Video Restoration with Motion Prediction Based on the Multiresolution Wavelet Analysis

We propose a novel method for image sequence restorations. It is based on the wavelet domain image restoration method proposed by Belge et al. for static images [1]. In this paper, by combining the iteration procedure in the Belge's method with the renewing process for sequentially given images and by employing Kalman filer for predicting the foreground movement of the images in the wavelet domain, considerable reduction of the computational cost is shown to be achievable. This is verified by computer simulations on artificially degraded images.

[1]  Bernd Neumann,et al.  Computer Vision — ECCV’98 , 1998, Lecture Notes in Computer Science.

[2]  Rachid Deriche,et al.  Image Sequence Restoration: A PDE Based Coupled Method for Image Restoration and Motion Segmentation , 1998, ECCV.

[3]  Zhiwei Luo,et al.  Restoration of degraded moving image for predicting a moving object , 2006, VISAPP.

[4]  A. Pižurica,et al.  Combined wavelet domain and temporal video denoising , 2003, Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, 2003..

[5]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[6]  Kenneth W. Tobin,et al.  Multiframe combination and blur deconvolution of video data , 2000, Electronic Imaging.

[7]  Marcel J. T. Reinders,et al.  A spatiotemporal image sequence restoration algorithm , 2002, Proceedings. International Conference on Image Processing.

[8]  Temel Kayikçioglu,et al.  An improved motion-compensated restoration method for damaged color motion picture films , 2004, Signal Process. Image Commun..

[9]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Eric L. Miller,et al.  Wavelet domain image restoration with adaptive edge-preserving regularization , 2000, IEEE Trans. Image Process..

[11]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[12]  Ivan W. Selesnick,et al.  Video denoising using 2D and 3D dual-tree complex wavelet transforms , 2003, SPIE Optics + Photonics.