Super-Resolution Reconstruction via Multi-frame Defocused Images Based on PSF Estimation and Compressive Sensing

被引：0
作者：
Mao Y. [1 ]
Jia H. [1 ]
Li C. [1 ]
Yan Y. [1 ]
机构：
[1] State Key Lab of Power Transmission Equipment and System Security and New Technology, Chongqing University, Chongqing
来源：
Sensing and Imaging | 2018年 / 19卷 / 01期
基金：
中国国家自然科学基金;
关键词：
Compressive sensing; Particle swarm optimization; Point spread function; Super-resolution;
D O I：
10.1007/s11220-018-0210-2
中图分类号：
学科分类号：
摘要：
Image super-resolution reconstruction is an effective method to improve image resolution, but most reconstruction methods rely on the clear low resolution images ignoring the blurred images which are also effective observations of the scene. Aiming at the problem, a super-resolution reconstruction (SRR) method via multi-frame defocused images is proposed. Firstly, according to the image degraded model, we establish the cost function of the point spread function (PSF) and utilize the particle swarm optimization algorithm to estimate it. Then, based on the multi-frame defocused images and PSFs, a joint reconstruction model is established to realize SRR by compressive sensing (CS) theory. In the CS framework, only the interpolated version of the low-resolution image is used for training purpose and the K-Singular Value Decomposition method is used for dictionary training. In addition, to solve the edge effect problem, an internal blur matrix is constructed according to the image blurring process, and a weight coefficient is introduced in the patch splicing process. Experiments show that the proposed algorithm can accurately estimate the defocused image PSF and achieve a good reconstruction effect. © 2018, Springer Science+Business Media, LLC, part of Springer Nature.
引用
收藏
相关论文
共 27 条
  • [1] Tsai R.Y., Huang T.S., Multiframe image restoration and registration, Advances in Computer Vision and Image Processing, 1, pp. 317-339, (1984)
  • [2] Zhang X., Liu Q., Et al., Non-local feature back-projection for image super-resolution, IET Image Processing, 10, 5, pp. 398-408, (2016)
  • [3] Rasti P., Demirel H., Anbarjafari G., Iterative back projection based image resolution enhancement, In Machine Vision and Image Processing, pp. 237-240, (2014)
  • [4] Liu J., Dai S., Guo Z., Zhang D., An improved POCS super-resolution infrared image reconstruction algorithm based on visual mechanism, Infrared Physics & Technology, 78, pp. 92-98, (2016)
  • [5] Liu H., Sun K., Sun H., Sun J., Super-resolution image reconstruction of pocs with edge preserving, Journal of Jilin University, 33, 6, pp. 620-624, (2015)
  • [6] Luo G.Z., Yin J.P., Zhu E., Super-resolution image reconstruction based on non-local POCS, Computer Science, 41, 8, pp. 40-47, (2014)
  • [7] Sun D., Gao Q., Lu Y., Zheng L., Wang H., A high quality single-image super-resolution algorithm based on linear bayesian map estimation with sparsity prior, Digital Signal Processing, 35, pp. 45-52, (2014)
  • [8] Marcelo O.C., Evandro O.T.S., Mario S.F., Super-resolution image reconstruction using nonparametric Bayesian INLA approximation, IEE Transactions on Image Processing, 21, 8, pp. 3491-3501, (2012)
  • [9] Sen P., Darabi S., Compressive image super-resolution, In Asilomar Conference on Signals, Systems and Computers, pp. 1235-1242, (2009)
  • [10] Pan Z., Yu J., Huang H., Hu S., Zhang A., Ma H., Et al., Super-resolution based on compressive sensing and structural self-similarity for remote sensing images, IEEE Transactions on Geoscience and Remote Sensing, 51, 9, pp. 4864-4876, (2013)
123