Image Fusion Based on Random Projection and Sparse Representation

Abstract

Abstract:

In order to reduce the computational cost while maintaining the sufficient fusion quality, a novel notion of image fusion approach was explored combining fusion with data compression based on compressed sensing. First, the sensing data was compressed by random projection. Then, the sparse coefficients were obtained on compressed samples by sparse representation. Finally, the fusion coefficients were combined with the fusion impact factor and the fused image was reconstructed from the combined sparse coefficients. Experimental results validate its rationality and effectiveness, which can achieve comparable fusion quality on less compressed sensing data.

Key words: image fusion, compressed sensing, random projection, sparse representation

CLC Number:

TN 919.85

WANG Rui,DU Linfeng,CHEN Junli,WAN Wanggen. Image Fusion Based on Random Projection and Sparse Representation[J]. Journal of Shanghai Jiaotong University, 2014, 48(10): 1421-1427.

References

［1］张强，郭宝龙. 一种基于非采样Contourlet变换红外图像与可见光图像融合算法［J］. 红外与毫米波学报，2007，26(6)：476480.

ZHANG Qiang, GUO Baolong. Infrared and visible images fusion based on nonsubsampled contourlet transform ［J］. J Infrared Millin Waves, 2007, 26(6): 476480.

［2］Yun S, Kim J, Kim S. Image enhancement using a fusion framework of histogram equalization and laplacian pyramid ［J］. IEEE Transactions on Consumer Electronics, 2010, 56(4): 27632771.

［3］Wang H, Peng J, Wu W. Fusion algorithm for multisensor images based on discrete multiwavelet transform ［J］. IEEE Proc Vis Image Signal Process, 2002, 149(5): 283289.

［4］Ioannidou S, Karathanassi V. Investigation of the dualtree complex and shiftinvariant discrete wavelet transforms on quickbird image fusion ［J］. Geoscience and Remote Sensing Letters, 2007, 4(1): 166170.

［5］ZHANG Xiuqiong, CHEN Qingli, MEN Tao. Comparison of fusion methods for the infrared and color visible images ［C］∥Proc IEEE Conf on Computer Science and Information Technology. New York, USA: IEEE Press, 2009: 421424.

［6］WAN Tao, QIN Zengchang. An application of compressive sensing for image fusion ［J］. International Journal of Computer Mathematics, 2011, 88(18): 39153930.

［7］LUO Xiaoyan, ZHANG Jun, YANG Jingyu, et al. Image fusion in compressed sensing ［C］∥IEEE International Conference on Image Processing. Barcelona, Catalonia, Spain: IEEE Press, 2009: 22052208.

［8］HAN Juanjuan, Loffeld O, Hartmann K, et al. Multi image fusion based on compressive sensing ［C］∥IEEE International Conference on Audio Language and Image Processing. Shanghai: IEEE, 2010:14631469.

［9］Xi L, Qin S. Efficient fusion for infrared and visible images based on compressive sensing principle ［J］. IET Image Processing, 2011, 3(5): 141147.

［10］LIU Guidong, SHEN Yi. Ultrasonic image fusion using compressed sensing ［J］. Electronics Letters, 2012, 9(48): 11821184.

［11］YANG Bin, LI Shutao. Multifocus image fusion and restoration with sparse representation［J］. IEEE Transactions on Instrumentation and Measurement, 2010, 59(4): 884891.

［12］YIN Haitao, LI Shutao. Multimodal image fusion with joint sparsity model ［J］. Optical Engineering, 2011,50(6): 067007106700710.

［13］Tropp J A, Gilbert A C. Signal recovery from random measurements via orthogonal matching pursuit ［J］. IEEE Transactions on Information Theory, 2007, 53(12): 46554666.

［14］Candes E, Romberg J, Tao T. Stable signal recovery form incomplete and inaccurate measurements ［J］.Communications on Pure and Applied Mathematics, 2006, 59 (8): 12071223.

［15］Aharon M, Elad M, Bruckstein A M. KSVD: An algorithm for designing of overcomplete dictionary for sparse representation ［J］.IEEE Transactions on Signal Processing, 2006,54(11): 43114322.

［16］Qu G, Zhang D, Yan P. Information measure for performance of image fusion ［J］. Electron Letters, 2002, 38(7): 313315.

［17］Petrovi V, Xydeas C. On the effects of sensor noise in pixellevel image fusion performance ［C］∥Proc of 3rd Int Conf on Image Fusion. Paris, France: IEEE Press, 2000: 1419.

［18］Piella G, Heijmans H. A new quality metric for image fusion［C］∥Proc 1st Int Conf Image Processing. Barcelona, Catalonia, Spain: IEEE Press, 2003:173176.

［19］刘贵喜，赵曙光，杨万海. 基于梯度塔形分解的多传感器图像融合［J］. 光电子·激光， 2001， 12(3)： 293296.

LIU Guixi, ZHAO Shuguang, YANG Wanhai. Multisensor image fusion scheme based on gradient pyramid decomposition ［J］. Journal of Optoelectronics Laser, 2001, 12(3): 293296.

［20］Pajares G, Cruz J. A waveletbased image fusion tutorial ［J］. Pattern Recognition, 2004, 37(9): 18551872.

[1]	ZHANG Haoping, JIANG Yilin, LI Xiaoyu. Reconstruction of Antenna Radiation Pattern Based on Compressed Sensing [J]. J Shanghai Jiaotong Univ Sci, 2020, 25(6): 790-794.
[2]	ZHAO Ting, WANG Shentao, NIU Lin, XI Peili, CAI Yunze. Detection Algorithm of Ship Wake in SAR Images [J]. Journal of Shanghai Jiao Tong University, 2020, 54(12): 1259-1268.
[3]	JIANG Yilin* (蒋伊琳), WANG Haiyan (王海艳), SHAO Ran (邵然), ZHANG Jianfeng (张建峰). Infrared Image Reconstruction Based on Archimedes Spiral Measurement Matrix [J]. Journal of Shanghai Jiao Tong University (Science), 2019, 24(2): 204-208.
[4]	XU Xiaoling (徐晓玲), LIU Yiling (刘沂玲), LIU Qiegen (刘且根),LU Hongyang (卢红阳), ZHANG Minghui (张明辉). Gradient-Based Low Rank Method for Highly Undersampled Magnetic Resonance Imaging Reconstruction [J]. Journal of Shanghai Jiao Tong University (Science), 2018, 23(3): 384-.
[5]	WANG Xing,ZHOU Yipeng,TIAN Yuanrong,CHEN You,ZHOU Dongqing,HE Jiyuan. Sparse Decomposition for Frequency Modulation Radar Signal Based on Advanced Genetic Algorithm and SinChirplet Atom [J]. Journal of Shanghai Jiaotong University, 2017, 51(9): 1124-1130.
[6]	L ¨U Wentao1* (吕文涛), WANG Junfeng2 (王军锋), YU Wenxian2 (郁文贤), BAO Xiaomin1 (包晓敏). Range Profile Target Recognition Using Sparse Representation Based on Feature Space [J]. Journal of shanghai Jiaotong University (Science), 2017, 22(5): 615-623.
[7]	BAI Caijuan1,LIU Jing1,JIANG Xiaoyu2,ZHANG Guoxian1,HUANG Kaiyu1. The Reconstruction of Digital Holography Based on Iterative De-Noising Shrinkage-Thresholding Algorithm [J]. Journal of Shanghai Jiaotong University, 2017, 51(12): 1435-1442.
[8]	Ming-hui ZHANG, Xiao-yang HE, Shen-yuan DU, Qie-gen* LIU. A Generalized Two-Level Bregman Method with Dictionary Updating for Non-Convex Magnetic Resonance Imaging Reconstruction [J]. Journal of Shanghai Jiao Tong University(Science), 2015, 20(6): 660-669.
[9]	GUO Tianxu，CHEN Maoyin，ZHOU Donghua. A Fault Detection Method of Non-Gaussian Processes and Small Shift [J]. Journal of Shanghai Jiaotong University, 2015, 49(06): 775-779.