MATLAB File Help: cv.SuperResolution Index
cv.SuperResolution

Class for a whole family of Super Resolution algorithms

The Super Resolution module contains a set of functions and classes that can be used to solve the problem of resolution enhancement. There are a few methods implemented, most of them are descibed in the papers [Farsiu03] and [Mitzel09].

Example

superres = cv.SuperResolution();
superres.Scale = 2;       % 2x scale
superres.Iterations = 10; % careful alg is computationally expensive!
superres.setOpticalFlow('FarnebackOpticalFlow', 'LevelsNumber',3);
superres.setInput('Video', 'video.avi');
while true
    tic, frame = superres.nextFrame(); toc
    if isempty(frame), break; end
    imshow(frame), drawnow
end

References

[Farsiu03]:

Sina Farsiu, Dirk Robinson, Michael Elad, and Peyman Milanfar. "Fast and robust super-resolution". In Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on, volume 2, pages II-291. IEEE, 2003.

[Mitzel09]:

Dennis Mitzel, Thomas Pock, Thomas Schoenemann, and Daniel Cremers. "Video super resolution using duality based tv-l 1 optical flow". In Pattern Recognition, pages 432-441. Springer, 2009.

See also
Class Details
Superclasses handle
Sealed false
Construct on load false
Constructor Summary
SuperResolution Create Bilateral TV-L1 Super Resolution 
Property Summary
Alpha Parameter of spacial distribution in Bilateral-TV. 
BlurKernelSize Gaussian blur kernel size. 
BlurSigma Gaussian blur sigma. 
Iterations count. 
KernelSize Kernel size of Bilateral-TV filter. 
Labmda Weight parameter to balance data term and smoothness term. 
Scale factor. 
Tau Asymptotic value of steepest descent method. 
TemporalAreaRadius Radius of the temporal search area. 
id Object ID 
Method Summary
  addlistener Add listener for event. 
  collectGarbage Clear all inner buffers 
  delete Destructor 
  eq == (EQ) Test handle equality. 
  findobj Find objects matching specified conditions. 
  findprop Find property of MATLAB handle object. 
  ge >= (GE) Greater than or equal relation for handles. 
  getOpticalFlow Dense optical flow algorithm 
  gt > (GT) Greater than relation for handles. 
Sealed   isvalid Test handle validity. 
  le <= (LE) Less than or equal relation for handles. 
  lt < (LT) Less than relation for handles. 
  ne ~= (NE) Not equal relation for handles. 
  nextFrame Process next frame from input and return output result 
  notify Notify listeners of event. 
  reset Reset the frame source 
  setInput Set input frame source for Super Resolution algorithm 
  setOpticalFlow Dense optical flow algorithm