This book focuses on the super resolution of images and video. The authors’ use of the term super resolution (SR) is used to describe the process of obtaining a high resolution (HR) image, or a sequence of HR images, from a set of low resolution (LR) observations. This process has also been referred to in the literature as resolution enhancement (RE). SR has been applied primarily to spatial and temporal RE, but also to hyperspectral image enhancement. This book concentrates on motion based spatial RE, although the authors also describe motion free and hyperspectral image SR problems. Also examined is the very recent research area of SR for compression, which consists of the intentional downsampling, during pre-processing, of a video sequence to be compressed and the application of SR techniques, during post-processing, on the compressed sequence. It is clear that there is a strong interplay between the tools and techniques developed for SR and a number of other inverse problems encountered in signal processing (e.g., image restoration, motion estimation). SR techniques are being applied to a variety of fields, such as obtaining improved still images from video sequences (video printing), high definition television, high performance color Liquid Crystal Display (LCD) screens, improvement of the quality of color images taken by one CCD, video surveillance, remote sensing, and medical imaging. The authors believe that the SR/RE area has matured enough to develop a body of knowledge that can now start to provide useful and practical solutions to challenging real problems and that SR techniques can be an integral part of an image and video codec and can drive the development of new coder-decoders (codecs) and standards.
Author(s): Aggelos Katsaggelos
Edition: 1
Publisher: Morgan and Claypool Publishers
Year: 2006
Language: English
Pages: 134
Tags: Информатика и вычислительная техника;Обработка медиа-данных;Обработка изображений;
Upsampling procedure......Page 0
What is super resolution of images and video?......Page 17
Why and when is super resolution possible?......Page 20
Applications......Page 24
Book outline......Page 27
Notation......Page 29
Bayesian modeling......Page 31
Bayesian inference......Page 32
Hierarchical Bayesian Modeling and Inference......Page 33
Image Formation Models for Uncompressed Observations......Page 35
The Warp--Blur Model......Page 39
The Blur--Warp Model......Page 41
Image Formation Models for Compressed Observations......Page 43
Limits on super resolution......Page 49
Motion Estimation from Uncompressed Observations......Page 55
Motion Estimation from Compressed Observations......Page 61
How to Detect Unreliable Motion Estimates......Page 65
Consistency of Motion Estimates for super resolution......Page 67
Some Open Issues in Motion Estimation for super resolution......Page 71
Estimation of High-Resolution Images......Page 73
High-resolution image estimation from uncompressed sequences......Page 74
High-Resolution image estimation from compressed sequences......Page 87
Some open issues in image estimation for super resolution......Page 91
Bayesian Inference Models in Super Resolution......Page 93
Hierarchical Bayesian Framework for Super Resolution......Page 94
Inference models for super-resolution reconstruction problems......Page 95
Some Open Issues in super resolution Bayesian Inference......Page 105
Pre- and Post-Processing of Video Sequences......Page 108
Including super resolution into the Compression Scheme......Page 110
Region-Based Super Resolution for Compression......Page 114
Motion and texture segmentation......Page 116
Downsampling process......Page 119
Upsampling procedure......Page 121
