Loading...
Searching...
No Matches
cv::detail::BundleAdjusterReproj Class Reference

Implementation of the camera parameters refinement algorithm which minimizes sum of the reprojection error squares. More...

#include <opencv2/stitching/detail/motion_estimators.hpp>

Inheritance diagram for cv::detail::BundleAdjusterReproj:
cv::detail::BundleAdjusterBase cv::detail::Estimator

Public Member Functions

 BundleAdjusterReproj ()
 
- Public Member Functions inherited from cv::detail::BundleAdjusterBase
double confThresh () const
 
Mat refinementMask () const
 
void setConfThresh (double conf_thresh)
 
void setRefinementMask (const Mat &mask)
 
void setTermCriteria (const TermCriteria &term_criteria)
 
TermCriteria termCriteria ()
 
- Public Member Functions inherited from cv::detail::Estimator
virtual ~Estimator ()
 
bool operator() (const std::vector< ImageFeatures > &features, const std::vector< MatchesInfo > &pairwise_matches, std::vector< CameraParams > &cameras)
 Estimates camera parameters.
 

Additional Inherited Members

- Protected Member Functions inherited from cv::detail::BundleAdjusterBase
 BundleAdjusterBase (int num_params_per_cam, int num_errs_per_measurement)
 Construct a bundle adjuster base instance.
 
virtual void calcError (Mat &err)=0
 Calculates error vector.
 
virtual void calcJacobian (Mat &jac)=0
 Calculates the cost function jacobian.
 
virtual bool estimate (const std::vector< ImageFeatures > &features, const std::vector< MatchesInfo > &pairwise_matches, std::vector< CameraParams > &cameras) CV_OVERRIDE
 This method must implement camera parameters estimation logic in order to make the wrapper detail::Estimator::operator()_ work.
 
virtual void obtainRefinedCameraParams (std::vector< CameraParams > &cameras) const =0
 Gets the refined camera parameters.
 
virtual void setUpInitialCameraParams (const std::vector< CameraParams > &cameras)=0
 Sets initial camera parameter to refine.
 
virtual bool estimate (const std::vector< ImageFeatures > &features, const std::vector< MatchesInfo > &pairwise_matches, std::vector< CameraParams > &cameras)=0
 This method must implement camera parameters estimation logic in order to make the wrapper detail::Estimator::operator()_ work.
 
- Protected Attributes inherited from cv::detail::BundleAdjusterBase
Mat cam_params_
 
double conf_thresh_
 
std::vector< std::pair< int, int > > edges_
 
const ImageFeaturesfeatures_
 
int num_errs_per_measurement_
 
int num_images_
 
int num_params_per_cam_
 
const MatchesInfopairwise_matches_
 
Mat refinement_mask_
 
TermCriteria term_criteria_
 
int total_num_matches_
 

Detailed Description

Implementation of the camera parameters refinement algorithm which minimizes sum of the reprojection error squares.

It can estimate focal length, aspect ratio, principal point. You can affect only on them via the refinement mask.

Constructor & Destructor Documentation

◆ BundleAdjusterReproj()

cv::detail::BundleAdjusterReproj::BundleAdjusterReproj ( )
inline

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