Infrared and Visible Image Fusion Algorithm Based on Gaussian Fuzzy Logic and Adaptive Dual-Channel Spiking Cortical Model
-
摘要: 为了克服当前的红外与可见光图像融合算法存在着目标不够突出、纹理细节丢失等现象,本文提出了一种基于高斯模糊逻辑和自适应双通道脉冲发放皮层模型(Adaptive Dual-Channel Spiking Cortical Model, ADCSCM)的红外与可见光图像融合算法。首先,使用非下采样剪切波变换(Non-Subsampled Sheartlet Transform, NSST)将源图像分解为低频和高频部分。其次,结合新拉普拉斯能量和(New Sum of Laplacian, NSL)与高斯模糊逻辑,设定双阈值来指导低频部分进行融合;同时,采用基于ADCSCM的融合规则来指导高频部分进行融合。最后,使用NSST逆变换进行重构来获取融合图像。实验结果表明,本文算法主观视觉效果最佳,并在互信息、信息熵和标准差3项指标上高于其他7种融合算法,能够有效突出红外目标、保留较多纹理细节,提高融合图像的质量。
-
关键词:
- 图像融合 /
- 非下采样剪切波变换 /
- 高斯模糊逻辑 /
- 自适应双通道脉冲发放皮层模型
Abstract: To overcome the shortcomings of current infrared and visible image fusion algorithms, such as non-prominent targets and the loss of many textural details, a novel infrared and visible image fusion algorithm based on Gaussian fuzzy logic and the adaptive dual-channel spiking cortical model (ADCSCM) is proposed in this paper. First, the source infrared and visible images are decomposed into low- and high-frequency parts by non-subsampled shearlet transform (NSST). Then, these are combined with the new sum of the Laplacian and Gaussian fuzzy logic, and dual thresholds are set to guide the fusion of the low-frequency part; simultaneously, the fusion rule based on the ADCSCM is used to guide the fusion of the high-frequency part. Finally, the fused low- and high-frequency parts are reconstructed using inverse NSST to obtain the fused image. The experimental results show that the proposed algorithm has the best subjective visual effect and is better than the other seven fusion algorithms in terms of mutual information, information entropy, and standard deviation. Furthermore, the proposed algorithm can effectively highlight the infrared target, retain more textural details, and improve the quality of the fused image. -
表 1 4组融合图像的客观评价结果
Table 1. The objective evaluation results of four groups of fused images
Fused
imagesEvaluation indexes Algorithms CVT NSCT GTF NSCT-PCNN NSST-PAPCNN MS-WLS MLGCF Proposed Camp MI 1.3967 1.4703 1.9961 1.6344 1.9792 1.5511 1.7092 2.2472 IE 6.5574 6.5693 6.6812 6.8681 6.8064 6.6214 6.6152 7.1566 SF 12.2275 12.2860 8.8771 11.6638 10.5236 13.2651 12.7512 12.9934 SD 27.1526 27.3415 27.0939 31.4014 30.2752 28.5545 29.2437 38.8731 VIFF 0.3606 0.4256 0.2257 0.3611 0.3716 0.4692 0.4587 0.4724 Lake MI 1.5413 1.6058 2.0167 2.1878 2.2921 2.0636 2.3721 3.9960 IE 6.6745 6.6764 6.6217 7.2516 7.1673 7.0032 7.0096 7.4731 SF 11.8183 11.7529 9.9321 12.2781 8.7916 12.2331 11.2376 12.1353 SD 27.1584 27.5441 40.4490 39.8795 43.4509 35.9000 35.0912 49.5824 VIFF 0.3260 0.3687 0.1731 0.3967 0.2784 0.4265 0.3977 0.4040 Flower MI 3.3300 3.5893 3.1504 3.6886 3.9911 3.8955 3.9984 4.3305 IE 6.5636 6.5577 6.2639 6.7200 6.8380 6.6259 6.6323 6.8793 SF 20.6859 21.3924 18.3972 20.3276 19.6811 21.6768 22.4519 22.1945 SD 36.2790 37.3107 36.3495 41.2683 41.5738 38.8609 39.5655 42.9559 VIFF 0.7544 0.8101 0.6731 0.8449 0.8452 0.7901 0.7841 0.9164 Bench MI 1.7790 1.8198 1.5464 3.5589 2.3970 2.3330 2.8215 3.9774 IE 6.9686 6.9609 6.7781 7.4965 7.3619 7.1646 7.1909 7.6089 SF 23.1776 23.2413 21.8150 23.4501 21.3190 26.3591 23.4811 23.6494 SD 34.9933 35.2022 30.8383 59.3188 50.2010 48.4621 49.5238 63.2357 VIFF 0.2333 0.2529 0.1260 0.2711 0.2646 0.4007 0.3662 0.2882 -
[1] 刘佳, 李登峰. 马氏距离与引导滤波加权的红外与可见光图像融合[J]. 红外技术, 2021, 43(2): 162-169. http://hwjs.nvir.cn/article/id/56484763-c7b0-4273-a087-8d672e8aba9aLIU Jia, LI Dengfeng. Infrared and visible light image fusion based on mahalanobis distance and guided filter weight-ing[J]. Infrared Technology, 2021, 43(2): 162-169. http://hwjs.nvir.cn/article/id/56484763-c7b0-4273-a087-8d672e8aba9a [2] 江泽涛, 何玉婷, 张少钦. 一种基于对比度增强和柯西模糊函数的红外与弱可见光图像融合算法[J]. 光子学报, 2019, 48(6): 149-158. https://www.cnki.com.cn/Article/CJFDTOTAL-GZXB201906019.htmJIANG Zetao, HE Yuting, ZHANG Shaoqin. Infrared and low-light-level visible image fusion algorithm based on contrast enhancement and cauchy fuzzy function[J]. Acta Photonica Sinica, 2019, 48(6): 149-158. https://www.cnki.com.cn/Article/CJFDTOTAL-GZXB201906019.htm [3] MA J, ZHOU Z, WANG B, et al. Infrared and visible image fusion based on visual saliency map and weighted least square optimization[J]. Infrared Physics & Technology, 2017, 82: 8-17. [4] 王建, 吴锡生. 基于改进的稀疏表示和PCNN的图像融合算法研究[J]. 智能系统学报, 2019, 14(5): 922-928. https://www.cnki.com.cn/Article/CJFDTOTAL-ZNXT201905011.htmWANG Jian, WU Xisheng. Image fusion based on the improved sparse representation and PCNN[J]. CAAI Transactions on Intelligent Systems, 2019, 14(5): 922-928. https://www.cnki.com.cn/Article/CJFDTOTAL-ZNXT201905011.htm [5] LIU Z, FENG Y, CHEN H, et al. A fusion algorithm for infrared and visible based on guided filtering and phase congruency in NSST domain[J]. Optics & Lasers in Engineering, 2017, 97: 71-77. [6] 邓立暖, 尧新峰. 基于NSST的红外与可见光图像融合算法[J]. 电子学报, 2017, 45(12): 2965-2970. doi: 10.3969/j.issn.0372-2112.2017.12.019DENG Linuan, YAO Xinfeng. Research on the fusion algorithm of infrared and visible images based on non-subsampled shearlet transform[J]. Acta Electronica Sinica, 2017, 45(12): 2965-2970. doi: 10.3969/j.issn.0372-2112.2017.12.019 [7] 王聪, 钱晨, 孙伟, 等. 基于SCM和CST的红外与可见光图像融合算法[J]. 红外技术, 2016, 38(5): 396-402. http://hwjs.nvir.cn/article/id/hwjs201605007WANG Cong, QIAN Chen, SUN Wei, et al. Infrared and visible images fusion based on SCM and CST[J]. Infrared Technology, 2016, 38(5): 396-402. http://hwjs.nvir.cn/article/id/hwjs201605007 [8] TAN W, ZHOU H, SONG J, et al. Infrared and visible image perceptive fusion through multi-level Gaussian curvature filtering image decomposition[J]. Applied Optics, 2019, 58(12): 3064-3073. doi: 10.1364/AO.58.003064 [9] 冯贺, 李立, 赵凯. 基于拉普拉斯分解耦合亮度调节的可见光与红外图像融合算法[J]. 电子测量与仪器学报, 2020, 34(10): 91-97. https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY202010011.htmFENG He, LI Li, ZHAO Kai. Fusion algorithm of visible and infrared image based on Laplace decomposition coupled with brightness adjustment[J]. Journal of Electronic Measurement and Instrument, 2020, 34(10): 91-97. https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY202010011.htm [10] GUO K, LABATE D. Optimally sparse multidimensional representation using shearlets[J]. SIAM Journal on Mathematical Analysis, 2007, 39(1): 298-318. doi: 10.1137/060649781 [11] 焦姣, 吴玲达. 向导滤波和NSST相结合的多光谱与全色图像融合算法[J]. 通信学报, 2018, 39(S2): 79-87. https://www.cnki.com.cn/Article/CJFDTOTAL-TXXB2018S2012.htmJIAO Jiao, WU Lingda. Multispectral and panchromatic images fusion method based on guided filter and NSST[J]. Journal on Communications, 2018, 39(S2): 79-87. https://www.cnki.com.cn/Article/CJFDTOTAL-TXXB2018S2012.htm [12] ZHAN K, ZHANG H, MA Y. New spiking cortical model for invariant texture retrieval and image processing[J]. IEEE Transactions on Neural Networks, 2009, 20(12): 1980-1986. doi: 10.1109/TNN.2009.2030585 [13] ZHAO C, HUANG Y, QIU S. Infrared and visible image fusion algorithm based on saliency detection and adaptive double-channel spiking cortical model[J]. Infrared Physics & Technology, 2019, 102: 102976. [14] 罗娟, 王立平, 谭云兰. 二代Curvelet变换耦合细节度量模型的遥感图像融合算法[J]. 电子测量与仪器学报, 2019, 33(7): 129-136. https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY201907017.htmLUO Juan, WANG Liping, TAN Yunlan. Remote sensing image fusion method using second generation curvelet transform coupled with detail metric model[J]. Journal of Electronic Measurement and Instrument, 2019, 33(7): 129-136. https://www.cnki.com.cn/Article/CJFDTOTAL-DZIY201907017.htm [15] 苏金凤, 张贵仓, 汪凯. 结合鲁棒主成分分析和非下采样轮廓波变换的红外与可见光图像的压缩融合[J]. 激光与光电子学进展, 2020, 57(4): 84-93. https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ202004008.htmSU J F, ZHANG G C, WANG K. Compressed fusion of infrared and visible images combining robust principal component analysis and non-subsampled contour transform[J]. Laser & Optoelectronics Progress, 2020, 57(4): 84-93. https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ202004008.htm [16] YIN S, CAO L, TAN Q, et al. Infrared and visible image fusion based on NSCT and fuzzy logic[C]//Proceedings of the 2010 IEEE International Conference on Mechatronics and Automation, 2010: 671-675. [17] 朱攀, 黄战华. 基于二维经验模态分解和高斯模糊逻辑的红外与可见光图像融合[J]. 光电子·激光, 2017, 28(10): 1156-1162. https://www.cnki.com.cn/Article/CJFDTOTAL-GDZJ201710016.htmZHU Pan, HUANG Zhanhua. Fusion of infrared and visible images based on BEMD and GFL[J]. Journal of Optoelectronics · Laser, 2017, 28(10): 1156-1162. https://www.cnki.com.cn/Article/CJFDTOTAL-GDZJ201710016.htm [18] 闫利, 向天烛. NSCT域内结合边缘特征和自适应PCNN的红外与可见光图像融合[J]. 电子学报, 2016, 44(4): 761-766. doi: 10.3969/j.issn.0372-2112.2016.04.002YAN Li, XIANG Tianzhu. Fusion of infrared and visible based on edge feature and adaptive PCNN in NSCT domain[J]. Acta Electronica Sinica, 2016, 44(4): 761-766. doi: 10.3969/j.issn.0372-2112.2016.04.002 [19] 侯瑞超, 周冬明, 聂仁灿, 等. 结合HSI变换与双通道脉冲发放皮层的彩色多聚焦图像融合[J]. 云南大学学报: 自然科学版, 2019, 41(2): 245-252. https://www.cnki.com.cn/Article/CJFDTOTAL-YNDZ201902006.htmHOU Ruichao, ZHOU Dongming, NIE Rencan, et al. Multi-focus color image fusion using HSI transform and dual channel spiking cortical model[J]. Journal of Yunnan University: Natural Sciences Edition, 2019, 41(2): 245-252. https://www.cnki.com.cn/Article/CJFDTOTAL-YNDZ201902006.htm [20] Nencini F, Garzelli A, Baronti S, et al. Remote sensing image fusion using the curvelet transform[J]. Information Fusion, 2007, 8(2): 143-156. doi: 10.1016/j.inffus.2006.02.001 [21] ZHANG Q, Guo B. Multifocus image fusion using the nonsubsampled contourlet transform[J]. Signal Process, 2009, 89(7): 1334-1346. doi: 10.1016/j.sigpro.2009.01.012 [22] MA J, CHEN C, LI C, et al. Infrared and visible image fusion via gradient transfer and total variation minimization[J]. Information Fusion, 2016, 31: 100-109. doi: 10.1016/j.inffus.2016.02.001 [23] QU X, YAN J, XIAO H, et al. Image fusion algorithm based on spatial frequency-motivated pulse coupled neural networks in nonsubsampled contourlet transform domain[J]. Acta Automatica Sinica, 2008, 34(12): 1508-1514. doi: 10.1016/S1874-1029(08)60174-3 [24] YIN M, LIU X, LIU Y, et al. Medical image fusion with parameter-adaptive pulse coupled neural network in nonsubsampled shearlet transform domain[J]. IEEE Transactions on Instrumentation and Measurement, 2019, 68(1): 49-64. doi: 10.1109/TIM.2018.2838778