Autocalibration

Detailed Description

Functions
bool	cv::detail::calibrateRotatingCamera (const std::vector< Mat > &Hs, Mat &K)
void	cv::detail::estimateFocal (const std::vector< ImageFeatures > &features, const std::vector< MatchesInfo > &pairwise_matches, std::vector< double > &focals)
	Estimates focal lengths for each given camera.
void	cv::detail::focalsFromHomography (const Mat &H, double &f0, double &f1, bool &f0_ok, bool &f1_ok)
	Tries to estimate focal lengths from the given homography under the assumption that the camera undergoes rotations around its centre only.

Function Documentation

calibrateRotatingCamera()

bool cv::detail::calibrateRotatingCamera	(	const std::vector< Mat > &	Hs,
		Mat &	K
	)

Python:
	cv.detail.calibrateRotatingCamera(	Hs[, K]	) ->	retval, K

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

estimateFocal()

void cv::detail::estimateFocal	(	const std::vector< ImageFeatures > &	features,
		const std::vector< MatchesInfo > &	pairwise_matches,
		std::vector< double > &	focals
	)

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

Estimates focal lengths for each given camera.

Parameters

features	Features of images.
pairwise_matches	Matches between all image pairs.
focals	Estimated focal lengths for each camera.

focalsFromHomography()

void cv::detail::focalsFromHomography	(	const Mat &	H,
		double &	f0,
		double &	f1,
		bool &	f0_ok,
		bool &	f1_ok
	)

Python:
	cv.detail.focalsFromHomography(	H, f0, f1, f0_ok, f1_ok	) ->	None

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

Tries to estimate focal lengths from the given homography under the assumption that the camera undergoes rotations around its centre only.

Parameters

H	Homography.
f0	Estimated focal length along X axis.
f1	Estimated focal length along Y axis.
f0_ok	True, if f0 was estimated successfully, false otherwise.
f1_ok	True, if f1 was estimated successfully, false otherwise.

See "Construction of Panoramic Image Mosaics with Global and Local Alignment" by Heung-Yeung Shum and Richard Szeliski.