OpenCV453
クラス | 列挙型 | 関数 | 変数
Stereo Correspondance Algorithms

クラス

class  cv::stereo::StereoMatcher
 Filters off small noise blobs (speckles) in the disparity map [詳解]
 
class  cv::stereo::StereoBinaryBM
 Class for computing stereo correspondence using the block matching algorithm, introduced and contributed to OpenCV by K. Konolige. [詳解]
 
class  cv::stereo::StereoBinarySGBM
 The class implements the modified H. Hirschmuller algorithm [HH08] that differs from the original one as follows: [詳解]
 
struct  cv::stereo::MatchQuasiDense
 
struct  cv::stereo::PropagationParameters
 
class  cv::stereo::QuasiDenseStereo
 Class containing the methods needed for Quasi Dense Stereo computation. [詳解]
 

列挙型

enum  { CV_SPECKLE_REMOVAL_ALGORITHM , CV_SPECKLE_REMOVAL_AVG_ALGORITHM }
 speckle removal algorithms. These algorithms have the purpose of removing small regions
 
enum  { CV_QUADRATIC_INTERPOLATION , CV_SIMETRICV_INTERPOLATION }
 subpixel interpolationm methods for disparities.
 

関数

 cv::stereo::MatchQuasiDense::CV_WRAP_AS (apply) bool operator<(const MatchQuasiDense &rhs) const
 
virtual CV_WRAP cv::stereo::QuasiDenseStereo::~QuasiDenseStereo ()=0
 destructor Method to free all the memory allocated by matrices and vectors in this class.
 
virtual CV_WRAP int cv::stereo::QuasiDenseStereo::loadParameters (cv::String filepath)=0
 Load a file containing the configuration parameters of the class. [詳解]
 
virtual CV_WRAP int cv::stereo::QuasiDenseStereo::saveParameters (cv::String filepath)=0
 Save a file containing all the configuration parameters the class is currently set to. [詳解]
 
virtual CV_WRAP void cv::stereo::QuasiDenseStereo::getSparseMatches (CV_OUT std::vector< MatchQuasiDense > &sMatches)=0
 Get The sparse corresponding points. [詳解]
 
virtual CV_WRAP void cv::stereo::QuasiDenseStereo::getDenseMatches (CV_OUT std::vector< MatchQuasiDense > &denseMatches)=0
 Get The dense corresponding points. [詳解]
 
virtual CV_WRAP void cv::stereo::QuasiDenseStereo::process (const cv::Mat &imgLeft, const cv::Mat &imgRight)=0
 Main process of the algorithm. This method computes the sparse seeds and then densifies them. [詳解]
 
virtual CV_WRAP cv::Point2f cv::stereo::QuasiDenseStereo::getMatch (const int x, const int y)=0
 Specify pixel coordinates in the left image and get its corresponding location in the right image. [詳解]
 
virtual CV_WRAP cv::Mat cv::stereo::QuasiDenseStereo::getDisparity ()=0
 Compute and return the disparity map based on the correspondences found in the "process" method. [詳解]
 
static CV_WRAP cv::Ptr< QuasiDenseStereocv::stereo::QuasiDenseStereo::create (cv::Size monoImgSize, cv::String paramFilepath=cv::String())
 

変数

CV_PROP_RW cv::Point2i cv::stereo::MatchQuasiDense::p0
 
CV_PROP_RW cv::Point2i cv::stereo::MatchQuasiDense::p1
 
CV_PROP_RW float cv::stereo::MatchQuasiDense::corr
 
CV_PROP_RW int cv::stereo::PropagationParameters::corrWinSizeX
 
CV_PROP_RW int cv::stereo::PropagationParameters::corrWinSizeY
 
CV_PROP_RW int cv::stereo::PropagationParameters::borderX
 
CV_PROP_RW int cv::stereo::PropagationParameters::borderY
 
CV_PROP_RW float cv::stereo::PropagationParameters::correlationThreshold
 
CV_PROP_RW float cv::stereo::PropagationParameters::textrureThreshold
 
CV_PROP_RW int cv::stereo::PropagationParameters::neighborhoodSize
 
CV_PROP_RW int cv::stereo::PropagationParameters::disparityGradient
 
CV_PROP_RW int cv::stereo::PropagationParameters::lkTemplateSize
 
CV_PROP_RW int cv::stereo::PropagationParameters::lkPyrLvl
 
CV_PROP_RW int cv::stereo::PropagationParameters::lkTermParam1
 
CV_PROP_RW float cv::stereo::PropagationParameters::lkTermParam2
 
CV_PROP_RW float cv::stereo::PropagationParameters::gftQualityThres
 
CV_PROP_RW int cv::stereo::PropagationParameters::gftMinSeperationDist
 
CV_PROP_RW int cv::stereo::PropagationParameters::gftMaxNumFeatures
 
CV_PROP_RW PropagationParameters cv::stereo::QuasiDenseStereo::Param
 

詳解

関数詳解

◆ getDenseMatches()

virtual CV_WRAP void cv::stereo::QuasiDenseStereo::getDenseMatches ( CV_OUT std::vector< MatchQuasiDense > &  denseMatches)
pure virtual

Get The dense corresponding points.

引数
[out]denseMatchesA vector containing all dense matches.
覚え書き
The method clears the denseMatches vector.
The returned Match elements inside the sMatches vector, do not use corr member.

◆ getDisparity()

virtual CV_WRAP cv::Mat cv::stereo::QuasiDenseStereo::getDisparity ( )
pure virtual

Compute and return the disparity map based on the correspondences found in the "process" method.

覚え書き
Default level is 50
戻り値
cv::Mat containing a the disparity image in grayscale.
参照
computeDisparity
quantizeDisparity

◆ getMatch()

virtual CV_WRAP cv::Point2f cv::stereo::QuasiDenseStereo::getMatch ( const int  x,
const int  y 
)
pure virtual

Specify pixel coordinates in the left image and get its corresponding location in the right image.

引数
[in]xThe x pixel coordinate in the left image channel.
[in]yThe y pixel coordinate in the left image channel.
戻り値
cv::Point(x,y)The location of the corresponding pixel in the right image.
cv::Point(0,0)(NO_MATCH) if no match is found in the right image for the specified pixel location in the left image.
覚え書き
This method should be always called after process, otherwise the matches will not be correct.

◆ getSparseMatches()

virtual CV_WRAP void cv::stereo::QuasiDenseStereo::getSparseMatches ( CV_OUT std::vector< MatchQuasiDense > &  sMatches)
pure virtual

Get The sparse corresponding points.

引数
[out]sMatchesA vector containing all sparse correspondences.
覚え書き
The method clears the sMatches vector.
The returned Match elements inside the sMatches vector, do not use corr member.

◆ loadParameters()

virtual CV_WRAP int cv::stereo::QuasiDenseStereo::loadParameters ( cv::String  filepath)
pure virtual

Load a file containing the configuration parameters of the class.

引数
[in]filepathThe location of the .YAML file containing the configuration parameters.
覚え書き
default value is an empty string in which case the default parameters will be loaded.
戻り値
1If the path is not empty and the program loaded the parameters successfully.
0If the path is empty and the program loaded default parameters.
-1If the file location is not valid or the program could not open the file and loaded default parameters from defaults.hpp.
覚え書き
The method is automatically called in the constructor and configures the class.
Loading different parameters will have an effect on the output. This is useful for tuning in case of video processing.
参照
loadParameters

◆ process()

virtual CV_WRAP void cv::stereo::QuasiDenseStereo::process ( const cv::Mat imgLeft,
const cv::Mat imgRight 
)
pure virtual

Main process of the algorithm. This method computes the sparse seeds and then densifies them.

Initially input images are converted to gray-scale and then the sparseMatching method is called to obtain the sparse stereo. Finally quasiDenseMatching is called to densify the corresponding points.

引数
[in]imgLeftThe left Channel of a stereo image pair.
[in]imgRightThe right Channel of a stereo image pair.
覚え書き
If input images are in color, the method assumes that are BGR and converts them to grayscale.
参照
sparseMatching
quasiDenseMatching

◆ saveParameters()

virtual CV_WRAP int cv::stereo::QuasiDenseStereo::saveParameters ( cv::String  filepath)
pure virtual

Save a file containing all the configuration parameters the class is currently set to.

引数
[in]filepathThe location to store the parameters file.
覚え書き
Calling this method with no arguments will result in storing class parameters to a file names "qds_parameters.yaml" in the root project folder.
This method can be used to generate a template file for tuning the class.
参照
loadParameters