OpenCV
4.8.0
Open Source Computer Vision
|
Implementation of the camera parameters refinement algorithm which minimizes sum of the reprojection error squares. More...
#include <opencv2/stitching/detail/motion_estimators.hpp>
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. More... | |
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. More... | |
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. More... | |
Protected Attributes inherited from cv::detail::BundleAdjusterBase | |
Mat | cam_params_ |
double | conf_thresh_ |
std::vector< std::pair< int, int > > | edges_ |
const ImageFeatures * | features_ |
int | num_errs_per_measurement_ |
int | num_images_ |
int | num_params_per_cam_ |
const MatchesInfo * | pairwise_matches_ |
Mat | refinement_mask_ |
TermCriteria | term_criteria_ |
int | total_num_matches_ |
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.
|
inline |