基于能量分割的空间域图像融合算法研究

王新赛; 冯小二; 李明明

基于能量分割的空间域图像融合算法研究

陆军炮兵防空兵学院(郑州校区), 河南郑州 450052

详细信息

作者简介:
王新赛（1963-），男，江苏睢宁人，教授，博士，研究方向为光电成像、模式识别。E-mail: wangxsai@126.com

中图分类号: TP391.41
计量
- 文章访问数: 343
- HTML全文浏览量: 63
- PDF下载量: 22
- 被引次数: 0
出版历程
- 收稿日期: 2020-08-24
- 修回日期: 2020-09-28
- 刊出日期: 2022-07-20

Research on Spatial Domain Image Fusion Algorithm Based on Energy Segmentation

Army Academy of Artillery and Air Defense Force Zhengzhou Campus, Zhengzhou 450052, China

摘要

摘要: 针对空间域图像融合存在不同图源差异性信息提取、融合权重选取困难等问题，提出了一种新的空间域图像融合算法。利用矩阵相似的基本原理，对红外图像矩阵进行对角化变换，计算可见光图像矩阵在主要特征向量上的映射，采用加权融合的方法处理特征值矩阵，对融合矩阵进行对角化逆变换重构融合图像。实验结果表明，算法在充分保留源图像有效信息的同时，融合图像的整体灰度得到了明显的改善，具有良好的图像质量评估指数和更加优秀的视觉效果。
- 空间域 /
- 对角化 /
- 特征向量 /
- 图像融合 /
- 质量评估
Abstract: To address the problems of image fusion in the spatial domain, such as the extraction of different image sources, and challenges in selecting fusion weights, a new spatial-domain image-fusion algorithm is proposed. Using the basic principle of matrix similarity, the infrared image matrix is diagonally transformed and the visible light image matrix is mapped onto the main eigenvectors. Then, the weighted fusion method is used to process the eigenvalue matrix and the fusion matrix is diagonalized as an inverse-transformed and reconstructed fusion image. The experimental results show that the algorithm fully retains the effective information of the source image; moreover, the overall grayscale of the fused image is significantly improved. Thus, the algorithm offers a strong image quality evaluation index and better visual effects.
- spatial domain /
- diagonalization /
- feature vector /
- image fusion /
- quality evaluation

HTML全文

图 1 矩阵对角化后特征值重构效果图

Figure 1. Rendering of eigenvalue reconstruction after matrix diagonalization

下载: 全尺寸图片幻灯片

图 2 本文算法流程图

Figure 2. The algorithm flowchart of this article

下载: 全尺寸图片幻灯片

图 3 Camp系列图像的融合结果

Figure 3. The fusion images of camp series

下载: 全尺寸图片幻灯片

图 4 tree系列图像的融合结果

Figure 4. The fusion images of tree series

下载: 全尺寸图片幻灯片

表 1 不同算法客观评估指标值

Table 1. Values of objective evaluation index for different algorithms

Algorithm	Camp			Tree
Algorithm	IE	Mean	AG	IE	Mean	AG
Infrared	6.64	94.16	0.0288	6.09	97.76	0.0288
Visible	6.97	88.66	0.0288	6.24	169.29	0.0157
Classical weighted average	5.64	90.17	0.0173	2.57	124.50	0.0085
PCA	6.27	96.22	0.0220	5.95	133.52	0.0151
The article	7.05	121.24	0.0309	6.40	189.94	0.0182

下载: 导出CSV

参考文献(12)

[1]	甄媚. 可见光图像与红外图像融合算法研究[D]. 西安: 西安科技大学, 2019. ZHEN Mei. Research on visible image and infrared image fusion algorithm[D]. Xi'an: Xi'an University of Science and Technology, 2019.
[2]	周渝人. 红外与可见光图像融合算法研究[D]. 长春: 中国科学院研究生院(长春光学精密机械与物理研究所), 2014. ZHOU Yuren. Research on infrared and visible light image fusion algorithm[D]. Changchun: Graduate School of Chinese Academy of Sciences (Changchun Institute of Optics, Fine Mechanics and Physics), 2014.
[3]	LI Hui, QI Xianbiao, XIE Wuyuan. Fast infrared and visible image fusion with structural decomposition[J]. Knowledge-Based Systems, 2020, 204: 106182. doi: 10.1016/j.knosys.2020.106182
[4]	赵娟, 孙澎涛, 吴粉侠, 等. 基于像素级的图像融合[J]. 长春工程学院学报: 自然科学版, 2011, 12(2): 106-108, 112. https://www.cnki.com.cn/Article/CJFDTOTAL-CGCZ201102029.htm ZHAO Juan, SUN Pengtao, WU Fenxia, et al. Pixel-level image fusion[J]. Journal of Changchun Institute of Technology: Natural Science Edition, 2011, 12(2): 106-108, 112. https://www.cnki.com.cn/Article/CJFDTOTAL-CGCZ201102029.htm
[5]	曲杨, 许卫东, 杨骏堂, 等. 一种可见光和红外图像加权融合最佳权值因子的确定方法[J]. 电子世界, 2017(13): 12-14. https://www.cnki.com.cn/Article/CJFDTOTAL-ELEW201713014.htm QU Yang, XU Weidong, YANG Juntang, et al. A method for determining the optimal weight factor for the weighted fusion of visible and infrared images[J]. The World of Electronics, 2017(13): 12-14. https://www.cnki.com.cn/Article/CJFDTOTAL-ELEW201713014.htm
[6]	刘成云, 常发亮, 刘春生, 等. 区域特征动态加权的IHS小波遥感图像融合[J]. 计算机工程, 2012, 38(8): 198-200. doi: 10.3969/j.issn.1000-3428.2012.08.065 LIU Chengyun, CHANG Faliang, LIU Chunsheng, et al. Fusion of IHS wavelet remote sensing images dynamically weighted by regional features[J]. Computer Engineering, 2012, 38(8): 198-200. doi: 10.3969/j.issn.1000-3428.2012.08.065
[7]	TU Teming, SU Shunchi, SHYU Hsuen Chyun. A New Look at HIS-like Image Fusion Methods[J]. Information Fusion, 2001, 2(3): 177-186. doi: 10.1016/S1566-2535(01)00036-7
[8]	Rajenda Pandit Desale, Sarita V Verma. Study and analysis of PCA, DCT & DWT based image fusion techniques[C]//International Conference on Signal Processing, Image Processing and Pattern Recognition, 2013: 1-4.
[9]	潘梅森, 汤井田, 杨晓利. 采用PCA和PSNR的医学图像配准[J]. 红外与激光工程, 2011, 40(2): 355-364. doi: 10.3969/j.issn.1007-2276.2011.02.035 PAN Meisun, TANG Jingtian, YANG Xiaoli. Medical image registration using PCA and PSNR[J]. Infrared and Laser Engineering, 2011, 40(2): 355-364. doi: 10.3969/j.issn.1007-2276.2011.02.035
[10]	吴粉侠, 李红, 李洪星. 基于NSCT变换和PCA的图像融合算法[J]. 航空计算技术, 2015, 45(3): 47-51. doi: 10.3969/j.issn.1671-654X.2015.03.012 WU Fenxia, LI Hong, LI Hongxing. Image fusion algorithm based on NSCT transform and PCA[J]. Aeronautical Computing Technology, 2015, 45(3): 47-51. doi: 10.3969/j.issn.1671-654X.2015.03.012
[11]	周琴. 矩阵特征值和特征向量在实际中的应用及其实现[J]. 高师理科学刊, 2019, 39(7): 8-10. https://www.cnki.com.cn/Article/CJFDTOTAL-GLKX201907003.htm ZHOU Qin. Application of matrix eigenvalues and eigenvectors in practice and their implementation[J]. Journal of Higher Learning Science, 2019, 39(7): 8-10. https://www.cnki.com.cn/Article/CJFDTOTAL-GLKX201907003.htm
[12]	闵超. 关于矩阵特征值有关性质的探讨——线性代数教学思考[J]. 教育教学论坛, 2019(24): 190-191. https://www.cnki.com.cn/Article/CJFDTOTAL-JYJU201924083.htm MIN Chao. Discussion on the properties of matrix eigenvalues -linear algebra teaching thinking [J]. The Altar of Education and Teaching, 2019(24): 190-191. https://www.cnki.com.cn/Article/CJFDTOTAL-JYJU201924083.htm