Sciweavers

Share
CVPR
2003
IEEE

Practical Super-Resolution from Dynamic Video Sequences

10 years 1 months ago
Practical Super-Resolution from Dynamic Video Sequences
This paper introduces a practical approach for superresolution, the process of reconstructing a high-resolution image from the low-resolution input ones. The emphasis of our work is to super-resolve frames from dynamic video sequences which may contain significant object occlusion or scene changes. As the quality of super-resolved images highly relies on the correctness of image alignment between consecutive frames, we employ the robust optical flow method to accurately estimate motion between the image pair. An efficient and reliable scheme is designed to detect and discard incorrect matchings which may degrade the output quality. We also introduce the usage of elliptical weighted average (EWA) filter to model the spatiallyvariant point spread function (PSF) of acquisition system in order to improve accuracy of the model. A number of complex and dynamic video sequences are tested to demonstrate the applicability and reliability of our algorithm.
Zhongding Jiang, Tien-Tsin Wong, Hujun Bao
Added 12 Oct 2009
Updated 29 Oct 2009
Type Conference
Year 2003
Where CVPR
Authors Zhongding Jiang, Tien-Tsin Wong, Hujun Bao
Comments (0)
books