OpenCV  3.4.17
Open Source Computer Vision
Classes | Functions
Super Resolution

Classes

class  cv::superres::BroxOpticalFlow
 
class  cv::superres::DenseOpticalFlowExt
 
class  cv::superres::DualTVL1OpticalFlow
 
class  cv::superres::FarnebackOpticalFlow
 
class  cv::superres::FrameSource
 
class  cv::superres::PyrLKOpticalFlow
 
class  cv::superres::SuperResolution
 Base class for Super Resolution algorithms. More...
 

Functions

Ptr< FrameSourcecv::superres::createFrameSource_Camera (int deviceId=0)
 
Ptr< FrameSourcecv::superres::createFrameSource_Empty ()
 
Ptr< FrameSourcecv::superres::createFrameSource_Video (const String &fileName)
 
Ptr< FrameSourcecv::superres::createFrameSource_Video_CUDA (const String &fileName)
 
Ptr< BroxOpticalFlowcv::superres::createOptFlow_Brox_CUDA ()
 
Ptr< DualTVL1OpticalFlowcv::superres::createOptFlow_DualTVL1 ()
 
Ptr< DualTVL1OpticalFlowcv::superres::createOptFlow_DualTVL1_CUDA ()
 
Ptr< FarnebackOpticalFlowcv::superres::createOptFlow_Farneback ()
 
Ptr< FarnebackOpticalFlowcv::superres::createOptFlow_Farneback_CUDA ()
 
Ptr< PyrLKOpticalFlowcv::superres::createOptFlow_PyrLK_CUDA ()
 
Ptr< SuperResolutioncv::superres::createSuperResolution_BTVL1 ()
 Create Bilateral TV-L1 Super Resolution. More...
 
Ptr< SuperResolutioncv::superres::createSuperResolution_BTVL1_CUDA ()
 

Detailed Description

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 described in the papers [67] and [157] .

Function Documentation

◆ createFrameSource_Camera()

Ptr<FrameSource> cv::superres::createFrameSource_Camera ( int  deviceId = 0)

◆ createFrameSource_Empty()

Ptr<FrameSource> cv::superres::createFrameSource_Empty ( )

◆ createFrameSource_Video()

Ptr<FrameSource> cv::superres::createFrameSource_Video ( const String fileName)

◆ createFrameSource_Video_CUDA()

Ptr<FrameSource> cv::superres::createFrameSource_Video_CUDA ( const String fileName)

◆ createOptFlow_Brox_CUDA()

Ptr<BroxOpticalFlow> cv::superres::createOptFlow_Brox_CUDA ( )

◆ createOptFlow_DualTVL1()

Ptr<DualTVL1OpticalFlow> cv::superres::createOptFlow_DualTVL1 ( )

◆ createOptFlow_DualTVL1_CUDA()

Ptr<DualTVL1OpticalFlow> cv::superres::createOptFlow_DualTVL1_CUDA ( )

◆ createOptFlow_Farneback()

Ptr<FarnebackOpticalFlow> cv::superres::createOptFlow_Farneback ( )

◆ createOptFlow_Farneback_CUDA()

Ptr<FarnebackOpticalFlow> cv::superres::createOptFlow_Farneback_CUDA ( )

◆ createOptFlow_PyrLK_CUDA()

Ptr<PyrLKOpticalFlow> cv::superres::createOptFlow_PyrLK_CUDA ( )

◆ createSuperResolution_BTVL1()

Ptr<SuperResolution> cv::superres::createSuperResolution_BTVL1 ( )

#include <opencv2/superres.hpp>

Create Bilateral TV-L1 Super Resolution.

This class implements Super Resolution algorithm described in the papers [67] and [157] .

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.

◆ createSuperResolution_BTVL1_CUDA()

Ptr<SuperResolution> cv::superres::createSuperResolution_BTVL1_CUDA ( )