采用非采样Contourlet变换与区域分类的红外和可见光图像融合

张蕾; 金龙旭; 韩双丽; 吕增明; 李新娥

doi:10.3788/OPE.20152303.0810

您当前的位置：

首页 >

文章列表页 >

采用非采样Contourlet变换与区域分类的红外和可见光图像融合

信息科学 | 更新时间：2020-08-13

- 采用非采样Contourlet变换与区域分类的红外和可见光图像融合
- Fusion of infrared and visual images based on non-sampled Contourlet transform and region classification
- 光学精密工程 2015年23卷第3期页码：810-818
- 作者机构：
  
  1. 中国科学院长春光学精密机械与物理研究所,吉林长春,中国,130033
  2. 中国科学院大学北京,中国,100049
  3. 东北师范大学物理学院,吉林长春,130024
- 作者简介：
- 基金信息：
  
  吉林省科技发展计划资助项目(No.20126016)()
- DOI：10.3788/OPE.20152303.0810
  中图分类号： TP391.4
- 收稿日期：2013-12-27，
  
  修回日期：2014-02-20，
  
  纸质出版日期：2015-03-25
- 稿件说明：
移动端阅览
张蕾, 金龙旭, 韩双丽等. 采用非采样Contourlet变换与区域分类的红外和可见光图像融合[J]. 光学精密工程, 2015,23(3): 810-818

ZHANG Lei, JIN Long-xu, HAN Shuang-li etc. Fusion of infrared and visual images based on non-sampled Contourlet transform and region classification[J]. Editorial Office of Optics and Precision Engineering, 2015,23(3): 810-818
张蕾, 金龙旭, 韩双丽等. 采用非采样Contourlet变换与区域分类的红外和可见光图像融合[J]. 光学精密工程, 2015,23(3): 810-818 DOI： 10.3788/OPE.20152303.0810.

ZHANG Lei, JIN Long-xu, HAN Shuang-li etc. Fusion of infrared and visual images based on non-sampled Contourlet transform and region classification[J]. Editorial Office of Optics and Precision Engineering, 2015,23(3): 810-818 DOI： 10.3788/OPE.20152303.0810.

摘要

提出基于多尺度变换和区域相结合的红外与可见光图像融合方法

用于有效保留红外图像与可见光图像中的空间信息及热目标信息

提升融合图像的可观测性和可理解性。首先

基于非采样Contourlet变换(NSCT)方法对红外和可见光图像进行初步融合

采用基于局部能量的规则融合低通子带系数

根据尺度内各方向子带的相关性原则融合带通方向子带系数。然后

计算初次融合后所得的融合图像与源图像的结构相似性(SSIM)

根据源图像与初次融合图像的结构相似程度对图像进行区域分类

得到相似区域分类标识图。最后

依据区域内各自的相似度特性

分别采用不同的融合策略进行二次融合

从而得到最终的融合结果。实验结果表明:该方法能够充分提取源图像的区域特征和纹理特征

融合结果在主观和客观评价上均优于目前流行的融合方法。与仅使用NSCT法进行融合相比

实验所采用的两组图像的质量评价指标分别提高了16%、85%、54%、36%和18%、102%、84%、41%。表明该方法在主客观评价上均优于双树复杂小波变换(DTCWT)、NSCT、冗余离散小波变换(RDWT)等方法。

Abstract

A novel method based on region classification and multi-resolution transform was presented for the fusion of infrared and visual images to retain their spatial information and thermal target information and to improve their observability and intelligibility. The fusion process contained the following three steps. Firstly

infrared and visual images were fused by the Non-sampled Contourlet Transform (NSCT) to get lowpass subband coefficients and bandpass directional subband coefficients. Lowpass subband coefficients were fused by the region energy rule and the bandpass directional subband coefficients was fused based on the correlation rule of the bandpass directional subband coefficients. Then

the Structural Similarity Index (SSIM) between original images and intermediate fused image was computed. Based on the obtained SSIM

the images were classified in regions and the similarity region classification maps were obtained. Finally

to generate general and complementary regions

pixels of original images were classified by the threshold of similarity. In accordance with the concentrated similarity of different regions

the original images were fused for the second time and the final fused images were obtained. In this method

the general and complementary regions of infrared and visual images were distinguished effectively. The experimental results show that the method is better in fusing infrared and visual images than some current methods

such as NCST

Dual-tree Complex Wavelet Transform (DTCWT)

Redundant Discrete Wavelet Transform (RDWT)

and Discrete Wavelet Transform (DWT). As compared with the NSCT method in two group images

their quality indexes have been increased by 16%

85%

54%

36% and 18%

102%

84%

41%

respectively.

关键词

Keywords

references

杨粤涛, 朱明, 贺柏根, 等. 采用改进投影梯度非负矩阵分解和非采样Contourlet变换的图像融合方法 [J]. 光学精密工程, 2011, 19(5):1143-1150. YANG Y T, ZHU M, HE B G, et al.. Fusion algorithm based on improved projected gradient NMF and NSCT [J]. Opt. Precision Eng., 2011, 19(5):1143-1150. (in Chinese)

朱明, 孙继刚, 梁伟, 等. 四元数曲波变换多源多聚焦彩色图像融合 [J]. 光学精密工程, 2013, 21(10):2671-2678. ZHU M, SUN J G, LIANG W, et al.. Multiple multifocus color image fusion using quaternion curvelet transform [J]. Opt. Precision Eng., 2013, 21(10):2671-2678. (in Chinese)

李光鑫, 徐抒岩, 吴伟平, 等. Piella像素级多分辨率图像融合框架的扩展及其算法 [J]. 光学精密工程, 2012, 20(12):2774-2780. LI G X, XU SH Y, WU W P, et al.. Extension of Piella pixel-level multiresolution image fusion framework and its algorithm [J]. Opt. Precision Eng., 2012, 20(12):2774-2780. (in Chinese)

傅瑶, 孙雪晨, 薛旭成, 等. 基于非下采样轮廓波变换的全色图像与多光谱图像融合方法研究 [J]. 液晶与显示, 2013, 28(3):429-434. FU Y, SUN X CH, XUE X CH, et al.. Panchromatic and multispectral image fusion method based on nonsubsampled contourlet transform [J]. Chinese Journal of Liquid Crystals and Displays, 2013, 28(3):429-434. (in Chinese)

LUO X Y, ZHANG J, DAI Q H. A regional image fusion based on similarity characteristics [J]. Signal Processing, 2012, 92:1268-1280.

PAJARES G, J. M. de la CRUZ. A wavelet-based image fusion tutorial [J]. Pattern Recognition, 2004, 37(9):1855-1872.

CHAI Y, LI H F, LI ZH F. Multifocus image fusion scheme using focused region detection and multiresolustion [J]. Optics Communications, 2011, 284:4376-4389.

YANG B, LI SH T, Pixel-level image fusion with simultaneous orthogonal matching pursuit [J]. Information Fusion, 2012, 13:10-19.

DO M N, VETTERLI M. The contourlet transform:an efficient directional multiresolution image representation [J]. IEEE Transactions on Image Processing, 2005, 14(12):2091-2106.

CUNHA A L Da, ZHOU J P, DO M N. Nonsubsampled contourlet transform:theory, design, and applications [J]. IEEE Transactions on Image Processing, 2006, 15(10):3089-3101.

WNAG Z, BOVIK A C, SHEIKH H R, et al.. Image quality assessment:from error visibility to structural similarity [J]. IEEE Transactions on Image Processing, 2004, 13(4):600-612.

LI T J, WANG Y Y. Biological image fusion using a NSCT based variable-weight method [J]. Information Fusion, 2011, 12:85-92.

PIELLA G, HEIJMANS H. A new quality metric for image fusion [C]. in:Proceedings of the International Conference on Image Processing, 2003:173-176.

XYDEAS C S, PETROVIC V. Objective image fusion performance measure [J]. Electronics Letters, 2000, 36(4):308-309.

浏览量

155

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于目标增强与蝴蝶优化的红外与可见光图像融合

基于非下采样双树复轮廓波变换和稀疏表示的红外和可见光图像融合

结合目标提取和压缩感知的红外与可见光图像融合

基于压缩感知的红外与可见光图像融合

基于多特征的红外与可见光图像融合