Class cv::stereo::QuasiDenseStereo#
Class containing the methods needed for Quasi Dense Stereo computation. View details
#include <opencv2/xstereo/quasi_dense_stereo.hpp>Collaboration diagram for cv::stereo::QuasiDenseStereo:
Detailed Description#
Class containing the methods needed for Quasi Dense Stereo computation.
This module contains the code to perform quasi dense stereo matching. The method initially starts with a sparse 3D reconstruction based on feature matching across a stereo image pair and subsequently propagates the structure into neighboring image regions. To obtain initial seed correspondences, the algorithm locates Shi and Tomashi features in the left image of the stereo pair and then tracks them using pyramidal Lucas-Kanade in the right image. To densify the sparse correspondences, the algorithm computes the zero-mean normalized cross-correlation (ZNCC) in small patches around every seed pair and uses it as a quality metric for each match. In this code, we introduce a custom structure to store the location and ZNCC value of correspondences called “Match”. Seed Matches are stored in a priority queue sorted according to their ZNCC value, allowing for the best quality Match to be readily available. The algorithm pops Matches and uses them to extract new matches around them. This is done by considering a small neighboring area around each Seed and retrieving correspondences above a certain texture threshold that are not previously computed. New matches are stored in the seed priority queue and used as seeds. The propagation process ends when no additional matches can be retrieved.
Also the original growing scheme idea is described in Lhuillier2000
See also
This code represents the work presented in Stoyanov2010. If this code is useful for your work please cite Stoyanov2010.
Constructor & Destructor Documentation#
~QuasiDenseStereo()#
cv::stereo::QuasiDenseStereo::~QuasiDenseStereo()
destructor Method to free all the memory allocated by matrices and vectors in this class.
Member Function Documentation#
getDenseMatches()#
void cv::stereo::QuasiDenseStereo::getDenseMatches(std::vector< MatchQuasiDense > & denseMatches)
Python:
cv.stereo.QuasiDenseStereo.getDenseMatches() -> denseMatches
Get The dense corresponding points.
Note
The method clears the denseMatches vector.
The returned Match elements inside the sMatches vector, do not use corr member.
Parameters
denseMatches— A vector containing all dense matches.
getDisparity()#
cv::Mat cv::stereo::QuasiDenseStereo::getDisparity()
Python:
cv.stereo.QuasiDenseStereo.getDisparity() -> retval
Compute and return the disparity map based on the correspondences found in the “process” method.
Note
Default level is 50
See also
computeDisparity
quantizeDisparity
Returns
cv::Mat containing a the disparity image in grayscale.
getMatch()#
cv::Point2f cv::stereo::QuasiDenseStereo::getMatch(
const int x,
const int y )
Python:
cv.stereo.QuasiDenseStereo.getMatch(x, y) -> retval
Specify pixel coordinates in the left image and get its corresponding location in the right image.
Note
This method should be always called after process, otherwise the matches will not be correct.
Parameters
x— The x pixel coordinate in the left image channel.y— The y pixel coordinate in the left image channel.
getSparseMatches()#
void cv::stereo::QuasiDenseStereo::getSparseMatches(std::vector< MatchQuasiDense > & sMatches)
Python:
cv.stereo.QuasiDenseStereo.getSparseMatches() -> sMatches
Get The sparse corresponding points.
Note
The method clears the sMatches vector.
The returned Match elements inside the sMatches vector, do not use corr member.
Parameters
sMatches— A vector containing all sparse correspondences.
loadParameters()#
int cv::stereo::QuasiDenseStereo::loadParameters(cv::String filepath)
Python:
cv.stereo.QuasiDenseStereo.loadParameters(filepath) -> retval
Load a file containing the configuration parameters of the class.
Note
default value is an empty string in which case the default parameters will be loaded.
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.
See also
Parameters
filepath— The location of the .YAML file containing the configuration parameters.
process()#
void cv::stereo::QuasiDenseStereo::process(
const cv::Mat & imgLeft,
const cv::Mat & imgRight )
Python:
cv.stereo.QuasiDenseStereo.process(imgLeft, imgRight)
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.
Note
If input images are in color, the method assumes that are BGR and converts them to grayscale.
See also
sparseMatching
quasiDenseMatching
Parameters
imgLeft— The left Channel of a stereo image pair.imgRight— The right Channel of a stereo image pair.
saveParameters()#
int cv::stereo::QuasiDenseStereo::saveParameters(cv::String filepath)
Python:
cv.stereo.QuasiDenseStereo.saveParameters(filepath) -> retval
Save a file containing all the configuration parameters the class is currently set to.
Note
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.
See also
Parameters
filepath— The location to store the parameters file.
create()#
static cv::Ptr< QuasiDenseStereo > cv::stereo::QuasiDenseStereo::create(
cv::Size monoImgSize,
cv::String paramFilepath = cv::String() )
Python:
cv.stereo.QuasiDenseStereo.create(monoImgSize[, paramFilepath]) -> retval
cv.stereo.QuasiDenseStereo_create(monoImgSize[, paramFilepath]) -> retval
Member Data Documentation#
Param#
PropagationParameters cv::stereo::QuasiDenseStereo::Param
Source file#
The documentation for this class was generated from the following file:
opencv2/xstereo/quasi_dense_stereo.hpp