Open Source Computer Vision
cv::gpu::DisparityBilateralFilter Class Reference

#include <gpu.hpp>

Public Types

enum  { DEFAULT_NDISP = 64 }
enum  { DEFAULT_RADIUS = 3 }
enum  { DEFAULT_ITERS = 1 }

Public Member Functions

 DisparityBilateralFilter (int ndisp=DEFAULT_NDISP, int radius=DEFAULT_RADIUS, int iters=DEFAULT_ITERS)
 the default constructor More...
 DisparityBilateralFilter (int ndisp, int radius, int iters, float edge_threshold, float max_disc_threshold, float sigma_range)
void operator() (const GpuMat &disparity, const GpuMat &image, GpuMat &dst, Stream &stream=Stream::Null())

Member Enumeration Documentation

§ anonymous enum

anonymous enum

§ anonymous enum

anonymous enum

§ anonymous enum

anonymous enum

Constructor & Destructor Documentation

§ DisparityBilateralFilter() [1/2]

cv::gpu::DisparityBilateralFilter::DisparityBilateralFilter ( int  ndisp = DEFAULT_NDISP,
int  radius = DEFAULT_RADIUS,
int  iters = DEFAULT_ITERS 

the default constructor

§ DisparityBilateralFilter() [2/2]

cv::gpu::DisparityBilateralFilter::DisparityBilateralFilter ( int  ndisp,
int  radius,
int  iters,
float  edge_threshold,
float  max_disc_threshold,
float  sigma_range 

the full constructor taking the number of disparities, filter radius, number of iterations, truncation of data continuity, truncation of disparity continuity and filter range sigma

Member Function Documentation

§ operator()()

void cv::gpu::DisparityBilateralFilter::operator() ( const GpuMat disparity,
const GpuMat image,
GpuMat dst,
Stream stream = Stream::Null() 

the disparity map refinement operator. Refine disparity map using joint bilateral filtering given a single color image. disparity must have CV_8U or CV_16S type, image must have CV_8UC1 or CV_8UC3 type.

The documentation for this class was generated from the following file: