A Novel Approach for Restoration of Low-rank Information from Remote Sensing Images via Matrix Completion

doi:10.13485/j.cnki.11-2089.2014.0150

Abstract

Abstract: This paper puts forward a novel approach for restoration of low-rank information from RS images based on matrix completion, and carried out some denoising and inpainting experiments using the singular value thresholding operator through determinate sampling and warm starting. The results indicate that the effect of our method is dominant when addressing the recovery of missing information caused by polluting and sheltering, and moreover, the approach can preserve details and textures in the images and make structures coherent while restoring original images, which shows great potential in the application of RS-image denoising and thick clouds removal. Especially when images possess low-rank characteristics such as similar structures and regular textures, the performance of the approach proposed will be better.

Key words: remote sensing image restoration, low-rank information recovery, matrix completion, singular value thresholding, thick clouds removal

CLC Number:

TP751
P237

MENG Fan, YANG Xiaomei, ZHOU Chenghu. A Novel Approach for Restoration of Low-rank Information from Remote Sensing Images via Matrix Completion[J]. Acta Geodaetica et Cartographica Sinica, 2014, 43(12): 1245-1251,1273.

References

[1] CANDES E J, RECHT B. Exact Matrix Completion via Convex Optimization[J]. Foundations of Computational Mathematics, 2009, 9(6): 717-772.
[2] CAI J, CANDES E J, SHEN Z. A Singular Value Thresholding Algorithm for Matrix Completion[J]. SIAM Journal on Optimization, 2010, 20(4): 1956-1982.
[3] PERONA P, MALIK J. Scale-space and Edge Detection Using Anisotropic Diffusion[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(7): 629-639.
[4] ALVAREZ L, MOREL J M. Formalization and Computational Aspects of Image Analysis[J]. Acta Numerica, 1994(3): 1-59.
[5] YOU Y L, KAVEH M. Fourth-order Partial Differential Equations for Noise Removal[J]. IEEE Transactions on Image Processing, 2000, 9(10): 1723-1729.
[6] RUDIN L, OSHER S, FATIMI E. Nonlinear Total Variation Based Noise Removal Algorithms[J]. Physisca D, 1992, 60: 259-268.
[7] GILBOA G, SOCHEN N, ZEEVI Y Y. Variational Denoising of Partly Textured Images by Spatially Varying Constraints[J]. IEEE Transactions on Image Processing, 2006, 15(8): 2281-2289.
[8] BUADES A, COLL B, MOREL J M. A Non-local Algorithm for Image Denoising[C]//Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE, 2005:60-65.
[9] GILBOA G, OSHER S. Nonlocal Operators with Applications to Image Processing[J]. SIAM Journal on Multiscale Modeling and Simulation, 2008, 7(3): 1005-1028.
[10] QIN C, WANG S Z, ZHANG X P. Simultaneous Inpainting for Image Structure and Texture Using Anisotropic Heat Transfer Model[J]. Multimedia Tools and Applications, 2012, 56(3): 469-483.
[11] DONG B, JI H, LI J, et al. Wavelet Frame Based Blind Image Inpainting[J]. Applied and Computational Harmonic Analysis, 2012, 32(2): 268-279.
[12] MAALOUF A, CARRE P, AUGEREAU B, et al. A Bandelet-based Inpainting Technique for Clouds Removal from Remotely Sensed Images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(7): 2363-2371.
[13] GABARDA S, CRISTOBAL G. Cloud Covering Denoising through Image Fusion[J]. Image and Vision Computing, 2007, 25: 523-530.
[14] LIANG Dong, KONG Jie, HU Gensheng, et al. The Removal of Thick Cloud and Cloud Shadow of Remote Sensing Image Based on Support Vector Machine[J]. Acta Geodaetica et Cartographica Sinica, 2012, 41(2): 225-231,231,238. (梁栋,孔颉,胡根生,等. 基于支持向量机的遥感影像厚云及云阴影去除[J]. 测绘学报,2012,41(2):225-231,238.)
[15] WANG Xianghai, ZHANG Hongwei, LI Fang. A PDE-based Hybrid Model for De-noising Remote Sensing Image with Gaussian and Salt-pepper Noise[J]. Acta Geodaetica et Cartographica Sinica, 2010, 39(3): 283-288. (王相海,张洪为,李放. 遥感图像高斯与椒盐噪声的PDE混合去噪模型研究[J]. 测绘学报,2010,39(3):283-288.)
[16] LIU Z, VANDENBERGHE L. Interior-point Method for Nuclear Norm Approximation with Application to System Identification[J]. SIAM Journal on Matrix Analysis and Applications, 2009, 31(3): 1235-1256.
[17] BERTALMIO M, SAPIRO G, CASELLES V, et al. Image Inpainting[C]//Proceedings of ACM SIGGRAPH.Chicago: ACM, 2000: 417-424.
[18] ZHANG Z, GANESH A, LIANG X, et al. TILT: Transform Invariant Low-rank Textures[J]. International Journal of Computer Vision, 2012, 99(1): 1-24.
[19] JI H, LIU C, SHEN Z, et al. Robust Video Denoising Using Low Rank Matrix Completion[C]//Proceedings of IEEE Conference on CVPR.[S.l.]:IEEE, 2010: 1791-1798.
[20] YIN W, OSHER S, GOLDFARB D, et al. Bregman Iterative Algorithms for l₁-minimization with Applications to Compressed
[21] ZHANG H, CHENG L, ZHU W. Nuclear Norm Regularization with a Low-rank Constraint for Matrix Completion[J]. Inverse Problems, 2010, 26(11): 115009-115023.
[22] ELAD M, STARCK J L, QUERRE P, et al. Simultaneous Cartoon and Texture Image Inpaiting Using Morphological Component Analysis (MCA) [J]. Applied and Computational Harmonic Analysis, 2005, 19(3): 340-358.
[23] LI Zhidan, HE Hongjie, YIN Zhongke, et al. Adaptive Image Inpainting Algorithm Based on Patch Structure Sparsity[J]. Acta Electronica Sinica, 2013, 41(3): 549-554. (李志丹,和红杰,尹忠科,等. 基于块结构稀疏度的自适应图像修复算法[J]. 电子学报,2013,41(3):549-554.)
[24] JUNG M, BRESSON X, CHAN T F, et al. Nonlocal Mumford-Shah Regularizers for Color Image Restoration[J]. IEEE Transactions on Image Processing, 2011, 20(6): 1583-1598.
[25] CANDES E J, TAO T. The Power of Convex Relaxation: Near-optimal Matrix Completion[J]. IEEE Transactions on Information Theory, 2010, 56(5): 2053-2080.
[26] ERIKSSON A, VAN DEN HENGEL A. Efficient Computation of Robust Low-rank Matrix Approximations in the Presence of Missing Data Using the l₁-norm[C]//Proceedings of IEEE Conference on CVPR.[S.l.]:IEEE,2010: 771-778.