Class used for calculation sparse optical flow and feature tracking with robust local optical flow (RLOF) algorithms.
More...
#include <opencv2/optflow/rlofflow.hpp>
Class used for calculation sparse optical flow and feature tracking with robust local optical flow (RLOF) algorithms.
The RLOF is a fast local optical flow approach described in [238] [239] [240] and [241] similar to the pyramidal iterative Lucas-Kanade method as proposed by [36]. More details and experiments can be found in the following thesis [242]. The implementation is derived from optflow::calcOpticalFlowPyrLK().
For the RLOF configuration see optflow::RLOFOpticalFlowParameter for further details. Parameters have been described in [238], [239], [240] and [241].
- Note
- SIMD parallelization is only available when compiling with SSE4.1.
- See also
- optflow::calcOpticalFlowSparseRLOF(), optflow::RLOFOpticalFlowParameter
◆ create()
Python: |
---|
| cv.optflow.SparseRLOFOpticalFlow.create( | [, rlofParam[, forwardBackwardThreshold]] | ) -> | retval |
| cv.optflow.SparseRLOFOpticalFlow_create( | [, rlofParam[, forwardBackwardThreshold]] | ) -> | retval |
Creates instance of SparseRLOFOpticalFlow.
- Parameters
-
rlofParam | see setRLOFOpticalFlowParameter |
forwardBackwardThreshold | see setForwardBackward |
◆ getForwardBackward()
virtual float cv::optflow::SparseRLOFOpticalFlow::getForwardBackward |
( |
| ) |
const |
|
pure virtual |
Python: |
---|
| cv.optflow.SparseRLOFOpticalFlow.getForwardBackward( | | ) -> | retval |
◆ getRLOFOpticalFlowParameter()
Python: |
---|
| cv.optflow.SparseRLOFOpticalFlow.getRLOFOpticalFlowParameter( | | ) -> | retval |
◆ setForwardBackward()
virtual void cv::optflow::SparseRLOFOpticalFlow::setForwardBackward |
( |
float | val | ) |
|
|
pure virtual |
Python: |
---|
| cv.optflow.SparseRLOFOpticalFlow.setForwardBackward( | val | ) -> | None |
Threshold for the forward backward confidence check.
For each feature point a motion vector \( d_{I0,I1}(\mathbf{x}) \) is computed. If the forward backward error
\[ EP_{FB} = || d_{I0,I1} + d_{I1,I0} || \]
is larger than threshold given by this function then the status will not be used by the following vector field interpolation. \( d_{I1,I0} \) denotes the backward flow. Note, the forward backward test will only be applied if the threshold > 0. This may results into a doubled runtime for the motion estimation.
- See also
- setForwardBackward
◆ setRLOFOpticalFlowParameter()
Python: |
---|
| cv.optflow.SparseRLOFOpticalFlow.setRLOFOpticalFlowParameter( | val | ) -> | None |
The documentation for this class was generated from the following file: