Hierarchical Model-Based Motion Estimation
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Is Super-Resolution with Optical Flow Feasible?
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Adaptive outlier rejection in image super-resolution
EURASIP Journal on Applied Signal Processing
An iterative image registration technique with an application to stereo vision
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
HOS-based image super-resolution reconstruction
MCAM'07 Proceedings of the 2007 international conference on Multimedia content analysis and mining
Extraction of high-resolution frames from video sequences
IEEE Transactions on Image Processing
IEEE Transactions on Image Processing
IEEE Transactions on Image Processing
Fast and robust multiframe super resolution
IEEE Transactions on Image Processing
An image super-resolution algorithm for different error levels per frame
IEEE Transactions on Image Processing
Robust methods for high-quality stills from interlaced video in the presence of dominant motion
IEEE Transactions on Circuits and Systems for Video Technology
Hi-index | 0.00 |
Super-resolution (SR) for video sequences is a technique to obtain a higher resolution image by fusing multiple low-resolution (LR) frames of the same scene. In a typical super-resolution algorithm, image registration is one of the most affective steps. The difficulty of this step results in the fact that most of the existing SR algorithms can not cope with local motions because they assume global motion. In this paper, we propose a SR algorithm that takes into account inaccurate estimates of the registration parameters and the point spread function. When frames obey the assumed global motion model, these inaccurate estimates, along with the additive Gaussian noise in the low-resolution image sequence, result in different noise level for each frame. However, in case of existence of local motion and/or occlusion, regions that have local motion and/or occlusion have different noise level. To cope with this problem, we propose to adaptively weight each segment according to its reliability. The segments are generated by segmenting the reference frame using watershed segmentation. The experimental results using real video sequences show the effectiveness of the proposed algorithm compared to three state-of-the-art SR algorithms.