多级方向引导滤波器及其在多传感器图像融合中的应用
|
摘要
基于多级方向引导滤波器,提出一种图像多尺度几何分析方法,并将其应用于多传感器图像融合中.首先利用引导滤波器对图像进行多级边缘保持分解,得到一个近似子带和多个不同尺度上的细节子带;然后采用楔形小尺寸方向剪切滤波器对细节子带进行方向分析,在不同尺度上生成多个方向子带,根据近似子带和方向细节子带所具有的不同物理意义,分别采用不同的融合准则对分解后的系数进行合并处理;最后通过对合并后的系数进行简单的叠加计算获得重构图像.该方法有效解决了在其他多尺度分解中滤波器缺乏自适应性和图像分析不具备平移不变性的问题.多组图像融合实验结果表明,在图像融合过程中,该方法的性能优于已有的其他典型多尺度分解方法.
We proposed an image multi-scale geometrical analysis method based on multistage directional guided filter,and applied it to the multi-sensor images fusion.Firstly,using the guided filter,an approximate sub-band and some detail sub-bands at the different scales were obtained by multistage edge-preserving decomposition of the image.Secondly,directional analysis of detail sub-bands was carried out by using wedge-shaped small size directional shear filter, multiple directional sub-bands were generated at the different scales.According to the different physical meanings of approximate sub-bands and the directional detail sub-bands,the different fusion criteria were used to merge the decomposed coefficients respectively.Finally,the reconstructed image was obtained by simple superposition calculation of the merged coefficients.This method effectively solved the problems that filters lacked self-adaptability and image analysis did not have translation invariancein the other multi-scale decomposition.The experimental results of multi-group image fusion show that the performance of this method is better than other typical multi-scale decomposition methods in the process of image fusion.
We proposed an image multi-scale geometrical analysis method based on multistage directional guided filter,and applied it to the multi-sensor images fusion.Firstly,using the guided filter,an approximate sub-band and some detail sub-bands at the different scales were obtained by multistage edge-preserving decomposition of the image.Secondly,directional analysis of detail sub-bands was carried out by using wedge-shaped small size directional shear filter, multiple directional sub-bands were generated at the different scales.According to the different physical meanings of approximate sub-bands and the directional detail sub-bands,the different fusion criteria were used to merge the decomposed coefficients respectively.Finally,the reconstructed image was obtained by simple superposition calculation of the merged coefficients.This method effectively solved the problems that filters lacked self-adaptability and image analysis did not have translation invariancein the other multi-scale decomposition.The experimental results of multi-group image fusion show that the performance of this method is better than other typical multi-scale decomposition methods in the process of image fusion.
引文
[1]LI Shutao,KANG Xudong,FANG Leyuan,et al.Pixel-Level Image Fusion:A Survey of the State of the Art[J].Information Fusion,2017,33(1):100-112.
[2]管飚.基于小波变换的多聚焦图像融合方法[J].吉林大学学报(理学版),2017,55(4):915-920.(GUAN Biao.Multi-focus Image Fusion Method Based on Wavelet Transform[J].Journal of Jilin University(Science Edition),2017,55(4):915-920.)
[3]TIAN Yingzhong,LUO Jie,ZHANG Wenjun,et al.Multifocus Image Fusion in Q-Shift DTCWT Domain Using Various Fusion Rules[J].Mathematical Problems in Engineering,2016(9):1-12.
[4]INDIRA K P,HEMAMALINI R R,NANDHITHA N M.Performance Evaluation of DWT,SWT and NSCT for Fusion of PET and CT Images Using Different Fusion Rules[J].Biomedical Research,2016,27(1):123-131.
[5]王昊鹏,刘泽乾,方兴,等.Curvelet域自适应脉冲耦合神经网络的图像融合方法[J].光电子·激光,2016,27(4):429-436.(WANG Haopeng,LIU Zeqian,FANG Xing,et al.Method for Image Fusion Based on Adaptive Pulse Coupled Neural Network in Curvelet Domain[J].Journal of Optoelectronics·Laser,2016,27(4):429-436.)
[6]WU Yiquan,WANG Zhilai.SAR and Infrared Image Fusion in Complex Contourlet Domain Based on Joint Sparse Representation[J].Journal of Radars,2017,6(4):349-358.
[7]PEJOSKI S,KAFEDZISKI V,GLEICH D.Compressed Sensing MRI Using Discrete Nonseparable Shearlet Transform and FISTA[J].IEEE Signal Processing Letters,2015,22(10):1566-1570.
[8]ZHANG Qiong,XAVIER M.An Adaptive Fusion Approach for Infrared and Visible Images Based on NSCT and Compressed Sensing[J].Infrared Physics&Technology,2016,74:11-20.
[9]CAI Jiajun,CHENG Qimin,PENG Mingjun,et al.Fusion of Infrared and Visible Images Based on Nonsubsampled Contourlet Transform and Sparse K-SVD Dictionary Learning[J].Infrared Physics&Technology,2017,82:85-95.
[10]KUTYNIOK G,LIM W Q.ShearLab 3D:Faithful Digital Shearlet Transforms Based on Compactly Supported Shearlets[J].ACM Transactions on Mathematical Software,2016,42(1):1-42.
[11]EASLEY G,LABATE D,LIM W Q.Sparse Directional Image Representations Using the Discrete Shearlet Transform[J].Applied&Computational Harmonic Analysis,2008,25(1):25-46.
[12]ZHAO Jufeng,FENG Huajun,XU Zhihai,et al.Detail Enhanced Multi-source Fusion Using Visual Weight Map Extraction Based on Multiscale Edge Preserving Decomposition[J].Optics Communications,2013,287(2):45-52.
[13]HU Jianwen,LI Shutao.The Multiscale Directional Bilateral Filter and Its Application to Multisensor Image Fusion[J].Information Fusion,2012,13(3):196-206.
[14]才华,陈广秋,刘广文,等.基于边界约束最优投影梯度NMF的TINST域图像融合方法[J].吉林大学学报(理学版),2016,54(5):1087-1095.(CAI Hua,CHEN Guangqiu,LIU Guangwen,et al.A Fusion Method Based on Bound-Constrained Optimization Using Projected Gradient for NMF in TINST Domain[J].Journal of Jilin University(Science Edition),2016,54(5):1087-1095.)
[15]HE Kaiming,SUN Jian,TANG Xiao’ou.Guided Image Filtering[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2013,35(6):1397-1409.
[16]TOET A,HOGERVORST M A.Multiscale Image Fusion through Guided Filtering[C/OL]//Proceeding Volume 9997,Target and Background SignaturesⅡ.2016-10-24.doi:10.1117/12.2239945.
[17]陈小潘,张凯,臧文乾,等.基于高提升滤波与Atrous小波分解的遥感图像融合算法[J].河南大学学报(自然科学版),2016,46(2):202-206.(CHEN Xiaopan,ZHANG Kai,ZANG Wenqian,et al.Remote Sensing Image Fusion Based on High-Boost Filtering andtrous Wavelet Transform[J].Journal of Henan University(Natural Science),2016,46(2):202-206.)
[18]DA C A,ZHOU J,DO M N.The Nonsubsampled Contourlet Transform:Theory,Design,and Applications[J].IEEE Transactions on Image Processing:A Publication of the IEEE Signal Processing Society,2006,15(10):3089-3101.
[19]STARCK J L,CANDES E J,DONOHO D L.The Curvelet Transform for Image Denoising[J].IEEETransactions on Image Processing:A Publication of the IEEE Signal Processing Society,2002,11(6):670-684.
[20]李颖奎,陈广秋,杨阳,等.多级方向加权最小二乘滤波器及其在多传感器图像融合中的应用[J].液晶与显示,2018,33(8):703-715.(LI Yingkui,CHEN Guangqiu,YANG Yang,et al.Multistage Directional Weighted Least Squares Filter and Its Application in Multi-sensor Image Fusion[J].Chinese Journal of Liquid Crystal and Displays,2018,33(8):703-715.)
[21]张小利.图像融合及其性能评估若干问题研究[D].长春:吉林大学,2016:93-94.(ZHANG Xiaoli.Study on Some Issues of Image Fusion and Performance Evaluation[D].Changchun:Jilin University,2016:93-94.)
[22]WANG S,REHMAN A,ZENG K,et al.SSIM-Motivated Two-Pass VBR Coding for High Efficiency Video Coding[J].IEEE Transactions on Circuits and Systems for Video Technology,2017,27(10):2189-2203.
[23]YOU Chunyan,LIU Yong,ZHAO Bo,et al.An Objective Quality Metric for Image Fusion Based on Mutual Information and Muti-scale Structural Similarity[J].Journal of Software,2014,9(4):1050-1054.
[2]管飚.基于小波变换的多聚焦图像融合方法[J].吉林大学学报(理学版),2017,55(4):915-920.(GUAN Biao.Multi-focus Image Fusion Method Based on Wavelet Transform[J].Journal of Jilin University(Science Edition),2017,55(4):915-920.)
[3]TIAN Yingzhong,LUO Jie,ZHANG Wenjun,et al.Multifocus Image Fusion in Q-Shift DTCWT Domain Using Various Fusion Rules[J].Mathematical Problems in Engineering,2016(9):1-12.
[4]INDIRA K P,HEMAMALINI R R,NANDHITHA N M.Performance Evaluation of DWT,SWT and NSCT for Fusion of PET and CT Images Using Different Fusion Rules[J].Biomedical Research,2016,27(1):123-131.
[5]王昊鹏,刘泽乾,方兴,等.Curvelet域自适应脉冲耦合神经网络的图像融合方法[J].光电子·激光,2016,27(4):429-436.(WANG Haopeng,LIU Zeqian,FANG Xing,et al.Method for Image Fusion Based on Adaptive Pulse Coupled Neural Network in Curvelet Domain[J].Journal of Optoelectronics·Laser,2016,27(4):429-436.)
[6]WU Yiquan,WANG Zhilai.SAR and Infrared Image Fusion in Complex Contourlet Domain Based on Joint Sparse Representation[J].Journal of Radars,2017,6(4):349-358.
[7]PEJOSKI S,KAFEDZISKI V,GLEICH D.Compressed Sensing MRI Using Discrete Nonseparable Shearlet Transform and FISTA[J].IEEE Signal Processing Letters,2015,22(10):1566-1570.
[8]ZHANG Qiong,XAVIER M.An Adaptive Fusion Approach for Infrared and Visible Images Based on NSCT and Compressed Sensing[J].Infrared Physics&Technology,2016,74:11-20.
[9]CAI Jiajun,CHENG Qimin,PENG Mingjun,et al.Fusion of Infrared and Visible Images Based on Nonsubsampled Contourlet Transform and Sparse K-SVD Dictionary Learning[J].Infrared Physics&Technology,2017,82:85-95.
[10]KUTYNIOK G,LIM W Q.ShearLab 3D:Faithful Digital Shearlet Transforms Based on Compactly Supported Shearlets[J].ACM Transactions on Mathematical Software,2016,42(1):1-42.
[11]EASLEY G,LABATE D,LIM W Q.Sparse Directional Image Representations Using the Discrete Shearlet Transform[J].Applied&Computational Harmonic Analysis,2008,25(1):25-46.
[12]ZHAO Jufeng,FENG Huajun,XU Zhihai,et al.Detail Enhanced Multi-source Fusion Using Visual Weight Map Extraction Based on Multiscale Edge Preserving Decomposition[J].Optics Communications,2013,287(2):45-52.
[13]HU Jianwen,LI Shutao.The Multiscale Directional Bilateral Filter and Its Application to Multisensor Image Fusion[J].Information Fusion,2012,13(3):196-206.
[14]才华,陈广秋,刘广文,等.基于边界约束最优投影梯度NMF的TINST域图像融合方法[J].吉林大学学报(理学版),2016,54(5):1087-1095.(CAI Hua,CHEN Guangqiu,LIU Guangwen,et al.A Fusion Method Based on Bound-Constrained Optimization Using Projected Gradient for NMF in TINST Domain[J].Journal of Jilin University(Science Edition),2016,54(5):1087-1095.)
[15]HE Kaiming,SUN Jian,TANG Xiao’ou.Guided Image Filtering[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2013,35(6):1397-1409.
[16]TOET A,HOGERVORST M A.Multiscale Image Fusion through Guided Filtering[C/OL]//Proceeding Volume 9997,Target and Background SignaturesⅡ.2016-10-24.doi:10.1117/12.2239945.
[17]陈小潘,张凯,臧文乾,等.基于高提升滤波与Atrous小波分解的遥感图像融合算法[J].河南大学学报(自然科学版),2016,46(2):202-206.(CHEN Xiaopan,ZHANG Kai,ZANG Wenqian,et al.Remote Sensing Image Fusion Based on High-Boost Filtering andtrous Wavelet Transform[J].Journal of Henan University(Natural Science),2016,46(2):202-206.)
[18]DA C A,ZHOU J,DO M N.The Nonsubsampled Contourlet Transform:Theory,Design,and Applications[J].IEEE Transactions on Image Processing:A Publication of the IEEE Signal Processing Society,2006,15(10):3089-3101.
[19]STARCK J L,CANDES E J,DONOHO D L.The Curvelet Transform for Image Denoising[J].IEEETransactions on Image Processing:A Publication of the IEEE Signal Processing Society,2002,11(6):670-684.
[20]李颖奎,陈广秋,杨阳,等.多级方向加权最小二乘滤波器及其在多传感器图像融合中的应用[J].液晶与显示,2018,33(8):703-715.(LI Yingkui,CHEN Guangqiu,YANG Yang,et al.Multistage Directional Weighted Least Squares Filter and Its Application in Multi-sensor Image Fusion[J].Chinese Journal of Liquid Crystal and Displays,2018,33(8):703-715.)
[21]张小利.图像融合及其性能评估若干问题研究[D].长春:吉林大学,2016:93-94.(ZHANG Xiaoli.Study on Some Issues of Image Fusion and Performance Evaluation[D].Changchun:Jilin University,2016:93-94.)
[22]WANG S,REHMAN A,ZENG K,et al.SSIM-Motivated Two-Pass VBR Coding for High Efficiency Video Coding[J].IEEE Transactions on Circuits and Systems for Video Technology,2017,27(10):2189-2203.
[23]YOU Chunyan,LIU Yong,ZHAO Bo,et al.An Objective Quality Metric for Image Fusion Based on Mutual Information and Muti-scale Structural Similarity[J].Journal of Software,2014,9(4):1050-1054.