Automatic target detection by optimal morphological filters
Journal of Computer Science and Technology
A super-resolution method with EWA
Journal of Computer Science and Technology
Super-resolution reconstruction of image sequence using multiple motion estimation fusion
Journal of Computer Science and Technology
Super resolution recovery for multi-camera surveillance imaging
ICME '03 Proceedings of the 2003 International Conference on Multimedia and Expo - Volume 2
Determining the regularization parameters for super-resolution problems
Signal Processing
A wavelet based entropic approach to high-resolution reconstruction of images
Machine Graphics & Vision International Journal
Simultaneous enhancement of spatial resolution and dynamic range from multiple images
CGIM '07 Proceedings of the Ninth IASTED International Conference on Computer Graphics and Imaging
Robust web image/video super-resolution
IEEE Transactions on Image Processing
Multiframe super-resolution reconstruction of small moving objects
IEEE Transactions on Image Processing
Local object-based super-resolution mosaicing from low-resolution video
Signal Processing
A closed form algorithm for superresolution
ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part II
Adaptive MAP high-resolution image reconstruction algorithm using local statistics
PCM'05 Proceedings of the 6th Pacific-Rim conference on Advances in Multimedia Information Processing - Volume Part II
Accurate image registration for MAP image super-resolution
Image Communication
Hi-index | 0.01 |
We propose a robust, object-based approach to high-resolution image reconstruction from video using the projections onto convex sets (POCS) framework. The proposed method employs a validity map and/or a segmentation map. The validity map disables projections based on observations with inaccurate motion information for robust reconstruction in the presence of motion estimation errors; while the segmentation map enables object-based processing where more accurate motion models can be utilized to improve the quality of the reconstructed image. Procedures for the computation of the validity map and segmentation map are presented. Experimental results demonstrate the improvement in image quality that can be achieved by the proposed methods