Abstract
Image super-resolution (SR) is a process to reconstruct a high-resolution (HR) image by fusing multiple low-resolution (LR) images. A critical step in image SR is accurate registration of the LR images, however the larger inter-frame motion can significantly affect the sub-pixel image registration, then it can also affect the output of HR reconstruction. So a novel Adaptive Frame Selection method is proposed in this paper for the reconstruction of multi-frame SR. It devises a framework to resolve the image SR reconstruction problem into two steps. Firstly, using the Optical flow algorithm to calculate the inter-frame motion estimation, designing an adaptive frame selection method to discard some of the larger inter-frame motion frames, then the less inter-frame motion of successive frames is obtained. Secondly, using the maximum a posteriori (MAP) based SR algorithm for the SR reconstruction. The experimental results indicate that the proposed algorithm has considerable effectiveness in terms of both objective measurements and visual evaluation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: International Joint Conference on Artificial Intelligence, pp. 674–679 (1981)
Irani, M., Peleg, S.: Improving resolution by image registration. CHIP: Graphical Models and Image Processing 53(3), 231–239 (1991)
Hardie, R.C., Barnard, K.J., Bognar, J.G., Armstrong, E.E., Watson, E.A.: High-resolution image reconstruction from a sequence of rotated and translated frames and its application to an infrared imaging system. Optical Engineering 37(1), 247–260 (1998)
Tsai, R.Y., Huang, T.S.: Multiframe image restoration and registration. In: Huang, T.S. (ed.) Advances in Computer Vision and Image Processing, vol. 1, pp. 317–339. JAI Press, Greenwich (1984)
Kim, S.P., Bose, N.K., Valenzuela, H.M.: Recursive reconstruction of high resolution image from noisy undersampled multiframes. IEEE Transactions on Acoustics, Speech, Signal Processing 38(6), 1013–1027 (1990)
Kim, S.P., Su, W.Y.: Recursive high-resolution reconstruction of blurred multiframe images. IEEE Transactions on Image Processing 2(4), 534–539 (1993)
Narayanan, B., Hardie, R.C., Barner, K.E., Shao, M.: A computationally efficient super-resolution algorithm for video processing using partition filters. IEEE Transactions on Circuits and Systems for Video Technology 17(5), 621–634 (2007)
Farsiu, S., Robinson, M.D., Elad, M., Milanfar, P.: Fast and robust multiframe super resolution. IEEE Transactions on Image Processing 13, 1327–1344 (2004)
Zhang, L., Zhang, H., Shen, H., Li, P.: A super-resolution reconstruction algorithm for surveillance images. Signal Processing 90, 848–859 (2010)
Zhang, Z., Wang, R.-S.: Frame selection in multi-frame image super-resolution restoration. Signal Processing 25, 1775–1780 (2009)
Jillela, R.R., Ross, A.: Adaptive Frame Selection for Improved Face Recognition in Low-Resolution Videos. Appeared in Proc. of International Joint Conference on Neural Networks (IJCNN), Atlanta, USA (June 2009)
Lucas, B.D., Kanade, T.: An iterative image registration technique with an applicatioin to stereo vision. In: Proceedings of DARPA Image Understanding, pp. 121–130 (1981)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag GmbH Berlin Heidelberg
About this paper
Cite this paper
Xue, C., Yu, M., Jia, C., Shi, S., Zhai, Y. (2012). Adaptive Frame Selection for Multi-frame Super Resolution. In: Jin, D., Lin, S. (eds) Advances in Future Computer and Control Systems. Advances in Intelligent and Soft Computing, vol 159. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-29387-0_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-29387-0_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-29386-3
Online ISBN: 978-3-642-29387-0
eBook Packages: EngineeringEngineering (R0)