Abstract | ||
---|---|---|
Unlike most Super-Resolution (SR) methods described in lit- erature, which perform only SR reconstruction on the back- ground of an image scene, we propose a framework that per- forms SR reconstruction simultaneously on the background and on moving objects. After registration of the background, moving objects are detected and to each moving object reg- istration is applied. The fusion and deblurring tasks of the frameworkare performedbythewell-knownmethodofHardie. To evaluate the performance of the framework the Triangle Orientation Discrimination (TOD) method is used. The TOD method quantitatively measures the SR performance on the image background and on moving objects. From experiments it can be concluded that under proper conditions, the SR per- formance on moving objects is similar as the SR performance on the background. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/ICIP.2006.313074 | ICIP |
Keywords | Field | DocType |
image resolution,image restoration,indexing terms,image registration,motion estimation,physics,super resolution,image fusion,superresolution | Background subtraction,Object detection,Computer vision,Pattern recognition,Image fusion,Deblurring,Computer science,Artificial intelligence,Image restoration,Superresolution,Image resolution,Image registration | Conference |
ISSN | ISBN | Citations |
1522-4880 | 1-4244-0480-0 | 10 |
PageRank | References | Authors |
0.68 | 3 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Adam W. M. van Eekeren | 1 | 32 | 2.53 |
Klamer Schutte | 2 | 173 | 18.26 |
Judith Dijk | 3 | 10 | 1.69 |
Dirk-Jan J. de Lange | 4 | 12 | 1.08 |
Lucas J. van Vliet | 5 | 842 | 113.16 |