-
Multi-frame super resolution reconstruction is a technology for obtaining a high resolution image from a set of blurred and aliased low resolution images. The most popular and widely used super resolution methods are motion based. However, the estimation of motion information (registration) is very difficult, computationally expensive and inaccurate, especially for aerial image. The sub-pixel registration error restricts the performance of the subsequent super resolution. Instead of trying to parameterize the motion estimation model, this paper proposes an image super resolution framework based on the polyphase components reconstruction algorithm and an improved steering kernel regression algorithm. Given an image observation model, a reversible 2D polyphase decomposition, which breaks down a high resolution image into polyphase components, is obtained. Though the assumption of diversity sampling, this paper adopts a fundamentally different approach, in which the low-resolution frames is used as the basis and the reference frame as the reference sub-polyphase component of the high resolution image for recovering the polyphase components of the high resolution image. The polyphase components, which fuse the low resolution frames with the complementary details, can be obtained by computing their expansion coefficients in terms of this basis using the available sub-polyphase components and then inversely transforming them into a high resolution image. This paper accomplishes this by formulating the problem as the maximum likelihood estimation, which guarantees a close-to-perfect solution. Furthermore, this paper proposes an improved steering kernel regression algorithm, to help restore the fusion image with mild blur and random noise. This paper adaptively refines the steering kernel regression function according to the local region context and structures. Thus, this new algorithm not only effectively combines denoising and deblurring together, but also preserves the edge information. Our framework develops an efficient and stable algorithm to tackle the huge size and ill-posedness of the super resolution problem, and improves the computational efficiency via avoiding registration and iterative computation. Several experimental results on synthetic data illustrate that our method outperforms the state-of-the-art methods in quantitative and qualitative comparisons. The proposed super resolution algorithm can indeed reconstruct high-frequency information which is otherwise unavailable in the single LR image. It can effectively suppress blur and noise, and produce visually pleasing resolution enhancement in aerial images.
-
Keywords:
- image reconstruction /
- super resolution /
- image polyphase decomposition /
- steering kernel regression
[1] Park S C, Park M K, Kang M G 2003 IEEE Signal Proc. Mag. 20 21
[2] Deng C Z, Tian W, Wang S Q, Zhu H S, Wu C M, Xiong Z W, Zhong W 2014 Opt. Precision Eng. 22 1648 (in Chinese) [邓承志, 田伟, 汪胜前, 朱华生, 吴朝明, 熊志文, 钟威 2014光学精密工程 22 1648]
[3] Ruan Q Q 2005 Physics 34 1 (in Chinese) [阮秋琦2005 物理 34 1]
[4] Farsiu S, Robinson D 2004 IEEE Trans. Image Process. 13 1327
[5] Peng Z M, Jing L, He Y M, Zhang P 2014 Opt. Precision Eng. 22 169 (in Chinese) [彭真明, 景亮, 何燕敏, 张萍 2014光学精密工程 22 169]
[6] Yang W B, Zhu M, Liu Z M, Chen D C 2014 Opt. Precision Eng. 22 2247 (in Chinese) [杨文波, 朱明, 刘志明, 陈东成 2014光学精密工程 22 2247]
[7] Tekalp A, Ozkan M, Sezan M 1992 Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing San Francisco, USA, March 23-26, 1992 p169
[8] Tsai R Y, Huang T S 1984 Adv. Comput. Vis. Image Process. 1 317
[9] Chen Y N, Jin W Q, Zhao L, Zhao L 2009 Acta Phys. Sin. 58 264 (in Chinese) [陈翼男, 金伟其, 赵磊, 赵琳 2009 58 264]
[10] Su B H, Jin W Q, Niu L H, Liu G R, Liu M Q 2001 Acta Photon. Sin. 3 492 (in Chinese) [苏秉华, 金伟其, 牛丽红, 刘广荣, 刘明奇2001光子学报 3 492]
[11] Tom B C, Katsaggelos A K 1996 Proceedings of SPIE Conference of Visual Communications and Image Processing Lausanne, Switzerland 1996 p1430
[12] Zhou S B, Yuan Y, Su L J 2013 Acta Phys. Sin. 62 130701 (in Chinese) [周树波, 原燕, 苏丽娟 2013 62 130701]
[13] Peyman M 2011 Super Resolution Imaging (Vol. 1) (New York:Benjamin) pp1-23
[14] Gong W G, Pan F Y, Li J M 2014 Opt. Precision Eng. 22 721 (in Chinese) [龚卫国, 潘飞宇, 李进明 2014光学精密工程 22 721]
[15] Liu H C, Li S T, Yin H T 2013 Opt. Commun. 289 45
[16] Deng C Z, Tian W, Chen P, Wang S Q, Zhu H S, Hu S F, 2014 Acta Phys. Sin. 63 044202 in Chinese 2014 63 044202 (in Chinese) [邓承志, 田伟, 陈盼, 汪胜前, 朱华生, 胡赛凤 2014 63 044202]
[17] Alam M S, Bognar J G, Hardie R C 2000 IEEE Trans. Instrum. 49 915
[18] Filip S, Gabriel C, Jan F 2006 IEEE Trans. Image Process. 16 9
[19] Fasal M A 2010 Ph. D. Dissertation (Ann Arbor:University of Michigan)
[20] Hiroyuki T, Sina F, Peyman M 2007 IEEE Trans. Image Process. 16 349
[21] Kim S Y, Cho W, Koschan A, Abidi M A 2011 Proceedings of the 7th International Symposium on Visual Computing LasVegas, Nevada, September 26-28, 2011 p291
[22] Antigoni P, Vassilis A 2009 Opt. Eng. 48 117004
[23] Yang J, Wright J, Huang T 2010 IEEE Trans. Image Process. 19 2861
-
[1] Park S C, Park M K, Kang M G 2003 IEEE Signal Proc. Mag. 20 21
[2] Deng C Z, Tian W, Wang S Q, Zhu H S, Wu C M, Xiong Z W, Zhong W 2014 Opt. Precision Eng. 22 1648 (in Chinese) [邓承志, 田伟, 汪胜前, 朱华生, 吴朝明, 熊志文, 钟威 2014光学精密工程 22 1648]
[3] Ruan Q Q 2005 Physics 34 1 (in Chinese) [阮秋琦2005 物理 34 1]
[4] Farsiu S, Robinson D 2004 IEEE Trans. Image Process. 13 1327
[5] Peng Z M, Jing L, He Y M, Zhang P 2014 Opt. Precision Eng. 22 169 (in Chinese) [彭真明, 景亮, 何燕敏, 张萍 2014光学精密工程 22 169]
[6] Yang W B, Zhu M, Liu Z M, Chen D C 2014 Opt. Precision Eng. 22 2247 (in Chinese) [杨文波, 朱明, 刘志明, 陈东成 2014光学精密工程 22 2247]
[7] Tekalp A, Ozkan M, Sezan M 1992 Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing San Francisco, USA, March 23-26, 1992 p169
[8] Tsai R Y, Huang T S 1984 Adv. Comput. Vis. Image Process. 1 317
[9] Chen Y N, Jin W Q, Zhao L, Zhao L 2009 Acta Phys. Sin. 58 264 (in Chinese) [陈翼男, 金伟其, 赵磊, 赵琳 2009 58 264]
[10] Su B H, Jin W Q, Niu L H, Liu G R, Liu M Q 2001 Acta Photon. Sin. 3 492 (in Chinese) [苏秉华, 金伟其, 牛丽红, 刘广荣, 刘明奇2001光子学报 3 492]
[11] Tom B C, Katsaggelos A K 1996 Proceedings of SPIE Conference of Visual Communications and Image Processing Lausanne, Switzerland 1996 p1430
[12] Zhou S B, Yuan Y, Su L J 2013 Acta Phys. Sin. 62 130701 (in Chinese) [周树波, 原燕, 苏丽娟 2013 62 130701]
[13] Peyman M 2011 Super Resolution Imaging (Vol. 1) (New York:Benjamin) pp1-23
[14] Gong W G, Pan F Y, Li J M 2014 Opt. Precision Eng. 22 721 (in Chinese) [龚卫国, 潘飞宇, 李进明 2014光学精密工程 22 721]
[15] Liu H C, Li S T, Yin H T 2013 Opt. Commun. 289 45
[16] Deng C Z, Tian W, Chen P, Wang S Q, Zhu H S, Hu S F, 2014 Acta Phys. Sin. 63 044202 in Chinese 2014 63 044202 (in Chinese) [邓承志, 田伟, 陈盼, 汪胜前, 朱华生, 胡赛凤 2014 63 044202]
[17] Alam M S, Bognar J G, Hardie R C 2000 IEEE Trans. Instrum. 49 915
[18] Filip S, Gabriel C, Jan F 2006 IEEE Trans. Image Process. 16 9
[19] Fasal M A 2010 Ph. D. Dissertation (Ann Arbor:University of Michigan)
[20] Hiroyuki T, Sina F, Peyman M 2007 IEEE Trans. Image Process. 16 349
[21] Kim S Y, Cho W, Koschan A, Abidi M A 2011 Proceedings of the 7th International Symposium on Visual Computing LasVegas, Nevada, September 26-28, 2011 p291
[22] Antigoni P, Vassilis A 2009 Opt. Eng. 48 117004
[23] Yang J, Wright J, Huang T 2010 IEEE Trans. Image Process. 19 2861
Catalog
Metrics
- Abstract views: 6230
- PDF Downloads: 221
- Cited By: 0
下载:
