPC(8): G06T5/50
CPCG06T5/50G06T2207/10024G06T2207/20221
Inventor李黎骆挺徐海勇吴圣聪何周燕张君君
Owner杭州电子科技大学上虞科学与工程研究院有限公司