基于先验HMRF的MAP分块超分重建方法
|
摘要
针对高光谱图像应用最大后验概率(Maximum A Posteriori, MAP)超分重建后细节信息丢失严重问题,本文提出一种基于先验Huber马尔科夫随机场(Huber Markov Random Field, HMRF)模型的MAP分块超分辨率重建算法,以期提高图像超分重建质量。首先,利用主成分变换获取图像域的主要成分,在此基础上采用样条插值得到初始迭代图像;而后将初始图像域分为若干子块,在每个子块图像域上建立具有自适应阈值的HMRF模型,并结合子块图像域的保真项构建目标函数,采用梯度最快下降法求解此函数得到超分子块图像,将其重组,进而与插值后的次要成分图像相结合,最后应用主成分逆变换方法得到最终的高分辨率图像。为了验证本文算法的有效性与优越性,分别对模拟和真实图像采用本文方法和具有代表性的Tikhonov、总变分及传统HMRF模型超分重建方法进行实验对比,其中本文方法重建结果在峰值信噪比和结构相似性定量评价方面明显优于其他方法重建结果,在定性评价方面边缘结构及细节信息也更加明显,表明本文算法较为突出。
The detailed information in super-resolution reconstruction of hyper-spectral image is usually lost after using the Maximum A Posteriori(MAP). To improve the quality of a reconstructed image, this paper presents a MAP block super-resolution reconstruction algorithm based on the prior Huber Markov Random Field(HMRF) model. Firstly, Principal Component Analysis(PCA) is used to obtain the main components for a given hyper-spectral image, and then the initial image is obtained by spline interpolation technique. By using main components from the PCA operation, the proposed algorithm can not only effectively reduce the usage of computation memory but also reserve most of the information from the image. After calculating the Q statistic of the initial image, it is found that stratifying the hyper-spectral image into several(e.g., seven in this study) spatial heterogeneities is an effective way to characterize the complexity of the hyper-spectral image. To this end, a suitable partitioning scheme for obtaining an optimal super-resolution reconstructed image is adopted after comparing the reconstructed results by using different blocks with different sizes. As a result, the domain of the hyper-spectral image is split into several sub-blocks. The HMRF model with an adaptive threshold is then established for each sub-block image, and an objective function is defined by combining the fidelity terms of the sub-block images. The objective function can be solved by using the gradient descent method to obtain the high resolution sub-block images, which are then combined with the interpolated secondary component images.Though some cross artifacts occur in the process, they can be removed by extending edge based methods. The effective extending edge-based method is also proposed in this paper. Finally, the final high resolution image can be obtained by using the inverse PCA operation. In order to verify the validity and the superiority of the proposed algorithm, we test the proposed algorithm, the representative Tikhonov-based algorithm, total variationbased algorithm, and the traditional HMRF model-based super-resolution reconstruction method with the simulated and real images, respectively. The testing results show that the proposed algorithm is superior to other methods in the peak signal-to-noise ratio(PSNR) and the Structure Similarity Image Measure(SSIM).The qualitative evaluation indicated that the proposed method could obtain more obvious edge structure and detailed information at the same time.
The detailed information in super-resolution reconstruction of hyper-spectral image is usually lost after using the Maximum A Posteriori(MAP). To improve the quality of a reconstructed image, this paper presents a MAP block super-resolution reconstruction algorithm based on the prior Huber Markov Random Field(HMRF) model. Firstly, Principal Component Analysis(PCA) is used to obtain the main components for a given hyper-spectral image, and then the initial image is obtained by spline interpolation technique. By using main components from the PCA operation, the proposed algorithm can not only effectively reduce the usage of computation memory but also reserve most of the information from the image. After calculating the Q statistic of the initial image, it is found that stratifying the hyper-spectral image into several(e.g., seven in this study) spatial heterogeneities is an effective way to characterize the complexity of the hyper-spectral image. To this end, a suitable partitioning scheme for obtaining an optimal super-resolution reconstructed image is adopted after comparing the reconstructed results by using different blocks with different sizes. As a result, the domain of the hyper-spectral image is split into several sub-blocks. The HMRF model with an adaptive threshold is then established for each sub-block image, and an objective function is defined by combining the fidelity terms of the sub-block images. The objective function can be solved by using the gradient descent method to obtain the high resolution sub-block images, which are then combined with the interpolated secondary component images.Though some cross artifacts occur in the process, they can be removed by extending edge based methods. The effective extending edge-based method is also proposed in this paper. Finally, the final high resolution image can be obtained by using the inverse PCA operation. In order to verify the validity and the superiority of the proposed algorithm, we test the proposed algorithm, the representative Tikhonov-based algorithm, total variationbased algorithm, and the traditional HMRF model-based super-resolution reconstruction method with the simulated and real images, respectively. The testing results show that the proposed algorithm is superior to other methods in the peak signal-to-noise ratio(PSNR) and the Structure Similarity Image Measure(SSIM).The qualitative evaluation indicated that the proposed method could obtain more obvious edge structure and detailed information at the same time.
引文
[1]杨闫君,田庆久,占玉林,等.空间分辨率与纹理特征对多光谱遥感分类的影响[J].地球信息科学学报,2018,20(1):99-107.[Yang Y J,Tian Q J,Zhan Y L,et al.Effects of spatial resolution and texture features on multi-spectral remote sensing classificationp[J].Journal of Geo-information Science,2018,20(1):99-107.]
[2]童庆禧,张兵,郑兰芬.高光谱遥感:原理,技术与应用[M].北京:高等教育出版社,2006.[Tong Q L,Zhang B,Zheng L F.Hyperspectral remote sensing:principle,technology and application[M].Beijing:Higher Education Press,2006.]
[3]Borman S,Stevenson R L.Super-resolution from image sequences:A review[C].In proceedings of the 1998 Midwest Symposium on Circuits and Systems,1998:374-378.
[4]Park S C,Park M K,Kang M G.Super-resolution image reconstruction:A technical overview[J].IEEE Signal Processing Magazine,2003,20(3):21-36.
[5]黄淑英.基于空间域正则化方法的图像超分辨率技术研究[D].青岛:中国海洋大学,2013.[Huang S Y.Research on image super-resolution reconstruction based on spatial regularization technique[D].Qingdao:Ocean University of China,2013.]
[6]Farsiu S,Elad M,Milanfar P.A practical approach to super-resolution[C].Proceedings of SPIE 2006,6077:24-38.
[7]Zhang K,Gao X,Tao D,et al.Single image super-resolution with non-local means and steering kernel regression[J].IEEETransactions on Image Processing,2012,21(11):4544-4556.
[8]Capel D P,Zisserman A.Super-resolution from multiple views using learnt image models[C].IEEE Conference on Computer Vision and Pattern Recognition,2001,2:627-634.
[9]Stark H,Oskoui P.High resolution image recovery from image plane arrays,using convex projection[J].Journal of the Optical Society of America,1989,6(11):1715-1726.
[10]Patti A J,Sezan M I,Tekalp A M.Super-resolution video reconstruction with arbitrary sampling lattices and nonzero aperture time[J].IEEE Transactions on Image Processing,1997,6(8):1064-1076.
[11]Schuler J M,Howerd J G,Warren P R,etc.Resolution enhancement through TRRID processing[A].In Proceedings of SPIE-The International Society for Optical Engineering[C].San Jose,CA,United States,2002:872-876.
[12]Gao X,Zhang K,Tao D,et al.Image super-resolution with sparse neighbor embedding[J].IEEE Transactions on Image Processing,2012,21(7):3194-3205.
[13]Schultz R R,Stevenson R L.Extraction of high-resolution frames from video sequences[J].IEEE Transactions on Image Processing,1996,5(6):996-1011.
[14]吴志春,叶发旺,郭福生,等.主成分分析技术在遥感蚀变信息提取中的应用研究综述[J].地球信息科学学报,2018,20(11):1644-1656.[Wu Z C,Ye F W,Guo F S,et al.A review on application of techniques of principle component analysis on extracting alteration information of remote sensing[J].Journal of Geo-information Science,2018,20(11):1644-1656.]
[15]王崴,唐一平,任娟莉,等.一种改进的Harris角点提取算法[J].光学精密工程,2008(10):1995-2001.[Wang H,Tang Y P,Ren J L,et al.An improved algorithm for Harris corner detection[J].Optics and Precision Engineering,2008(10):1995-2001.]
[16]刘佳,傅卫平,王雯,等.基于改进SIFT算法的图像匹配[J].仪器仪表学报,2013,34(5):1107-1112.[Liu J,Fu WP,Wang W,et al.Image matching based on improved SIFT algorithm[J].Journal of Instrumentation,2013,34(5):1107-1112.]
[17]王思珺,赵建,韩希珍.基于仿射变换的快速全局运动估计算法[J].液晶与显示,2012,27(2):263-266.[Wang S Q,Zhao J,Han X Z.Fast global motion estimation algorithm based on affine transformation[J].Liquid Crystal And Display,2012,27(2):263-266.]
[18]张艳,王涛,徐青.基于HMRF先验模型的HBE卫星遥感图像超分辨率重建[J].武汉大学学报·信息科学版,2007,32(7):589-592.[Zhang Y,Wang T,Xu Q.HBE satellite super-resolution reconstruction with HMRF prior model[J].Journal of Wuhan University(Information Science Edition),2007,32(7):589-592.]
[19]刘薇.超分辨率图像重建关键问题研究[D].西安:西安理工大学,2013.[Liu W.Research on the key issues of super-resolution image reconstruction[D].Xi'an:Xi'an University of Technology,2013.]
[20]王涛,高新波,张都应.一种基于内容的图像质量评价测度[J].中国图象图形学报,2007,12(6):1002-1007.[Wang T,Gao X B,Zhang D Y.An objective content-based image quality assessment metric[J].Journal of Image and Graphics,2007,12(6):1002-1007.]
[21]Wang J F,Stein A,Gao B B,Ge Y.A review of spatial sampling[J].Spatial Statistics,2012,2:1-14.
[22]http://aviris.jpl.nasa.gov/.
[23]Wang J F,Zhang T L,Fu B J.A measure of spatial stratified heterogeneity[J].Ecological Indicators,2016,67:250-256.
[24]傅初黎,李洪芳,熊向团.不适定问题的迭代Tikhonov正则化方法[J].计算数学,2006(3):237-246.[Fu C L,Li HF Xiong X T.Iterative tikhonov regularization for illposed problems[J].Computational Mathematics,2006(3):237-246.]
[25]占美全,邓志良.基于L1范数的总变分正则化超分辨率图像重建[J].科学技术与工程,2010,10(28):6903-6906.[Zhan M Q,Deng Z L.L1 norm of total variation regularization based super-resolution reconstruction for images[J].Science Technology and Engineering,2010,10(28):6903-6906.]
[2]童庆禧,张兵,郑兰芬.高光谱遥感:原理,技术与应用[M].北京:高等教育出版社,2006.[Tong Q L,Zhang B,Zheng L F.Hyperspectral remote sensing:principle,technology and application[M].Beijing:Higher Education Press,2006.]
[3]Borman S,Stevenson R L.Super-resolution from image sequences:A review[C].In proceedings of the 1998 Midwest Symposium on Circuits and Systems,1998:374-378.
[4]Park S C,Park M K,Kang M G.Super-resolution image reconstruction:A technical overview[J].IEEE Signal Processing Magazine,2003,20(3):21-36.
[5]黄淑英.基于空间域正则化方法的图像超分辨率技术研究[D].青岛:中国海洋大学,2013.[Huang S Y.Research on image super-resolution reconstruction based on spatial regularization technique[D].Qingdao:Ocean University of China,2013.]
[6]Farsiu S,Elad M,Milanfar P.A practical approach to super-resolution[C].Proceedings of SPIE 2006,6077:24-38.
[7]Zhang K,Gao X,Tao D,et al.Single image super-resolution with non-local means and steering kernel regression[J].IEEETransactions on Image Processing,2012,21(11):4544-4556.
[8]Capel D P,Zisserman A.Super-resolution from multiple views using learnt image models[C].IEEE Conference on Computer Vision and Pattern Recognition,2001,2:627-634.
[9]Stark H,Oskoui P.High resolution image recovery from image plane arrays,using convex projection[J].Journal of the Optical Society of America,1989,6(11):1715-1726.
[10]Patti A J,Sezan M I,Tekalp A M.Super-resolution video reconstruction with arbitrary sampling lattices and nonzero aperture time[J].IEEE Transactions on Image Processing,1997,6(8):1064-1076.
[11]Schuler J M,Howerd J G,Warren P R,etc.Resolution enhancement through TRRID processing[A].In Proceedings of SPIE-The International Society for Optical Engineering[C].San Jose,CA,United States,2002:872-876.
[12]Gao X,Zhang K,Tao D,et al.Image super-resolution with sparse neighbor embedding[J].IEEE Transactions on Image Processing,2012,21(7):3194-3205.
[13]Schultz R R,Stevenson R L.Extraction of high-resolution frames from video sequences[J].IEEE Transactions on Image Processing,1996,5(6):996-1011.
[14]吴志春,叶发旺,郭福生,等.主成分分析技术在遥感蚀变信息提取中的应用研究综述[J].地球信息科学学报,2018,20(11):1644-1656.[Wu Z C,Ye F W,Guo F S,et al.A review on application of techniques of principle component analysis on extracting alteration information of remote sensing[J].Journal of Geo-information Science,2018,20(11):1644-1656.]
[15]王崴,唐一平,任娟莉,等.一种改进的Harris角点提取算法[J].光学精密工程,2008(10):1995-2001.[Wang H,Tang Y P,Ren J L,et al.An improved algorithm for Harris corner detection[J].Optics and Precision Engineering,2008(10):1995-2001.]
[16]刘佳,傅卫平,王雯,等.基于改进SIFT算法的图像匹配[J].仪器仪表学报,2013,34(5):1107-1112.[Liu J,Fu WP,Wang W,et al.Image matching based on improved SIFT algorithm[J].Journal of Instrumentation,2013,34(5):1107-1112.]
[17]王思珺,赵建,韩希珍.基于仿射变换的快速全局运动估计算法[J].液晶与显示,2012,27(2):263-266.[Wang S Q,Zhao J,Han X Z.Fast global motion estimation algorithm based on affine transformation[J].Liquid Crystal And Display,2012,27(2):263-266.]
[18]张艳,王涛,徐青.基于HMRF先验模型的HBE卫星遥感图像超分辨率重建[J].武汉大学学报·信息科学版,2007,32(7):589-592.[Zhang Y,Wang T,Xu Q.HBE satellite super-resolution reconstruction with HMRF prior model[J].Journal of Wuhan University(Information Science Edition),2007,32(7):589-592.]
[19]刘薇.超分辨率图像重建关键问题研究[D].西安:西安理工大学,2013.[Liu W.Research on the key issues of super-resolution image reconstruction[D].Xi'an:Xi'an University of Technology,2013.]
[20]王涛,高新波,张都应.一种基于内容的图像质量评价测度[J].中国图象图形学报,2007,12(6):1002-1007.[Wang T,Gao X B,Zhang D Y.An objective content-based image quality assessment metric[J].Journal of Image and Graphics,2007,12(6):1002-1007.]
[21]Wang J F,Stein A,Gao B B,Ge Y.A review of spatial sampling[J].Spatial Statistics,2012,2:1-14.
[22]http://aviris.jpl.nasa.gov/.
[23]Wang J F,Zhang T L,Fu B J.A measure of spatial stratified heterogeneity[J].Ecological Indicators,2016,67:250-256.
[24]傅初黎,李洪芳,熊向团.不适定问题的迭代Tikhonov正则化方法[J].计算数学,2006(3):237-246.[Fu C L,Li HF Xiong X T.Iterative tikhonov regularization for illposed problems[J].Computational Mathematics,2006(3):237-246.]
[25]占美全,邓志良.基于L1范数的总变分正则化超分辨率图像重建[J].科学技术与工程,2010,10(28):6903-6906.[Zhan M Q,Deng Z L.L1 norm of total variation regularization based super-resolution reconstruction for images[J].Science Technology and Engineering,2010,10(28):6903-6906.]
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |