Module optflow

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§

prelude

Structs§

DenseRLOFOpticalFlow: Fast dense optical flow computation based on robust local optical flow (RLOF) algorithms and sparse-to-dense interpolation scheme.
DualTVL1OpticalFlow: “Dual TV L1” Optical Flow Algorithm.
GPCDetails
GPCMatchingParams: Class encapsulating matching parameters.
GPCPatchDescriptor
GPCPatchSample
GPCTrainingParams: Class encapsulating training parameters.
GPCTrainingSamples: Class encapsulating training samples.
GPCTree: Class for individual tree.
GPCTree_Node
OpticalFlowPCAFlow: PCAFlow algorithm.
PCAPrior: 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.
RLOFOpticalFlowParameter: This is used store and set up the parameters of the robust local optical flow (RLOF) algoritm.
SparseRLOFOpticalFlow: Class used for calculation sparse optical flow and feature tracking with robust local optical flow (RLOF) algorithms.

Enums§

GPCDescType: Descriptor types for the Global Patch Collider.
InterpolationType
SolverType
SupportRegionType

Constants§

GPC_DESCRIPTOR_DCT: Better quality but slow
GPC_DESCRIPTOR_WHT: Worse quality but much faster
INTERP_EPIC: < Edge-preserving interpolation using ximgproc::EdgeAwareInterpolator, see Revaud2015,Geistert2016.
INTERP_GEO: < Fast geodesic interpolation, see Geistert2016
INTERP_RIC: < SLIC based robust interpolation using ximgproc::RICInterpolator, see Hu2017.
SR_CROSS: < Apply a adaptive support region obtained by cross-based segmentation as described in Senst2014
SR_FIXED: < Apply a constant support region
ST_BILINEAR: < Apply optimized iterative refinement based bilinear equation solutions as described in Senst2013
ST_STANDART: < Apply standard iterative refinement

Traits§

DenseRLOFOpticalFlowTrait: Mutable methods for crate::optflow::DenseRLOFOpticalFlow
DenseRLOFOpticalFlowTraitConst: Constant methods for crate::optflow::DenseRLOFOpticalFlow
DualTVL1OpticalFlowTrait: Mutable methods for crate::optflow::DualTVL1OpticalFlow
DualTVL1OpticalFlowTraitConst: Constant methods for crate::optflow::DualTVL1OpticalFlow
GPCDetailsTrait: Mutable methods for crate::optflow::GPCDetails
GPCDetailsTraitConst: Constant methods for crate::optflow::GPCDetails
GPCPatchDescriptorTrait: Mutable methods for crate::optflow::GPCPatchDescriptor
GPCPatchDescriptorTraitConst: Constant methods for crate::optflow::GPCPatchDescriptor
GPCPatchSampleTrait: Mutable methods for crate::optflow::GPCPatchSample
GPCPatchSampleTraitConst: Constant methods for crate::optflow::GPCPatchSample
GPCTrainingSamplesTrait: Mutable methods for crate::optflow::GPCTrainingSamples
GPCTrainingSamplesTraitConst: Constant methods for crate::optflow::GPCTrainingSamples
GPCTreeTrait: Mutable methods for crate::optflow::GPCTree
GPCTreeTraitConst: Constant methods for crate::optflow::GPCTree
OpticalFlowPCAFlowTrait: Mutable methods for crate::optflow::OpticalFlowPCAFlow
OpticalFlowPCAFlowTraitConst: Constant methods for crate::optflow::OpticalFlowPCAFlow
PCAPriorTrait: Mutable methods for crate::optflow::PCAPrior
PCAPriorTraitConst: Constant methods for crate::optflow::PCAPrior
RLOFOpticalFlowParameterTrait: Mutable methods for crate::optflow::RLOFOpticalFlowParameter
RLOFOpticalFlowParameterTraitConst: Constant methods for crate::optflow::RLOFOpticalFlowParameter
SparseRLOFOpticalFlowTrait: Mutable methods for crate::optflow::SparseRLOFOpticalFlow
SparseRLOFOpticalFlowTraitConst: Constant methods for crate::optflow::SparseRLOFOpticalFlow

Functions§

calc_global_orientation: Calculates a global motion orientation in a selected region.
calc_motion_gradient: Calculates a gradient orientation of a motion history image.
calc_motion_gradient_def: Calculates a gradient orientation of a motion history image.
calc_optical_flow_dense_rlof: Fast dense optical flow computation based on robust local optical flow (RLOF) algorithms and sparse-to-dense interpolation scheme.
calc_optical_flow_dense_rlof_def: Fast dense optical flow computation based on robust local optical flow (RLOF) algorithms and sparse-to-dense interpolation scheme.
calc_optical_flow_sf: Calculate an optical flow using “SimpleFlow” algorithm.
calc_optical_flow_sf_1: Calculate an optical flow using “SimpleFlow” algorithm.
calc_optical_flow_sparse_rlof: Calculates fast optical flow for a sparse feature set using the robust local optical flow (RLOF) similar to optflow::calcOpticalFlowPyrLK().
calc_optical_flow_sparse_rlof_def: Calculates fast optical flow for a sparse feature set using the robust local optical flow (RLOF) similar to optflow::calcOpticalFlowPyrLK().
calc_optical_flow_sparse_to_dense: Fast dense optical flow based on PyrLK sparse matches interpolation.
calc_optical_flow_sparse_to_dense_def: Fast dense optical flow based on PyrLK sparse matches interpolation.
create_opt_flow_deep_flow: DeepFlow optical flow algorithm implementation.
create_opt_flow_dense_rlof: Additional interface to the Dense RLOF algorithm - optflow::calcOpticalFlowDenseRLOF()
create_opt_flow_dual_tvl1: Creates instance of cv::DenseOpticalFlow
create_opt_flow_farneback: Additional interface to the Farneback’s algorithm - calcOpticalFlowFarneback()
create_opt_flow_pca_flow: Creates an instance of PCAFlow
create_opt_flow_simple_flow: Additional interface to the SimpleFlow algorithm - calcOpticalFlowSF()
create_opt_flow_sparse_rlof: Additional interface to the Sparse RLOF algorithm - optflow::calcOpticalFlowSparseRLOF()
create_opt_flow_sparse_to_dense: Additional interface to the SparseToDenseFlow algorithm - calcOpticalFlowSparseToDense()
read
segment_motion: Splits a motion history image into a few parts corresponding to separate independent motions (for example, left hand, right hand).
update_motion_history: Updates the motion history image by a moving silhouette.
write

Type Aliases§

GPCSamplesVector

Module optflowCopy item path