Expand description
Optical Flow Algorithms
Dense optical flow algorithms compute motion for each point:
- cv::optflow::calcOpticalFlowSF
- cv::optflow::createOptFlow_DeepFlow
Motion templates is alternative technique for detecting motion and computing its direction. See samples/motempl.py.
- cv::motempl::updateMotionHistory
- cv::motempl::calcMotionGradient
- cv::motempl::calcGlobalOrientation
- cv::motempl::segmentMotion
Functions reading and writing .flo files in “Middlebury” format, see: http://vision.middlebury.edu/flow/code/flow-code/README.txt
- cv::optflow::readOpticalFlow
- cv::optflow::writeOpticalFlow
Modules
Structs
- Fast dense optical flow computation based on robust local optical flow (RLOF) algorithms and sparse-to-dense interpolation scheme.
- “Dual TV L1” Optical Flow Algorithm.
- Class encapsulating matching parameters.
- Class encapsulating training parameters.
- Class encapsulating training samples.
- Class for individual tree.
- PCAFlow algorithm.
- This class can be used for imposing a learned prior on the resulting optical flow. Solution will be regularized according to this prior. You need to generate appropriate prior file with “learn_prior.py” script beforehand.
- This is used store and set up the parameters of the robust local optical flow (RLOF) algoritm.
- Class used for calculation sparse optical flow and feature tracking with robust local optical flow (RLOF) algorithms.
Enums
- Descriptor types for the Global Patch Collider.
Constants
- Better quality but slow
- Worse quality but much faster
- < Edge-preserving interpolation using ximgproc::EdgeAwareInterpolator, see Revaud2015,Geistert2016.
- < Fast geodesic interpolation, see Geistert2016
- < SLIC based robust interpolation using ximgproc::RICInterpolator, see Hu2017.
- < Apply a adaptive support region obtained by cross-based segmentation as described in Senst2014
- < Apply a constant support region
- < Apply optimized iterative refinement based bilinear equation solutions as described in Senst2013
- < Apply standard iterative refinement
Traits
- Mutable methods for crate::optflow::DenseRLOFOpticalFlow
- Constant methods for crate::optflow::DenseRLOFOpticalFlow
- Mutable methods for crate::optflow::DualTVL1OpticalFlow
- Constant methods for crate::optflow::DualTVL1OpticalFlow
- Mutable methods for crate::optflow::GPCDetails
- Constant methods for crate::optflow::GPCDetails
- Mutable methods for crate::optflow::GPCPatchDescriptor
- Constant methods for crate::optflow::GPCPatchDescriptor
- Mutable methods for crate::optflow::GPCPatchSample
- Constant methods for crate::optflow::GPCPatchSample
- Mutable methods for crate::optflow::GPCTrainingSamples
- Constant methods for crate::optflow::GPCTrainingSamples
- Mutable methods for crate::optflow::GPCTree
- Constant methods for crate::optflow::GPCTree
- Mutable methods for crate::optflow::OpticalFlowPCAFlow
- Constant methods for crate::optflow::OpticalFlowPCAFlow
- Mutable methods for crate::optflow::PCAPrior
- Constant methods for crate::optflow::PCAPrior
- Mutable methods for crate::optflow::RLOFOpticalFlowParameter
- Constant methods for crate::optflow::RLOFOpticalFlowParameter
- Mutable methods for crate::optflow::SparseRLOFOpticalFlow
- Constant methods for crate::optflow::SparseRLOFOpticalFlow
Functions
- Calculates a global motion orientation in a selected region.
- Calculates a gradient orientation of a motion history image.
- Fast dense optical flow computation based on robust local optical flow (RLOF) algorithms and sparse-to-dense interpolation scheme.
- Calculate an optical flow using “SimpleFlow” algorithm.
- Calculate an optical flow using “SimpleFlow” algorithm.
- Calculates fast optical flow for a sparse feature set using the robust local optical flow (RLOF) similar to optflow::calcOpticalFlowPyrLK().
- Fast dense optical flow based on PyrLK sparse matches interpolation.
- DeepFlow optical flow algorithm implementation.
- Additional interface to the Dense RLOF algorithm - optflow::calcOpticalFlowDenseRLOF()
- Creates instance of cv::DenseOpticalFlow
- Additional interface to the Farneback’s algorithm - calcOpticalFlowFarneback()
- Creates an instance of PCAFlow
- Additional interface to the SimpleFlow algorithm - calcOpticalFlowSF()
- Additional interface to the Sparse RLOF algorithm - optflow::calcOpticalFlowSparseRLOF()
- Additional interface to the SparseToDenseFlow algorithm - calcOpticalFlowSparseToDense()
- Splits a motion history image into a few parts corresponding to separate independent motions (for example, left hand, right hand).
- Updates the motion history image by a moving silhouette.