结合FABEMD和改进的显著性检测的图像融合

doi:10.3969/j.issn.1001-506X.2020.02.06

摘要/Abstract

摘要：

针对红外与可见光图像融合中存在的显著目标不突出、对比度低、存在较多的伪影问题,提出了一种结合快速自适应二维经验模态分解(fast and adaptive bidimensional empirical mode decomposition, FABMED)和改进的显著性检测的图像融合算法。首先,通过FABEMD对红外和可见光图像进行多尺度分解得到对应的基础层和细节层。然后,对最大对称环绕显著性检测做暗抑制改进,将其用于基础层的融合上;结合改进的显著性检测和引导滤波,对细节层进行融合。最后,对各融合子图进行FABEMD逆变换重构出融合图像。与其他经典的融合算法相比,仿真实验验证了本文算法的有效性。

关键词: 图像融合, 快速自适应二维经验模态分解, 显著性检测, 引导滤波

Abstract:

Aiming at the problem that the significant targets are not prominent, the contrast is low, and there are many artifacts in infrared and visible image fusion, an image fusion algorithm combining fast and adaptive bidimensional empirical mode decomposition (FABMED) with improved visual saliency detection is proposed. First, the multi-scale decomposition of infrared and visible images is performed by FABEMD to obtain the corresponding base layer and detail layers. A dim suppression improvement is then performed on the maximum symmetric surround saliency detection, which is used for the fusion of the base layer. Combined with the improved saliency detection and guided filter, the detail layers are fused. To this end, the inverse FABEMD transform on each fusion sub-image is performed to reconstruct the fused image. Compared with other typical fusion algorithms, the simulation experiments verify the effectiveness of the proposed algorithm.

Key words: image fusion, fast and adaptive bidimensional empirical mode decomposition (FABEMD), saliency detection, guided filter

中图分类号:

TP391

安影, 范训礼, 陈莉, 刘佩. 结合FABEMD和改进的显著性检测的图像融合[J]. 系统工程与电子技术, 2020, 42(2): 292-300.

Ying AN, Xunli FAN, Li CHEN, Pei LIU. Image fusion combining FABEMD with improved saliency detection[J]. Systems Engineering and Electronics, 2020, 42(2): 292-300.

图/表 9

图1

图2

图3

图4

图5

图6

图7

图8

表1

参考文献 26

1	MA J Y , CHEN C , LI C , et al. Infrared and visible image fusion via gradient transfer and total variation minimization[J]. Information Fusion, 2016, 31 (C): 100- 109.
2	LI S T , KANG X , FANG L , et al. Pixel-level image fusion: a survey of the state of the art[J]. Information Fusion, 2017, 33 (C): 100- 112.
3	MA J Y , MA Y , LI C . Infrared and visible image fusion methods and applications: a survey[J]. Information Fusion, 2019, 45, 153- 178. doi: 10.1016/j.inffus.2018.02.004
4	刘斌, 付忠旺. 基于四通道不可分提升小波的多聚焦图像融合[J]. 系统工程与电子技术, 2018, 40 (2): 463- 471.
	LIU B , FU Z W . Multi-focus image fusion based on four-channel non- separable lifting wavelet[J]. Systems Engineering and Electronics, 2018, 40 (2): 463- 471.
5	邢雅琼, 王晓丹, 毕凯, 等. 基于NSCT和ICA的红外和可见光图像融合方法[J]. 系统工程与电子技术, 2013, 35 (11): 2251- 2257.
	XING Y Q , WANG X D , BI K , et al. Fusion technique for infrared and visible light images based on independent component analysis and non-subsampled contourlet transform[J]. Systems Engineering and Electronics, 2013, 35 (11): 2251- 2257.
6	LI M J, DONG Y B. Image fusion algorithm based on contrast pyramid and application[C]//Proc.of the International Conference on Mechatronic Sciences, Electric Engineering and Computer, 2013: 1342-1345.
7	QU X J, ZHANG F, ZHANG Y, et al.Method of dual-band infrared images fusion based on gradient pyramid decomposition[C]//Proc.of the IET International Conference on Information Science and Control Engineering, 2012: 1-4.
8	朱攀, 刘泽阳, 黄战华. 基于DTCWT和稀疏表示的红外偏振与光强图像融合[J]. 光子学报, 2017, 46 (12): 213- 221.
	ZHU P , LIU Z Y , HUANG Z H . Infrared polarization and intensity image fusion based on dual-tree complex wavelet transform and sparse representation[J]. Acta Photonica Sinica, 2017, 46 (12): 213- 221.
9	HUANG N E , SHEN Z , LONG S R , et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, 1998, 454 (1971): 903- 995. doi: 10.1098/rspa.1998.0193
10	BHUIYAN S M A , ADHAMI R R , KHAN J F . Fast and adaptive bidimensional empirical mode decomposition using order-statistics filter based envelope estimation[J]. Eurasip Journal on Advances in Signal Processing, 2008, 2008 (1): 1- 18.
11	林子慧, 魏宇星, 张建林, 等. 基于显著性图的红外与可见光图像融合[J]. 红外技术, 2019, 41 (7): 640- 645.
	LIN Z H , WEI Y X , ZHANG J L , et al. Image fusion of infrared and visible images based on saliency map[J]. Infrared Technology, 2019, 41 (7): 640- 645.
12	CHENG M M , MITRA N J , HUANG X , et al. Global contrast based salient region detection[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2015, 37 (3): 569- 582. doi: 10.1109/TPAMI.2014.2345401
13	ACHANTA R, ESTRADA F, WILS P, et al. Salient region detection and segmentation[C]//Proc.of the International Conference on Computer Vision Systems, 2008: 66-75.
14	ACHANTA R, HEMAMI S, ESTRADA F, et al. Frequency-tuned salient region detection[C]//Proc.of the IEEE International Conference on Computer Vision and Pattern Recognition, 2009: 1597-1604.
15	ZHAI Y, SHAH M. Visual attention detection in video sequences using spatiotemporal cues[C]//Proc.of the 14th ACM International Conference on Multimedia, 2006: 815-824.
16	ACHANTA R, SUSSTRUNK S. Saliency detection using maximum symmetric surround[C]//Proc.of the IEEE International Conference on Image Processing, 2010: 2653-2656.
17	LI S T , KANG X D , HU J W . Image fusion with guided filtering[J]. IEEE Trans.on Image Processing, 2013, 22 (7): 2864- 2875. doi: 10.1109/TIP.2013.2244222
18	NAIDU V P S . Image fusion technique using multi-resolution singular value decomposition[J]. Defence Science Journal, 2011, 61 (5): 479- 484. doi: 10.14429/dsj.61.705
19	LIU Y , WANG Z F . Simultaneous image fusion and denoising with adaptive sparse representation[J]. Image Processing IET, 2014, 9 (5): 347- 357.
20	KUMAR B K S . Image fusion based on pixel significance using cross bilateral filter[J]. Signal, Image and Video Processing, 2015, 9 (5): 1193- 1204. doi: 10.1007/s11760-013-0556-9
21	LIU Y , CHEN X , WARD R K , et al. Image fusion with convolutional sparse representation[J]. IEEE Signal Processing Letters, 2016, 23 (12): 1882- 1886. doi: 10.1109/LSP.2016.2618776
22	MA J Y , ZHOU Z Q , 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.
23	LI H, WU X J. Infrared and visible image fusion using latent low-rank representation[Online][2019-09-06].https: //arxiv.org/abs/1804.08992.
24	ROBERTS J W , ADRDT J A V . Assessment of image fusion procedures using entropy, image quality and multispectral classification[J]. Journal of Applied Remote Sensing, 2008, 2 (1): 023522. doi: 10.1117/1.2945910
25	QU G H , ZHANG D L , YAN P F . Information measure for performance of image fusion[J]. Electronics letters, 2002, 38 (7): 313- 315. doi: 10.1049/el:20020212
26	WANG Z , BOVIK A C , SHEIKH H R , et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Trans.on Image Processing, 2004, 13 (4): 600- 612. doi: 10.1109/TIP.2003.819861

融合图像	融合规则	算法
融合图像	融合规则	本文算法	MSVD	GF	CP	ASR	CBF	CSR	WLS	LatLRR
S1	EN	7.178 9	6.470 0	7.251 8	6.800 5	6.567 3	7.050 6	6.523 6	6.984 7	6.646 8
	SD	50.546 3	23.850 1	44.620 9	31.276 7	26.249 1	40.941 6	25.183 7	39.044 3	26.796 3
	MI	1.246 7	0.881 5	2.790 3	0.584 4	0.811 2	1.417 8	0.854 6	0.928 5	0.831 4
	SSIM	0.728 3	0.770 8	0.718 6	0.713 4	0.743 5	0.621 3	0.769 3	0.727 2	0.777 6
S2	EN	7.097 6	6.259 4	6.377 7	6.833 9	6.441 5	6.548 2	6.433 8	6.602 8	6.623 9
	SD	38.063 0	22.868 4	26.060 9	32.434 7	25.861 4	27.418 4	25.754 8	28.251 3	30.935 2
	MI	1.429 8	0.768 6	0.761 6	0.830 2	0.773 1	0.763 5	0.789 6	0.785 0	0.867 8
	SSIM	0.717 2	0.743 5	0.727 2	0.692 4	0.739 0	0.621 0	0.739 7	0.727 4	0.754 5
S3	EN	7.546 0	6.553 1	6.857 5	6.682 5	6.809 1	6.777 0	6.801 5	6.970 2	6.903 6
	SD	64.279 6	31.619 0	32.898 3	34.143 0	34.497 6	33.193 0	34.386 7	49.308 0	37.729 5
	MI	2.315 8	0.987 0	1.220 2	0.597 7	1.063 4	0.945 2	1.071 4	1.015 8	1.020 2
	SSIM	0.717 3	0.741 1	0.725 6	0.695 1	0.736 8	0.638 5	0.753 3	0.716 6	0.767 1
S4	EN	7.320 1	6.333 5	7.026 9	6.806 8	6.363 9	6.877 8	6.353 5	6.740 3	6.554 4
	SD	57.213 8	27.283 5	48.277 0	37.090 8	28.778 1	36.413 4	28.559 7	42.076 6	32.076 4
	MI	1.718 8	0.956 9	1.734 6	0.695 2	0.891 5	0.933 9	0.967 5	1.008 8	0.939 2
	SSIM	0.700 4	0.714 2	0.688 1	0.640 8	0.698 9	0.539 6	0.718 9	0.697 3	0.732 2
S5	EN	7.593 7	6.777 3	6.857 5	7.035 6	6.410 8	6.869 1	6.801 5	7.236 6	6.572 2
	SD	59.808 7	33.952 5	32.898 3	44.807 0	23.770 4	33.266 5	34.386 7	53.665 0	26.291 3
	MI	1.247 1	0.723 9	0.624 3	1.082 6	1.183 6	0.552 5	0.721 3	0.720 9	1.084 2
	SSIM	0.589 7	0.458 7	0.437 7	0.503 5	0.620 7	0.358 8	0.454 9	0.361 4	0.640 0

[1]	王健, 何自豪, 刘洁, 杨珂. 基于梯度域导向滤波器和改进PCNN的图像融合算法[J]. 系统工程与电子技术, 2022, 44(8): 2381-2392.
[2]	童莹萍, 全英汇, 冯伟, 邢孟道. 基于空谱信息协同与Gram-Schmidt变换的多源遥感图像融合方法[J]. 系统工程与电子技术, 2022, 44(7): 2074-2083.
[3]	方澄, 路稳, 姬菁颖, 宋玉蒙, 梁斐菲, 罗志伟. 基于外观相似性更新的相关滤波跟踪算法[J]. 系统工程与电子技术, 2022, 44(1): 117-126.
[4]	徐国明, 袁宏武, 薛模根, 王峰. 全偏振参量低秩稀疏分解伪彩色图像融合[J]. 系统工程与电子技术, 2020, 42(11): 2450-2460.
[5]	刘松涛, 姜康辉, 刘振兴. 基于区域协方差和目标度的航空侦察图像舰船目标检测[J]. 系统工程与电子技术, 2019, 41(5): 972-980.
[6]	宗静静, 邱天爽. 稀疏表示中稀疏系数的 l-1 范数的特性分析[J]. 系统工程与电子技术, 2019, 41(12): 2692-2696.
[7]	刘松涛, 刘振兴, 姜康辉. 基于模糊Renyi熵和区域增长的图像目标分割方法[J]. 系统工程与电子技术, 2018, 40(8): 1693-1701.
[8]	王晨, 樊养余. 基于动态指导滤波的显著性检测方法[J]. 系统工程与电子技术, 2018, 40(6): 1391-1397.
[9]	刘斌, 付忠旺. 基于四通道不可分提升小波的多聚焦图像融合[J]. 系统工程与电子技术, 2018, 40(2): 463-471.
[10]	常莉红, 冯象初, 张瑞. 四元数小波变换联合稀疏表示的图像融合[J]. 系统工程与电子技术, 2017, 39(7): 1633-1639.
[11]	王殿伟, 王晶, 许志杰, 刘颖. 一种光照不均匀图像的自适应校正算法[J]. 系统工程与电子技术, 2017, 39(6): 1383-1390.
[12]	赵蓝飞, 王爱丽, 王博, 吕鑫淼. 基于子图融合技术的图像增强算法[J]. 系统工程与电子技术, 2017, 39(12): 2840-2848.
[13]	朱文杰, 王广龙, 高凤岐, 乔中涛, 黄瑞. 引导滤波与视觉感知结合的自然场景轮廓提取[J]. 系统工程与电子技术, 2017, 39(1): 206-214.
[14]	胡晓伟, 童宁宁, 何兴宇, 雷腾, 王宇晨. 基于窄带雷达组网的高速自旋目标成像[J]. 系统工程与电子技术, 2016, 38(4): 792-798.
[15]	周志强，汪渤，李立广，李笋. 基于双边与高斯滤波混合分解的图像融合方法[J]. 系统工程与电子技术, 2016, 38(1): 8-13.