Multi-scale decomposition based detail perception fusion algorithm for extreme exposure images

被引：0
|
作者：
Zhang J. [1 ]
Huang J. [1 ]
Yang D. [1 ]
Liang B. [1 ]
Chen J. [1 ]
Zhao D. [1 ]
机构：
[1] School of Automation, Central South University, Changsha
来源：
Guofang Keji Daxue Xuebao/Journal of National University of Defense Technology | 2024年 / 46卷 / 02期
关键词：
high dynamic range; image fusion; multi-scale decomposition;
D O I：
10.11887/j.cn.202402017
中图分类号：
学科分类号：
摘要：
Aiming at the problem of the low dynamic range of extreme exposure images, such as underexposure and overexposure images, a detail perception image fusion algorithm based on multi-scale decomposition was proposed. After detail enhancement, the underexposed image was roughly fused with the overexposed image. Wavelet transform was used to perform multi-scale decomposition on the brightness component of the image after detail enhancement, and a special high-frequency and low-frequency fusion strategy was designed to realize the fine fusion of brightness components. The hue and saturation components of the coarse fusion image were recombined with the brightness components of the fine fusion image to obtain the final fusion result. Based on abundant testing data, the experimental results show that the visual effect of this method is excellent. The index of averaged MEF-SSIM is 0.9854, and the index of averaged SSIM is 0.6508, which are superior to the existing mainstream algorithms. © 2024 National University of Defense Technology. All rights reserved.
引用
收藏
页码：162 / 173
页数：11
相关论文
共 33 条
  • [1] HUANG L, LI Z P, XU C, Et al., Multi-exposure image fusion based on feature evaluation with adaptive faetor, IET Image Processing, 15, 13, pp. 3211-3220, (2021)
  • [2] SHEN R, CHENC I, BASU A., QoE-based multi-exposure fusion in hierarchical multivariate Caussian CRF [J], IEEE Transactions on Image Processing, 22, 6, pp. 2469-2478, (2013)
  • [3] XU F, LIU J H, SONG Y M, Et al., Multi-exposure image fusion techniques: a comprehensive review, Remote Sensing, 14, 3, (2022)
  • [4] LI H L., Research on methods of acquiring HDR images based on deep learning [D], (2021)
  • [5] MA X Y, FAN F Q, LU T R, Et al., Multi-exposure image fusion de-ghosting algorithm based on image block decomposition [J], Acta Optica Sinica, 39, 9, pp. 132-140, (2019)
  • [6] LIAO Y H., Research on the solution of high dynamic range scenes in digital photography [D], (2015)
  • [7] YAN Y., Research on feature extraction and fusion of multiexposure images based on learning theory [D], (2021)
  • [8] WANG D., Research on high dynamic imaging technology based on convolutional neural network [D], (2020)
  • [9] YU Z J., Research and implementation on tone mapping for high dynamic range images, (2010)
  • [10] SHEN R, CHENC I, SHI J B, Et al., Generalized random walks for fusion of multi-exposure images [J], IEEE Transactions on Image Processing, 20, 12, pp. 3634-3646, (2011)
1234