Global Motion Estimation#

Detailed Description#

The video stabilization module contains a set of functions and classes for global motion estimation between point clouds or between images. In the last case features are extracted and matched internally. For the sake of convenience the motion estimation functions are wrapped into classes. Both the functions and the classes are available.

Classes#

Name	Description
`class` `cv::videostab::FromFileMotionReader`	View details
`class` `cv::videostab::GaussianMotionFilter`	View details
`class` `cv::videostab::ImageMotionEstimatorBase`	Base class for global 2D motion estimation methods which take frames as input. View details
`class` `cv::videostab::IMotionStabilizer`	View details
`class` `cv::videostab::KeypointBasedMotionEstimator`	Describes a global 2D motion estimation method which uses keypoints detection and optical flow for matching. View details
`class` `cv::videostab::LpMotionStabilizer`	View details
`class` `cv::videostab::MotionEstimatorBase`	Base class for all global motion estimation methods. View details
`class` `cv::videostab::MotionEstimatorL1`	Describes a global 2D motion estimation method which minimizes L1 error. View details
`class` `cv::videostab::MotionEstimatorRansacL2`	Describes a robust RANSAC-based global 2D motion estimation method which minimizes L2 error. View details
`class` `cv::videostab::MotionFilterBase`	View details
`class` `cv::videostab::MotionStabilizationPipeline`	View details
`struct` `cv::videostab::RansacParams`	Describes RANSAC method parameters. View details
`class` `cv::videostab::ToFileMotionWriter`	View details

Enumerations#

enum cv::videostab::MotionModel {
    cv::videostab::MM_TRANSLATION = 0,
    cv::videostab::MM_TRANSLATION_AND_SCALE = 1,
    cv::videostab::MM_ROTATION = 2,
    cv::videostab::MM_RIGID = 3,
    cv::videostab::MM_SIMILARITY = 4,
    cv::videostab::MM_AFFINE = 5,
    cv::videostab::MM_HOMOGRAPHY = 6,
    cv::videostab::MM_UNKNOWN = 7
}

Describes motion model between two point clouds. View details

Functions#

Return	Name	Description
	`cv::GaussianMotionFilter( int radius = 15, float stdev = -1.f )`
	`cv::RansacParams( int size, float thresh, float eps, float prob )`	Constructor.
`Mat`	`cv::ensureInclusionConstraint( const Mat & M, Size size, float trimRatio )`
`Mat`	`cv::estimateGlobalMotionLeastSquares( InputOutputArray points0, InputOutputArray points1, int model = MM_AFFINE, float * rmse = 0 )`	Estimates best global motion between two 2D point clouds in the least-squares sense.
`Mat`	`cv::estimateGlobalMotionRansac( InputArray points0, InputArray points1, int model = MM_AFFINE, const RansacParams & params = RansacParams::default2dMotion(MM_AFFINE), float * rmse = 0, int * ninliers = 0 )`	Estimates best global motion between two 2D point clouds robustly (using RANSAC method).
`float`	`cv::estimateOptimalTrimRatio( const Mat & M, Size size )`
`Mat`	`cv::getMotion( int from, int to, const std::vector< Mat > & motions )`	Computes motion between two frames assuming that all the intermediate motions are known.

Enumeration Type Documentation#

MotionModel#

enum cv::videostab::MotionModel

#include <opencv2/videostab/motion_core.hpp>

Describes motion model between two point clouds.

Enumerator:

MM_TRANSLATION

MM_TRANSLATION_AND_SCALE

MM_ROTATION

MM_RIGID

MM_SIMILARITY

MM_AFFINE

MM_HOMOGRAPHY

MM_UNKNOWN

Function Documentation#

ensureInclusionConstraint()#

Mat cv::videostab::ensureInclusionConstraint(
const Mat & M,
Size size,
float trimRatio )

#include <opencv2/videostab/motion_stabilizing.hpp>

estimateGlobalMotionLeastSquares()#

Mat cv::videostab::estimateGlobalMotionLeastSquares(
InputOutputArray points0,
InputOutputArray points1,
int model = MM_AFFINE,
float * rmse = 0 )

#include <opencv2/videostab/global_motion.hpp>

Estimates best global motion between two 2D point clouds in the least-squares sense.

Note

Works in-place and changes input point arrays.

Parameters

points0 — Source set of 2D points (32F).
points1 — Destination set of 2D points (32F).
model — Motion model (up to MM_AFFINE).
rmse — Final root-mean-square error.

Returns

3x3 2D transformation matrix (32F).

estimateGlobalMotionRansac()#

Mat cv::videostab::estimateGlobalMotionRansac(
InputArray points0,
InputArray points1,
int model = MM_AFFINE,
const RansacParams & params = RansacParams::default2dMotion(MM_AFFINE),
float * rmse = 0,
int * ninliers = 0 )

#include <opencv2/videostab/global_motion.hpp>

Estimates best global motion between two 2D point clouds robustly (using RANSAC method).

Parameters

points0 — Source set of 2D points (32F).
points1 — Destination set of 2D points (32F).
model — Motion model. See cv::videostab::MotionModel.
params — RANSAC method parameters. See videostab::RansacParams.
rmse — Final root-mean-square error.
ninliers — Final number of inliers.

estimateOptimalTrimRatio()#

float cv::videostab::estimateOptimalTrimRatio(
const Mat & M,
Size size )

#include <opencv2/videostab/motion_stabilizing.hpp>

getMotion()#

Mat cv::videostab::getMotion(
int from,
int to,
const std::vector< Mat > & motions )

#include <opencv2/videostab/global_motion.hpp>

Computes motion between two frames assuming that all the intermediate motions are known.

Parameters

from — Source frame index.
to — Destination frame index.
motions — Pair-wise motions. motions[i] denotes motion from the frame i to the frame i+1

Returns

Motion from the Source frame to the Destination frame.

Here is the call graph for this function: