Extraction of High-Resolution Frame from Low-Resolution Video Sequence Using Region-Based Motion Estimation

Osama Ahmed OMER  Toshihisa TANAKA  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E93-A   No.4   pp.742-751
Publication Date: 2010/04/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.E93.A.742
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Digital Signal Processing
Keyword: 
super-resolution,  region matching,  image registration,  resolution enhancement,  

Full Text: PDF>>
Buy this Article




Summary: 
The problem of recovering a high-resolution frame from a sequence of low-resolution frames is considered. In general, video frames cannot be related through global parametric transformation due to the arbitrary individual pixel movement between frame pairs. To overcome this problem, we propose to employ region-matching technique for motion estimation with a modified model for frame alignment. To do that, the reference frame is segmented into arbitrary-shaped regions which are further matched with that of the other frames. Then, the frame alignment is accomplished by optimizing the cost function that consists of L1-norm of the difference between the interpolated low-resolution (LR) frames and the simulated LR frames. The experimental results demonstrate that using region matching in motion estimation step with the modified alignment model works better than other motion models such as affine, block matching, and optical flow motion models.