Video Restoration with Motion Prediction Based on the Multiresolution Wavelet Analysis

Authors:
Kei Akiyama;Zhi-Wei Luo;Masaki Onishi;Shigeyuki Hosoe;Kouichi Taji;Yoji Uno
Affiliations:
Graduate School of Engineering, Nagoya University, Nagoya, Japan 464-8603 and Bio-mimetic Control Research Center, RIKEN, Nagoya, Japan 463-0003 and Hitachi Global Storage Technologies Japan, Ltd. ...;Faculty of Engineering, Kobe University, Kobe, Japan 657-8501 and Bio-mimetic Control Research Center, RIKEN, Nagoya, Japan 463-0003;Information Technology Research Institute, AIST, Tsukuba, Japan 305-8568 and Bio-mimetic Control Research Center, RIKEN, Nagoya, Japan 463-0003;Bio-mimetic Control Research Center, RIKEN, Nagoya, Japan 463-0003;Graduate School of Engineering, Nagoya University, Nagoya, Japan 464-8603;Graduate School of Engineering, Nagoya University, Nagoya, Japan 464-8603
Venue:
Neural Information Processing
Year:
2008

Citing 6
Cited 0

A Theory for Multiresolution Signal Decomposition: The Wavelet Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Ten lectures on wavelets

Ten lectures on wavelets
Nonlinear total variation based noise removal algorithms

Proceedings of the eleventh annual international conference of the Center for Nonlinear Studies on Experimental mathematics : computational issues in nonlinear science: computational issues in nonlinear science
Image Sequence Restoration: A PDE Based Coupled Method for Image Restoration and Motion Segmentation

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Combined Wavelet Domain and Temporal Video Denoising

AVSS '03 Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance
Wavelet domain image restoration with adaptive edge-preserving regularization

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.01

Visualization

Abstract

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.