Namespace OpenCvSharp.Detail
Classes
- AffineBasedEstimator
Affine transformation based estimator. This estimator uses pairwise transformations estimated by the matcher to estimate the final transformation for each camera.
- AffineBestOf2NearestMatcher
Features matcher similar to cv::detail::BestOf2NearestMatcher which finds two best matches for each feature and leaves the best one only if the ratio between descriptor distances is greater than the threshold match_conf.
Unlike cv::detail::BestOf2NearestMatcher this matcher uses affine transformation (affine transformation estimate will be placed in matches_info).
- BestOf2NearestMatcher
Features matcher which finds two best matches for each feature and leaves the best one only if the ratio between descriptor distances is greater than the threshold match_conf
- BestOf2NearestRangeMatcher
Features matcher similar to cv::detail::BestOf2NearestMatcher which finds two best matches for each feature and leaves the best one only if the ratio between descriptor distances is greater than the threshold match_conf.
Unlike cv::detail::BestOf2NearestMatcher, this matcher only matches images that are no more than range_width apart in the source sequence.
- Blender
Base class for all blenders. Simple blender which puts one image over another.
- BlocksChannelsCompensator
Exposure compensator which tries to remove exposure related artifacts by adjusting image blocks on each channel independently.
- BlocksCompensator
Exposure compensator which tries to remove exposure related artifacts by adjusting image blocks. Shared base for BlocksGainCompensator and BlocksChannelsCompensator; it has no public constructor of its own (matching upstream OpenCV, which does not expose one either).
- BlocksGainCompensator
Exposure compensator which tries to remove exposure related artifacts by adjusting image block intensities.
- BundleAdjusterAffine
Bundle adjuster that expects an affine transformation represented in homogeneous coordinates in R for each camera parameter. Estimates all transformation parameters; the refinement mask is ignored.
- BundleAdjusterAffinePartial
Bundle adjuster that expects an affine transformation with 4 degrees of freedom, represented in homogeneous coordinates in R for each camera parameter. Estimates all transformation parameters; the refinement mask is ignored.
- BundleAdjusterBase
Base class for all camera parameters refinement methods.
- BundleAdjusterRay
Implementation of the camera parameters refinement algorithm which minimizes the sum of the distances between the rays passing through the camera center and a feature. It can estimate focal length; it ignores the refinement mask.
- BundleAdjusterReproj
Implementation of the camera parameters refinement algorithm which minimizes the sum of the reprojection error squares. It can estimate focal length, aspect ratio and principal point.
- CameraParams
Describes camera parameters. Translation is assumed to be zero during the whole stitching pipeline.
- ChannelsCompensator
Exposure compensator which tries to remove exposure related artifacts by adjusting image intensities on each channel independently.
- DpSeamFinder
Seam estimator based on dynamic programming.
- Estimator
Rotation estimator base class. It takes features of all images, pairwise matches between all images and estimates rotations of all cameras.
- ExposureCompensator
Base class for all exposure compensators.
- FeatherBlender
Simple blender which mixes images at its borders.
- FeaturesMatcher
Feature matchers base class.
- GainCompensator
Exposure compensator which tries to remove exposure related artifacts by adjusting image intensities.
- GraphCutSeamFinder
Minimum graph cut-based seam estimator.
- HomographyBasedEstimator
Homography based rotation estimator.
- ImageFeatures
Structure containing image keypoints and descriptors.
- LightGlueFeaturesMatcher
Features matcher that adapts LightGlueMatcher (a DNN-based descriptor matcher) to the stitching pipeline's FeaturesMatcher interface. Requires OpenCV built with the dnn module; otherwise the underlying LightGlueMatcher throws at runtime.
- MatchesInfo
Structure containing information about matches between two images.
It's assumed that there is a transformation between those images. Transformation may be homography or affine transformation based on selected matcher.
- MultiBandBlender
Blender which uses a multi-band blending algorithm.
- NoBundleAdjuster
Stub bundle adjuster that does nothing.
- NoExposureCompensator
Stub exposure compensator which does nothing.
- NoSeamFinder
Stub seam estimator which does nothing.
- SeamFinder
Base class for a seam estimator.
- Timelapser
Base class for timelapse composition. Takes a sequence of images, applies the appropriate shift, and stores the result.
- VoronoiSeamFinder
Voronoi diagram-based seam estimator.
Structs
Enums
- BlenderType
Kind of blender to build (see CreateDefault(BlenderType, bool)).
- ExposureCompensatorType
Kind of exposure compensator to build (see CreateDefault(ExposureCompensatorType)).
- SeamFinderCostFunction
Cost function used by DpSeamFinder and GraphCutSeamFinder.
- SeamFinderType
Kind of seam finder to build (see CreateDefault(SeamFinderType)).
- TimelapserType
Kind of timelapse to build (see Timelapser).