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].
Base class for Super Resolution algorithms.
superres::
SuperResolution
: public Algorithm
, public superres::
FrameSource
¶The class is only used to define the common interface for the whole family of Super Resolution algorithms.
Set input frame source for Super Resolution algorithm.
void superres::SuperResolution::
setInput
(const Ptr<FrameSource>& frameSource)¶Parameters: |
|
---|
Process next frame from input and return output result.
void superres::SuperResolution::
nextFrame
(OutputArray frame)¶Parameters: |
|
---|
Clear all inner buffers.
void superres::SuperResolution::
collectGarbage
()¶Create Bilateral TV-L1 Super Resolution.
Ptr<SuperResolution> superres::
createSuperResolution_BTVL1
()¶
Ptr<SuperResolution> superres::
createSuperResolution_BTVL1_GPU
()¶This class implements Super Resolution algorithm described in the papers [Farsiu03] and [Mitzel09] .
Here are important members of the class that control the algorithm, which you can set after constructing the class instance:
- int scale Scale factor.
- int iterations Iteration count.
- double tau Asymptotic value of steepest descent method.
- double lambda Weight parameter to balance data term and smoothness term.
- double alpha Parameter of spacial distribution in Bilateral-TV.
- int btvKernelSize Kernel size of Bilateral-TV filter.
- int blurKernelSize Gaussian blur kernel size.
- double blurSigma Gaussian blur sigma.
- int temporalAreaRadius Radius of the temporal search area.
- Ptr<DenseOpticalFlowExt> opticalFlow Dense optical flow algorithm.
[Farsiu03] | (1, 2)
|
[Mitzel09] | (1, 2)
|