1
/*M///////////////////////////////////////////////////////////////////////////////////////
3
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
5
// By downloading, copying, installing or using the software you agree to this license.
6
// If you do not agree to this license, do not download, install,
7
// copy or use the software.
11
// For Open Source Computer Vision Library
13
// Copyright (C) 2000-2008, Intel Corporation, all rights reserved.
14
// Copyright (C) 2009, Willow Garage Inc., all rights reserved.
15
// Copyright (C) 2013, OpenCV Foundation, all rights reserved.
16
// Third party copyrights are property of their respective owners.
18
// Redistribution and use in source and binary forms, with or without modification,
19
// are permitted provided that the following conditions are met:
21
// * Redistribution's of source code must retain the above copyright notice,
22
// this list of conditions and the following disclaimer.
24
// * Redistribution's in binary form must reproduce the above copyright notice,
25
// this list of conditions and the following disclaimer in the documentation
26
// and/or other materials provided with the distribution.
28
// * The name of the copyright holders may not be used to endorse or promote products
29
// derived from this software without specific prior written permission.
31
// This software is provided by the copyright holders and contributors "as is" and
32
// any express or implied warranties, including, but not limited to, the implied
33
// warranties of merchantability and fitness for a particular purpose are disclaimed.
34
// In no event shall the Intel Corporation or contributors be liable for any direct,
35
// indirect, incidental, special, exemplary, or consequential damages
36
// (including, but not limited to, procurement of substitute goods or services;
37
// loss of use, data, or profits; or business interruption) however caused
38
// and on any theory of liability, whether in contract, strict liability,
39
// or tort (including negligence or otherwise) arising in any way out of
40
// the use of this software, even if advised of the possibility of such damage.
44
#ifndef OPENCV_TRACKING_HPP
45
#define OPENCV_TRACKING_HPP
47
#include "opencv2/core.hpp"
48
#include "opencv2/imgproc.hpp"
53
//! @addtogroup video_track
56
enum { OPTFLOW_USE_INITIAL_FLOW = 4,
57
OPTFLOW_LK_GET_MIN_EIGENVALS = 8,
58
OPTFLOW_FARNEBACK_GAUSSIAN = 256
61
/** @brief Finds an object center, size, and orientation.
63
@param probImage Back projection of the object histogram. See calcBackProject.
64
@param window Initial search window.
65
@param criteria Stop criteria for the underlying meanShift.
67
(in old interfaces) Number of iterations CAMSHIFT took to converge
68
The function implements the CAMSHIFT object tracking algorithm @cite Bradski98 . First, it finds an
69
object center using meanShift and then adjusts the window size and finds the optimal rotation. The
70
function returns the rotated rectangle structure that includes the object position, size, and
71
orientation. The next position of the search window can be obtained with RotatedRect::boundingRect()
73
See the OpenCV sample camshiftdemo.c that tracks colored objects.
76
- (Python) A sample explaining the camshift tracking algorithm can be found at
77
opencv_source_code/samples/python/camshift.py
79
CV_EXPORTS_W RotatedRect CamShift( InputArray probImage, CV_IN_OUT Rect& window,
80
TermCriteria criteria );
81
/** @example samples/cpp/camshiftdemo.cpp
82
An example using the mean-shift tracking algorithm
85
/** @brief Finds an object on a back projection image.
87
@param probImage Back projection of the object histogram. See calcBackProject for details.
88
@param window Initial search window.
89
@param criteria Stop criteria for the iterative search algorithm.
91
: Number of iterations CAMSHIFT took to converge.
92
The function implements the iterative object search algorithm. It takes the input back projection of
93
an object and the initial position. The mass center in window of the back projection image is
94
computed and the search window center shifts to the mass center. The procedure is repeated until the
95
specified number of iterations criteria.maxCount is done or until the window center shifts by less
96
than criteria.epsilon. The algorithm is used inside CamShift and, unlike CamShift , the search
97
window size or orientation do not change during the search. You can simply pass the output of
98
calcBackProject to this function. But better results can be obtained if you pre-filter the back
99
projection and remove the noise. For example, you can do this by retrieving connected components
100
with findContours , throwing away contours with small area ( contourArea ), and rendering the
101
remaining contours with drawContours.
104
CV_EXPORTS_W int meanShift( InputArray probImage, CV_IN_OUT Rect& window, TermCriteria criteria );
106
/** @brief Constructs the image pyramid which can be passed to calcOpticalFlowPyrLK.
108
@param img 8-bit input image.
109
@param pyramid output pyramid.
110
@param winSize window size of optical flow algorithm. Must be not less than winSize argument of
111
calcOpticalFlowPyrLK. It is needed to calculate required padding for pyramid levels.
112
@param maxLevel 0-based maximal pyramid level number.
113
@param withDerivatives set to precompute gradients for the every pyramid level. If pyramid is
114
constructed without the gradients then calcOpticalFlowPyrLK will calculate them internally.
115
@param pyrBorder the border mode for pyramid layers.
116
@param derivBorder the border mode for gradients.
117
@param tryReuseInputImage put ROI of input image into the pyramid if possible. You can pass false
118
to force data copying.
119
@return number of levels in constructed pyramid. Can be less than maxLevel.
121
CV_EXPORTS_W int buildOpticalFlowPyramid( InputArray img, OutputArrayOfArrays pyramid,
122
Size winSize, int maxLevel, bool withDerivatives = true,
123
int pyrBorder = BORDER_REFLECT_101,
124
int derivBorder = BORDER_CONSTANT,
125
bool tryReuseInputImage = true );
127
/** @example samples/cpp/lkdemo.cpp
128
An example using the Lucas-Kanade optical flow algorithm
131
/** @brief Calculates an optical flow for a sparse feature set using the iterative Lucas-Kanade method with
134
@param prevImg first 8-bit input image or pyramid constructed by buildOpticalFlowPyramid.
135
@param nextImg second input image or pyramid of the same size and the same type as prevImg.
136
@param prevPts vector of 2D points for which the flow needs to be found; point coordinates must be
137
single-precision floating-point numbers.
138
@param nextPts output vector of 2D points (with single-precision floating-point coordinates)
139
containing the calculated new positions of input features in the second image; when
140
OPTFLOW_USE_INITIAL_FLOW flag is passed, the vector must have the same size as in the input.
141
@param status output status vector (of unsigned chars); each element of the vector is set to 1 if
142
the flow for the corresponding features has been found, otherwise, it is set to 0.
143
@param err output vector of errors; each element of the vector is set to an error for the
144
corresponding feature, type of the error measure can be set in flags parameter; if the flow wasn't
145
found then the error is not defined (use the status parameter to find such cases).
146
@param winSize size of the search window at each pyramid level.
147
@param maxLevel 0-based maximal pyramid level number; if set to 0, pyramids are not used (single
148
level), if set to 1, two levels are used, and so on; if pyramids are passed to input then
149
algorithm will use as many levels as pyramids have but no more than maxLevel.
150
@param criteria parameter, specifying the termination criteria of the iterative search algorithm
151
(after the specified maximum number of iterations criteria.maxCount or when the search window
152
moves by less than criteria.epsilon.
153
@param flags operation flags:
154
- **OPTFLOW_USE_INITIAL_FLOW** uses initial estimations, stored in nextPts; if the flag is
155
not set, then prevPts is copied to nextPts and is considered the initial estimate.
156
- **OPTFLOW_LK_GET_MIN_EIGENVALS** use minimum eigen values as an error measure (see
157
minEigThreshold description); if the flag is not set, then L1 distance between patches
158
around the original and a moved point, divided by number of pixels in a window, is used as a
160
@param minEigThreshold the algorithm calculates the minimum eigen value of a 2x2 normal matrix of
161
optical flow equations (this matrix is called a spatial gradient matrix in @cite Bouguet00), divided
162
by number of pixels in a window; if this value is less than minEigThreshold, then a corresponding
163
feature is filtered out and its flow is not processed, so it allows to remove bad points and get a
166
The function implements a sparse iterative version of the Lucas-Kanade optical flow in pyramids. See
167
@cite Bouguet00 . The function is parallelized with the TBB library.
171
- An example using the Lucas-Kanade optical flow algorithm can be found at
172
opencv_source_code/samples/cpp/lkdemo.cpp
173
- (Python) An example using the Lucas-Kanade optical flow algorithm can be found at
174
opencv_source_code/samples/python/lk_track.py
175
- (Python) An example using the Lucas-Kanade tracker for homography matching can be found at
176
opencv_source_code/samples/python/lk_homography.py
178
CV_EXPORTS_W void calcOpticalFlowPyrLK( InputArray prevImg, InputArray nextImg,
179
InputArray prevPts, InputOutputArray nextPts,
180
OutputArray status, OutputArray err,
181
Size winSize = Size(21,21), int maxLevel = 3,
182
TermCriteria criteria = TermCriteria(TermCriteria::COUNT+TermCriteria::EPS, 30, 0.01),
183
int flags = 0, double minEigThreshold = 1e-4 );
185
/** @brief Computes a dense optical flow using the Gunnar Farneback's algorithm.
187
@param prev first 8-bit single-channel input image.
188
@param next second input image of the same size and the same type as prev.
189
@param flow computed flow image that has the same size as prev and type CV_32FC2.
190
@param pyr_scale parameter, specifying the image scale (\<1) to build pyramids for each image;
191
pyr_scale=0.5 means a classical pyramid, where each next layer is twice smaller than the previous
193
@param levels number of pyramid layers including the initial image; levels=1 means that no extra
194
layers are created and only the original images are used.
195
@param winsize averaging window size; larger values increase the algorithm robustness to image
196
noise and give more chances for fast motion detection, but yield more blurred motion field.
197
@param iterations number of iterations the algorithm does at each pyramid level.
198
@param poly_n size of the pixel neighborhood used to find polynomial expansion in each pixel;
199
larger values mean that the image will be approximated with smoother surfaces, yielding more
200
robust algorithm and more blurred motion field, typically poly_n =5 or 7.
201
@param poly_sigma standard deviation of the Gaussian that is used to smooth derivatives used as a
202
basis for the polynomial expansion; for poly_n=5, you can set poly_sigma=1.1, for poly_n=7, a
203
good value would be poly_sigma=1.5.
204
@param flags operation flags that can be a combination of the following:
205
- **OPTFLOW_USE_INITIAL_FLOW** uses the input flow as an initial flow approximation.
206
- **OPTFLOW_FARNEBACK_GAUSSIAN** uses the Gaussian \f$\texttt{winsize}\times\texttt{winsize}\f$
207
filter instead of a box filter of the same size for optical flow estimation; usually, this
208
option gives z more accurate flow than with a box filter, at the cost of lower speed;
209
normally, winsize for a Gaussian window should be set to a larger value to achieve the same
212
The function finds an optical flow for each prev pixel using the @cite Farneback2003 algorithm so that
214
\f[\texttt{prev} (y,x) \sim \texttt{next} ( y + \texttt{flow} (y,x)[1], x + \texttt{flow} (y,x)[0])\f]
218
- An example using the optical flow algorithm described by Gunnar Farneback can be found at
219
opencv_source_code/samples/cpp/fback.cpp
220
- (Python) An example using the optical flow algorithm described by Gunnar Farneback can be
221
found at opencv_source_code/samples/python/opt_flow.py
223
CV_EXPORTS_W void calcOpticalFlowFarneback( InputArray prev, InputArray next, InputOutputArray flow,
224
double pyr_scale, int levels, int winsize,
225
int iterations, int poly_n, double poly_sigma,
228
/** @brief Computes an optimal affine transformation between two 2D point sets.
230
@param src First input 2D point set stored in std::vector or Mat, or an image stored in Mat.
231
@param dst Second input 2D point set of the same size and the same type as A, or another image.
232
@param fullAffine If true, the function finds an optimal affine transformation with no additional
233
restrictions (6 degrees of freedom). Otherwise, the class of transformations to choose from is
234
limited to combinations of translation, rotation, and uniform scaling (4 degrees of freedom).
236
The function finds an optimal affine transform *[A|b]* (a 2 x 3 floating-point matrix) that
237
approximates best the affine transformation between:
240
* Two raster images. In this case, the function first finds some features in the src image and
241
finds the corresponding features in dst image. After that, the problem is reduced to the first
243
In case of point sets, the problem is formulated as follows: you need to find a 2x2 matrix *A* and
244
2x1 vector *b* so that:
246
\f[[A^*|b^*] = arg \min _{[A|b]} \sum _i \| \texttt{dst}[i] - A { \texttt{src}[i]}^T - b \| ^2\f]
247
where src[i] and dst[i] are the i-th points in src and dst, respectively
248
\f$[A|b]\f$ can be either arbitrary (when fullAffine=true ) or have a form of
249
\f[\begin{bmatrix} a_{11} & a_{12} & b_1 \\ -a_{12} & a_{11} & b_2 \end{bmatrix}\f]
250
when fullAffine=false.
252
@deprecated Use cv::estimateAffine2D, cv::estimateAffinePartial2D instead. If you are using this function
253
with images, extract points using cv::calcOpticalFlowPyrLK and then use the estimation functions.
256
estimateAffine2D, estimateAffinePartial2D, getAffineTransform, getPerspectiveTransform, findHomography
258
CV_DEPRECATED CV_EXPORTS Mat estimateRigidTransform( InputArray src, InputArray dst, bool fullAffine );
262
MOTION_TRANSLATION = 0,
263
MOTION_EUCLIDEAN = 1,
265
MOTION_HOMOGRAPHY = 3
268
/** @brief Computes the Enhanced Correlation Coefficient value between two images @cite EP08 .
270
@param templateImage single-channel template image; CV_8U or CV_32F array.
271
@param inputImage single-channel input image to be warped to provide an image similar to
272
templateImage, same type as templateImage.
273
@param inputMask An optional mask to indicate valid values of inputImage.
279
CV_EXPORTS_W double computeECC(InputArray templateImage, InputArray inputImage, InputArray inputMask = noArray());
281
/** @example samples/cpp/image_alignment.cpp
282
An example using the image alignment ECC algorithm
285
/** @brief Finds the geometric transform (warp) between two images in terms of the ECC criterion @cite EP08 .
287
@param templateImage single-channel template image; CV_8U or CV_32F array.
288
@param inputImage single-channel input image which should be warped with the final warpMatrix in
289
order to provide an image similar to templateImage, same type as templateImage.
290
@param warpMatrix floating-point \f$2\times 3\f$ or \f$3\times 3\f$ mapping matrix (warp).
291
@param motionType parameter, specifying the type of motion:
292
- **MOTION_TRANSLATION** sets a translational motion model; warpMatrix is \f$2\times 3\f$ with
293
the first \f$2\times 2\f$ part being the unity matrix and the rest two parameters being
295
- **MOTION_EUCLIDEAN** sets a Euclidean (rigid) transformation as motion model; three
296
parameters are estimated; warpMatrix is \f$2\times 3\f$.
297
- **MOTION_AFFINE** sets an affine motion model (DEFAULT); six parameters are estimated;
298
warpMatrix is \f$2\times 3\f$.
299
- **MOTION_HOMOGRAPHY** sets a homography as a motion model; eight parameters are
300
estimated;\`warpMatrix\` is \f$3\times 3\f$.
301
@param criteria parameter, specifying the termination criteria of the ECC algorithm;
302
criteria.epsilon defines the threshold of the increment in the correlation coefficient between two
303
iterations (a negative criteria.epsilon makes criteria.maxcount the only termination criterion).
304
Default values are shown in the declaration above.
305
@param inputMask An optional mask to indicate valid values of inputImage.
306
@param gaussFiltSize An optional value indicating size of gaussian blur filter; (DEFAULT: 5)
308
The function estimates the optimum transformation (warpMatrix) with respect to ECC criterion
309
(@cite EP08), that is
311
\f[\texttt{warpMatrix} = \texttt{warpMatrix} = \arg\max_{W} \texttt{ECC}(\texttt{templateImage}(x,y),\texttt{inputImage}(x',y'))\f]
315
\f[\begin{bmatrix} x' \\ y' \end{bmatrix} = W \cdot \begin{bmatrix} x \\ y \\ 1 \end{bmatrix}\f]
317
(the equation holds with homogeneous coordinates for homography). It returns the final enhanced
318
correlation coefficient, that is the correlation coefficient between the template image and the
319
final warped input image. When a \f$3\times 3\f$ matrix is given with motionType =0, 1 or 2, the third
322
Unlike findHomography and estimateRigidTransform, the function findTransformECC implements an
323
area-based alignment that builds on intensity similarities. In essence, the function updates the
324
initial transformation that roughly aligns the images. If this information is missing, the identity
325
warp (unity matrix) is used as an initialization. Note that if images undergo strong
326
displacements/rotations, an initial transformation that roughly aligns the images is necessary
327
(e.g., a simple euclidean/similarity transform that allows for the images showing the same image
328
content approximately). Use inverse warping in the second image to take an image close to the first
329
one, i.e. use the flag WARP_INVERSE_MAP with warpAffine or warpPerspective. See also the OpenCV
330
sample image_alignment.cpp that demonstrates the use of the function. Note that the function throws
331
an exception if algorithm does not converges.
334
computeECC, estimateAffine2D, estimateAffinePartial2D, findHomography
336
CV_EXPORTS_W double findTransformECC( InputArray templateImage, InputArray inputImage,
337
InputOutputArray warpMatrix, int motionType,
338
TermCriteria criteria,
339
InputArray inputMask, int gaussFiltSize);
343
double findTransformECC(InputArray templateImage, InputArray inputImage,
344
InputOutputArray warpMatrix, int motionType = MOTION_AFFINE,
345
TermCriteria criteria = TermCriteria(TermCriteria::COUNT+TermCriteria::EPS, 50, 0.001),
346
InputArray inputMask = noArray());
348
/** @example samples/cpp/kalman.cpp
349
An example using the standard Kalman filter
352
/** @brief Kalman filter class.
354
The class implements a standard Kalman filter <http://en.wikipedia.org/wiki/Kalman_filter>,
355
@cite Welch95 . However, you can modify transitionMatrix, controlMatrix, and measurementMatrix to get
356
an extended Kalman filter functionality.
357
@note In C API when CvKalman\* kalmanFilter structure is not needed anymore, it should be released
358
with cvReleaseKalman(&kalmanFilter)
360
class CV_EXPORTS_W KalmanFilter
363
CV_WRAP KalmanFilter();
365
@param dynamParams Dimensionality of the state.
366
@param measureParams Dimensionality of the measurement.
367
@param controlParams Dimensionality of the control vector.
368
@param type Type of the created matrices that should be CV_32F or CV_64F.
370
CV_WRAP KalmanFilter( int dynamParams, int measureParams, int controlParams = 0, int type = CV_32F );
372
/** @brief Re-initializes Kalman filter. The previous content is destroyed.
374
@param dynamParams Dimensionality of the state.
375
@param measureParams Dimensionality of the measurement.
376
@param controlParams Dimensionality of the control vector.
377
@param type Type of the created matrices that should be CV_32F or CV_64F.
379
void init( int dynamParams, int measureParams, int controlParams = 0, int type = CV_32F );
381
/** @brief Computes a predicted state.
383
@param control The optional input control
385
CV_WRAP const Mat& predict( const Mat& control = Mat() );
387
/** @brief Updates the predicted state from the measurement.
389
@param measurement The measured system parameters
391
CV_WRAP const Mat& correct( const Mat& measurement );
393
CV_PROP_RW Mat statePre; //!< predicted state (x'(k)): x(k)=A*x(k-1)+B*u(k)
394
CV_PROP_RW Mat statePost; //!< corrected state (x(k)): x(k)=x'(k)+K(k)*(z(k)-H*x'(k))
395
CV_PROP_RW Mat transitionMatrix; //!< state transition matrix (A)
396
CV_PROP_RW Mat controlMatrix; //!< control matrix (B) (not used if there is no control)
397
CV_PROP_RW Mat measurementMatrix; //!< measurement matrix (H)
398
CV_PROP_RW Mat processNoiseCov; //!< process noise covariance matrix (Q)
399
CV_PROP_RW Mat measurementNoiseCov;//!< measurement noise covariance matrix (R)
400
CV_PROP_RW Mat errorCovPre; //!< priori error estimate covariance matrix (P'(k)): P'(k)=A*P(k-1)*At + Q)*/
401
CV_PROP_RW Mat gain; //!< Kalman gain matrix (K(k)): K(k)=P'(k)*Ht*inv(H*P'(k)*Ht+R)
402
CV_PROP_RW Mat errorCovPost; //!< posteriori error estimate covariance matrix (P(k)): P(k)=(I-K(k)*H)*P'(k)
404
// temporary matrices
413
/** @brief Read a .flo file
415
@param path Path to the file to be loaded
417
The function readOpticalFlow loads a flow field from a file and returns it as a single matrix.
418
Resulting Mat has a type CV_32FC2 - floating-point, 2-channel. First channel corresponds to the
419
flow in the horizontal direction (u), second - vertical (v).
421
CV_EXPORTS_W Mat readOpticalFlow( const String& path );
422
/** @brief Write a .flo to disk
424
@param path Path to the file to be written
425
@param flow Flow field to be stored
427
The function stores a flow field in a file, returns true on success, false otherwise.
428
The flow field must be a 2-channel, floating-point matrix (CV_32FC2). First channel corresponds
429
to the flow in the horizontal direction (u), second - vertical (v).
431
CV_EXPORTS_W bool writeOpticalFlow( const String& path, InputArray flow );
434
Base class for dense optical flow algorithms
436
class CV_EXPORTS_W DenseOpticalFlow : public Algorithm
439
/** @brief Calculates an optical flow.
441
@param I0 first 8-bit single-channel input image.
442
@param I1 second input image of the same size and the same type as prev.
443
@param flow computed flow image that has the same size as prev and type CV_32FC2.
445
CV_WRAP virtual void calc( InputArray I0, InputArray I1, InputOutputArray flow ) = 0;
446
/** @brief Releases all inner buffers.
448
CV_WRAP virtual void collectGarbage() = 0;
451
/** @brief Base interface for sparse optical flow algorithms.
453
class CV_EXPORTS_W SparseOpticalFlow : public Algorithm
456
/** @brief Calculates a sparse optical flow.
458
@param prevImg First input image.
459
@param nextImg Second input image of the same size and the same type as prevImg.
460
@param prevPts Vector of 2D points for which the flow needs to be found.
461
@param nextPts Output vector of 2D points containing the calculated new positions of input features in the second image.
462
@param status Output status vector. Each element of the vector is set to 1 if the
463
flow for the corresponding features has been found. Otherwise, it is set to 0.
464
@param err Optional output vector that contains error response for each point (inverse confidence).
466
CV_WRAP virtual void calc(InputArray prevImg, InputArray nextImg,
467
InputArray prevPts, InputOutputArray nextPts,
469
OutputArray err = cv::noArray()) = 0;
473
/** @brief Class computing a dense optical flow using the Gunnar Farneback's algorithm.
475
class CV_EXPORTS_W FarnebackOpticalFlow : public DenseOpticalFlow
478
CV_WRAP virtual int getNumLevels() const = 0;
479
CV_WRAP virtual void setNumLevels(int numLevels) = 0;
481
CV_WRAP virtual double getPyrScale() const = 0;
482
CV_WRAP virtual void setPyrScale(double pyrScale) = 0;
484
CV_WRAP virtual bool getFastPyramids() const = 0;
485
CV_WRAP virtual void setFastPyramids(bool fastPyramids) = 0;
487
CV_WRAP virtual int getWinSize() const = 0;
488
CV_WRAP virtual void setWinSize(int winSize) = 0;
490
CV_WRAP virtual int getNumIters() const = 0;
491
CV_WRAP virtual void setNumIters(int numIters) = 0;
493
CV_WRAP virtual int getPolyN() const = 0;
494
CV_WRAP virtual void setPolyN(int polyN) = 0;
496
CV_WRAP virtual double getPolySigma() const = 0;
497
CV_WRAP virtual void setPolySigma(double polySigma) = 0;
499
CV_WRAP virtual int getFlags() const = 0;
500
CV_WRAP virtual void setFlags(int flags) = 0;
502
CV_WRAP static Ptr<FarnebackOpticalFlow> create(
504
double pyrScale = 0.5,
505
bool fastPyramids = false,
509
double polySigma = 1.1,
513
/** @brief Variational optical flow refinement
515
This class implements variational refinement of the input flow field, i.e.
516
it uses input flow to initialize the minimization of the following functional:
517
\f$E(U) = \int_{\Omega} \delta \Psi(E_I) + \gamma \Psi(E_G) + \alpha \Psi(E_S) \f$,
518
where \f$E_I,E_G,E_S\f$ are color constancy, gradient constancy and smoothness terms
519
respectively. \f$\Psi(s^2)=\sqrt{s^2+\epsilon^2}\f$ is a robust penalizer to limit the
520
influence of outliers. A complete formulation and a description of the minimization
521
procedure can be found in @cite Brox2004
523
class CV_EXPORTS_W VariationalRefinement : public DenseOpticalFlow
526
/** @brief @ref calc function overload to handle separate horizontal (u) and vertical (v) flow components
527
(to avoid extra splits/merges) */
528
CV_WRAP virtual void calcUV(InputArray I0, InputArray I1, InputOutputArray flow_u, InputOutputArray flow_v) = 0;
530
/** @brief Number of outer (fixed-point) iterations in the minimization procedure.
531
@see setFixedPointIterations */
532
CV_WRAP virtual int getFixedPointIterations() const = 0;
533
/** @copybrief getFixedPointIterations @see getFixedPointIterations */
534
CV_WRAP virtual void setFixedPointIterations(int val) = 0;
536
/** @brief Number of inner successive over-relaxation (SOR) iterations
537
in the minimization procedure to solve the respective linear system.
538
@see setSorIterations */
539
CV_WRAP virtual int getSorIterations() const = 0;
540
/** @copybrief getSorIterations @see getSorIterations */
541
CV_WRAP virtual void setSorIterations(int val) = 0;
543
/** @brief Relaxation factor in SOR
545
CV_WRAP virtual float getOmega() const = 0;
546
/** @copybrief getOmega @see getOmega */
547
CV_WRAP virtual void setOmega(float val) = 0;
549
/** @brief Weight of the smoothness term
551
CV_WRAP virtual float getAlpha() const = 0;
552
/** @copybrief getAlpha @see getAlpha */
553
CV_WRAP virtual void setAlpha(float val) = 0;
555
/** @brief Weight of the color constancy term
557
CV_WRAP virtual float getDelta() const = 0;
558
/** @copybrief getDelta @see getDelta */
559
CV_WRAP virtual void setDelta(float val) = 0;
561
/** @brief Weight of the gradient constancy term
563
CV_WRAP virtual float getGamma() const = 0;
564
/** @copybrief getGamma @see getGamma */
565
CV_WRAP virtual void setGamma(float val) = 0;
567
/** @brief Creates an instance of VariationalRefinement
569
CV_WRAP static Ptr<VariationalRefinement> create();
572
/** @brief DIS optical flow algorithm.
574
This class implements the Dense Inverse Search (DIS) optical flow algorithm. More
575
details about the algorithm can be found at @cite Kroeger2016 . Includes three presets with preselected
576
parameters to provide reasonable trade-off between speed and quality. However, even the slowest preset is
577
still relatively fast, use DeepFlow if you need better quality and don't care about speed.
579
This implementation includes several additional features compared to the algorithm described in the paper,
580
including spatial propagation of flow vectors (@ref getUseSpatialPropagation), as well as an option to
581
utilize an initial flow approximation passed to @ref calc (which is, essentially, temporal propagation,
582
if the previous frame's flow field is passed).
584
class CV_EXPORTS_W DISOpticalFlow : public DenseOpticalFlow
589
PRESET_ULTRAFAST = 0,
594
/** @brief Finest level of the Gaussian pyramid on which the flow is computed (zero level
595
corresponds to the original image resolution). The final flow is obtained by bilinear upscaling.
596
@see setFinestScale */
597
CV_WRAP virtual int getFinestScale() const = 0;
598
/** @copybrief getFinestScale @see getFinestScale */
599
CV_WRAP virtual void setFinestScale(int val) = 0;
601
/** @brief Size of an image patch for matching (in pixels). Normally, default 8x8 patches work well
602
enough in most cases.
604
CV_WRAP virtual int getPatchSize() const = 0;
605
/** @copybrief getPatchSize @see getPatchSize */
606
CV_WRAP virtual void setPatchSize(int val) = 0;
608
/** @brief Stride between neighbor patches. Must be less than patch size. Lower values correspond
609
to higher flow quality.
610
@see setPatchStride */
611
CV_WRAP virtual int getPatchStride() const = 0;
612
/** @copybrief getPatchStride @see getPatchStride */
613
CV_WRAP virtual void setPatchStride(int val) = 0;
615
/** @brief Maximum number of gradient descent iterations in the patch inverse search stage. Higher values
616
may improve quality in some cases.
617
@see setGradientDescentIterations */
618
CV_WRAP virtual int getGradientDescentIterations() const = 0;
619
/** @copybrief getGradientDescentIterations @see getGradientDescentIterations */
620
CV_WRAP virtual void setGradientDescentIterations(int val) = 0;
622
/** @brief Number of fixed point iterations of variational refinement per scale. Set to zero to
623
disable variational refinement completely. Higher values will typically result in more smooth and
625
@see setGradientDescentIterations */
626
CV_WRAP virtual int getVariationalRefinementIterations() const = 0;
627
/** @copybrief getGradientDescentIterations @see getGradientDescentIterations */
628
CV_WRAP virtual void setVariationalRefinementIterations(int val) = 0;
630
/** @brief Weight of the smoothness term
631
@see setVariationalRefinementAlpha */
632
CV_WRAP virtual float getVariationalRefinementAlpha() const = 0;
633
/** @copybrief getVariationalRefinementAlpha @see getVariationalRefinementAlpha */
634
CV_WRAP virtual void setVariationalRefinementAlpha(float val) = 0;
636
/** @brief Weight of the color constancy term
637
@see setVariationalRefinementDelta */
638
CV_WRAP virtual float getVariationalRefinementDelta() const = 0;
639
/** @copybrief getVariationalRefinementDelta @see getVariationalRefinementDelta */
640
CV_WRAP virtual void setVariationalRefinementDelta(float val) = 0;
642
/** @brief Weight of the gradient constancy term
643
@see setVariationalRefinementGamma */
644
CV_WRAP virtual float getVariationalRefinementGamma() const = 0;
645
/** @copybrief getVariationalRefinementGamma @see getVariationalRefinementGamma */
646
CV_WRAP virtual void setVariationalRefinementGamma(float val) = 0;
649
/** @brief Whether to use mean-normalization of patches when computing patch distance. It is turned on
650
by default as it typically provides a noticeable quality boost because of increased robustness to
651
illumination variations. Turn it off if you are certain that your sequence doesn't contain any changes
653
@see setUseMeanNormalization */
654
CV_WRAP virtual bool getUseMeanNormalization() const = 0;
655
/** @copybrief getUseMeanNormalization @see getUseMeanNormalization */
656
CV_WRAP virtual void setUseMeanNormalization(bool val) = 0;
658
/** @brief Whether to use spatial propagation of good optical flow vectors. This option is turned on by
659
default, as it tends to work better on average and can sometimes help recover from major errors
660
introduced by the coarse-to-fine scheme employed by the DIS optical flow algorithm. Turning this
661
option off can make the output flow field a bit smoother, however.
662
@see setUseSpatialPropagation */
663
CV_WRAP virtual bool getUseSpatialPropagation() const = 0;
664
/** @copybrief getUseSpatialPropagation @see getUseSpatialPropagation */
665
CV_WRAP virtual void setUseSpatialPropagation(bool val) = 0;
667
/** @brief Creates an instance of DISOpticalFlow
669
@param preset one of PRESET_ULTRAFAST, PRESET_FAST and PRESET_MEDIUM
671
CV_WRAP static Ptr<DISOpticalFlow> create(int preset = DISOpticalFlow::PRESET_FAST);
674
/** @brief Class used for calculating a sparse optical flow.
676
The class can calculate an optical flow for a sparse feature set using the
677
iterative Lucas-Kanade method with pyramids.
679
@sa calcOpticalFlowPyrLK
682
class CV_EXPORTS_W SparsePyrLKOpticalFlow : public SparseOpticalFlow
685
CV_WRAP virtual Size getWinSize() const = 0;
686
CV_WRAP virtual void setWinSize(Size winSize) = 0;
688
CV_WRAP virtual int getMaxLevel() const = 0;
689
CV_WRAP virtual void setMaxLevel(int maxLevel) = 0;
691
CV_WRAP virtual TermCriteria getTermCriteria() const = 0;
692
CV_WRAP virtual void setTermCriteria(TermCriteria& crit) = 0;
694
CV_WRAP virtual int getFlags() const = 0;
695
CV_WRAP virtual void setFlags(int flags) = 0;
697
CV_WRAP virtual double getMinEigThreshold() const = 0;
698
CV_WRAP virtual void setMinEigThreshold(double minEigThreshold) = 0;
700
CV_WRAP static Ptr<SparsePyrLKOpticalFlow> create(
701
Size winSize = Size(21, 21),
702
int maxLevel = 3, TermCriteria crit =
703
TermCriteria(TermCriteria::COUNT+TermCriteria::EPS, 30, 0.01),
705
double minEigThreshold = 1e-4);
added
removed
usr/include/opencv2/video/tracking.hpp
