Super-resolution image reconstruction for video sequence

Because of motion, optical and sensor PSF, image resolution is usually not high in video image. To solve this problem this paper firstly proposes a model of image degradation. Then using the continuous frames which is taken from the same scene, it adopts the cubic spline interpolate method for motion compensation. After image registration, we make use of average filter to reconstruct the image. Lastly, we utilize Wiener filtering to eliminate blurring. The result indicates that compared with the original image the reconstructed image resolution is improved obviously.

[1]  Qiang Sun,et al.  A New Approach to Unsupervised Image Segmentation Based on Wavelet-Domain Hidden Markov Tree Models , 2004, ICIAR.

[2]  Peyman Milanfar,et al.  Efficient generalized cross-validation with applications to parametric image restoration and resolution enhancement , 2001, IEEE Trans. Image Process..

[3]  Guoliang Fan,et al.  Unsupervised image segmentation using wavelet-domain hidden Markov models , 2003, SPIE Optics + Photonics.

[4]  B. Gunturk,et al.  Multiframe resolution-enhancement methods for compressed video , 2002, IEEE Signal Processing Letters.

[5]  Moon Gi Kang,et al.  Super-resolution image reconstruction: a technical overview , 2003, IEEE Signal Process. Mag..

[6]  Tieniu Tan,et al.  A survey on visual surveillance of object motion and behaviors , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[7]  Hua Han,et al.  Wavelet-domain HMT-based image super-resolution , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[8]  Hu He.  Bayesian-based image/video super-resolution techniques , 2005 .