Study on super-resolution reconstruction algorithm based on sparse representation and dictionary learning for remote sensing image

Super-resolution image reconstruction plays a very important role in the interpretation of remote sensing images. Especially when the resolution of images is low, the size of the objects to be identified is close to the minimum resolution, and can be reconstructed by super-resolution better interpretation of the feature. In this paper, K-SVD algorithm is used to study the exampler of high resolution image library, and the dictionary of high resolution remote sensing image is obtained. The low resolution image is represented by high resolution dictionary, and the remote sensing reconstruction of remote sensing image is realized. Which improves the peak noise ratio and mean square error of the image, and has better performance than the interpolation algorithm. The method proposed in this paper has important significance and application prospect in remote sensing image application.

[1]  Wesley De Neve,et al.  Comparison of prediction schemes with motion information reuse for low complexity spatial scalability , 2005 .

[2]  Li Wei,et al.  Research on remote sensing image retrieval based on geographical and semantic features , 2009, 2009 International Conference on Image Analysis and Signal Processing.

[3]  Zhe L. Lin,et al.  Fast Image Super-Resolution Based on In-Place Example Regression , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Michael Elad,et al.  On Single Image Scale-Up Using Sparse-Representations , 2010, Curves and Surfaces.

[5]  Jiancheng Luo,et al.  Modified local variance based method for selecting the optimal spatial resolution of remote sensing image , 2010, 2010 18th International Conference on Geoinformatics.

[6]  Shuyuan Yang,et al.  Novel Super Resolution Restoration of Remote Sensing Images Based on Compressive Sensing and Example Patches-Aided Dictionary Learning , 2011, 2011 International Workshop on Multi-Platform/Multi-Sensor Remote Sensing and Mapping.

[7]  谢浩,et al.  Effects of Spatial resolution of remote sensing image on the accuracy of extracted slope collapse data , 2016 .

[8]  M. Elad,et al.  $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation , 2006, IEEE Transactions on Signal Processing.

[9]  Federico Cristina,et al.  High Resolution Images from Low Resolution Video Sequences , 2005 .

[10]  Zongxu Pan,et al.  Super resolution of remote sensing image based on structure similarity in CS frame , 2011, International Symposium on Multispectral Image Processing and Pattern Recognition.

[11]  A. Bruckstein,et al.  K-SVD : An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation , 2005 .

[12]  MA Wei-jun.  Research on the Optimal Spatial Resolution of Remote Sensing Image for Census Area Division , 2011 .

[13]  Roger Y. Tsai,et al.  Multiframe image restoration and registration , 1984 .

[14]  William P. Kustas,et al.  Effect of remote sensing spatial resolution on interpreting tower-based flux observations , 2006 .

[15]  Manjunath V. Joshi,et al.  New Learning Based Super-Resolution: Use of DWT and IGMRF Prior , 2010, IEEE Transactions on Image Processing.