Improving resolution by image registration
CVGIP: Graphical Models and Image Processing
| Hi-index | 0.00 |
A common method for reconstructing a turbulence scene is through the creation of an artificial reference image. The reference image is usually obtained by averaging video through time. Using optical flow from that reference image to input images would give rise to such applications as: super-resolution, tracking, and so forth. This technique, however, suffers from several drawbacks: the resulting artificial reference image is blurred, so the calculated optical flow is not precise and limits the ability of higher level applications (such as super-resolution, tracking, mosaics). We present a mathematical framework for reconstructing a video scene as would have been seen without turbulence interference, yielding an observable live video output. We then use both frames and optical flow to get the aforementioned applications while dealing with camera motion, and draw guidelines to deal with in-scene motion inherently.