OpenCV  3.3.1-dev
Open Source Computer Vision
Classes | Enumerations | Functions
Object Tracking

Classes

class  cv::DenseOpticalFlow
 
class  cv::DualTVL1OpticalFlow
 "Dual TV L1" Optical Flow Algorithm. More...
 
class  cv::FarnebackOpticalFlow
 Class computing a dense optical flow using the Gunnar Farneback's algorithm. More...
 
class  cv::KalmanFilter
 Kalman filter class. More...
 
class  cv::SparseOpticalFlow
 Base interface for sparse optical flow algorithms. More...
 
class  cv::SparsePyrLKOpticalFlow
 Class used for calculating a sparse optical flow. More...
 

Enumerations

enum  {
  cv::OPTFLOW_USE_INITIAL_FLOW = 4,
  cv::OPTFLOW_LK_GET_MIN_EIGENVALS = 8,
  cv::OPTFLOW_FARNEBACK_GAUSSIAN = 256
}
 
enum  {
  cv::MOTION_TRANSLATION = 0,
  cv::MOTION_EUCLIDEAN = 1,
  cv::MOTION_AFFINE = 2,
  cv::MOTION_HOMOGRAPHY = 3
}
 

Functions

int cv::buildOpticalFlowPyramid (InputArray img, OutputArrayOfArrays pyramid, Size winSize, int maxLevel, bool withDerivatives=true, int pyrBorder=BORDER_REFLECT_101, int derivBorder=BORDER_CONSTANT, bool tryReuseInputImage=true)
 Constructs the image pyramid which can be passed to calcOpticalFlowPyrLK. More...
 
void cv::calcOpticalFlowFarneback (InputArray prev, InputArray next, InputOutputArray flow, double pyr_scale, int levels, int winsize, int iterations, int poly_n, double poly_sigma, int flags)
 Computes a dense optical flow using the Gunnar Farneback's algorithm. More...
 
void cv::calcOpticalFlowPyrLK (InputArray prevImg, InputArray nextImg, InputArray prevPts, InputOutputArray nextPts, OutputArray status, OutputArray err, Size winSize=Size(21, 21), int maxLevel=3, TermCriteria criteria=TermCriteria(TermCriteria::COUNT+TermCriteria::EPS, 30, 0.01), int flags=0, double minEigThreshold=1e-4)
 Calculates an optical flow for a sparse feature set using the iterative Lucas-Kanade method with pyramids. More...
 
RotatedRect cv::CamShift (InputArray probImage, Rect &window, TermCriteria criteria)
 Finds an object center, size, and orientation. More...
 
Ptr< DualTVL1OpticalFlowcv::createOptFlow_DualTVL1 ()
 Creates instance of cv::DenseOpticalFlow. More...
 
Mat cv::estimateRigidTransform (InputArray src, InputArray dst, bool fullAffine)
 Computes an optimal affine transformation between two 2D point sets. More...
 
double cv::findTransformECC (InputArray templateImage, InputArray inputImage, InputOutputArray warpMatrix, int motionType=MOTION_AFFINE, TermCriteria criteria=TermCriteria(TermCriteria::COUNT+TermCriteria::EPS, 50, 0.001), InputArray inputMask=noArray())
 Finds the geometric transform (warp) between two images in terms of the ECC criterion [46] . More...
 
int cv::meanShift (InputArray probImage, Rect &window, TermCriteria criteria)
 Finds an object on a back projection image. More...
 

Detailed Description

Enumeration Type Documentation

§ anonymous enum

anonymous enum
Enumerator
OPTFLOW_USE_INITIAL_FLOW 
Python: cv.OPTFLOW_USE_INITIAL_FLOW
OPTFLOW_LK_GET_MIN_EIGENVALS 
Python: cv.OPTFLOW_LK_GET_MIN_EIGENVALS
OPTFLOW_FARNEBACK_GAUSSIAN 
Python: cv.OPTFLOW_FARNEBACK_GAUSSIAN

§ anonymous enum

anonymous enum
Enumerator
MOTION_TRANSLATION 
Python: cv.MOTION_TRANSLATION
MOTION_EUCLIDEAN 
Python: cv.MOTION_EUCLIDEAN
MOTION_AFFINE 
Python: cv.MOTION_AFFINE
MOTION_HOMOGRAPHY 
Python: cv.MOTION_HOMOGRAPHY

Function Documentation

§ buildOpticalFlowPyramid()

int cv::buildOpticalFlowPyramid ( InputArray  img,
OutputArrayOfArrays  pyramid,
Size  winSize,
int  maxLevel,
bool  withDerivatives = true,
int  pyrBorder = BORDER_REFLECT_101,
int  derivBorder = BORDER_CONSTANT,
bool  tryReuseInputImage = true 
)
Python:
retval, pyramid=cv.buildOpticalFlowPyramid(img, winSize, maxLevel[, pyramid[, withDerivatives[, pyrBorder[, derivBorder[, tryReuseInputImage]]]]])

Constructs the image pyramid which can be passed to calcOpticalFlowPyrLK.

Parameters
img8-bit input image.
pyramidoutput pyramid.
winSizewindow size of optical flow algorithm. Must be not less than winSize argument of calcOpticalFlowPyrLK. It is needed to calculate required padding for pyramid levels.
maxLevel0-based maximal pyramid level number.
withDerivativesset to precompute gradients for the every pyramid level. If pyramid is constructed without the gradients then calcOpticalFlowPyrLK will calculate them internally.
pyrBorderthe border mode for pyramid layers.
derivBorderthe border mode for gradients.
tryReuseInputImageput ROI of input image into the pyramid if possible. You can pass false to force data copying.
Returns
number of levels in constructed pyramid. Can be less than maxLevel.

§ calcOpticalFlowFarneback()

void cv::calcOpticalFlowFarneback ( InputArray  prev,
InputArray  next,
InputOutputArray  flow,
double  pyr_scale,
int  levels,
int  winsize,
int  iterations,
int  poly_n,
double  poly_sigma,
int  flags 
)
Python:
flow=cv.calcOpticalFlowFarneback(prev, next, flow, pyr_scale, levels, winsize, iterations, poly_n, poly_sigma, flags)

Computes a dense optical flow using the Gunnar Farneback's algorithm.

Parameters
prevfirst 8-bit single-channel input image.
nextsecond input image of the same size and the same type as prev.
flowcomputed flow image that has the same size as prev and type CV_32FC2.
pyr_scaleparameter, specifying the image scale (<1) to build pyramids for each image; pyr_scale=0.5 means a classical pyramid, where each next layer is twice smaller than the previous one.
levelsnumber of pyramid layers including the initial image; levels=1 means that no extra layers are created and only the original images are used.
winsizeaveraging window size; larger values increase the algorithm robustness to image noise and give more chances for fast motion detection, but yield more blurred motion field.
iterationsnumber of iterations the algorithm does at each pyramid level.
poly_nsize of the pixel neighborhood used to find polynomial expansion in each pixel; larger values mean that the image will be approximated with smoother surfaces, yielding more robust algorithm and more blurred motion field, typically poly_n =5 or 7.
poly_sigmastandard deviation of the Gaussian that is used to smooth derivatives used as a basis for the polynomial expansion; for poly_n=5, you can set poly_sigma=1.1, for poly_n=7, a good value would be poly_sigma=1.5.
flagsoperation flags that can be a combination of the following:
  • OPTFLOW_USE_INITIAL_FLOW uses the input flow as an initial flow approximation.
  • OPTFLOW_FARNEBACK_GAUSSIAN uses the Gaussian \(\texttt{winsize}\times\texttt{winsize}\) filter instead of a box filter of the same size for optical flow estimation; usually, this option gives z more accurate flow than with a box filter, at the cost of lower speed; normally, winsize for a Gaussian window should be set to a larger value to achieve the same level of robustness.

The function finds an optical flow for each prev pixel using the [48] algorithm so that

\[\texttt{prev} (y,x) \sim \texttt{next} ( y + \texttt{flow} (y,x)[1], x + \texttt{flow} (y,x)[0])\]

Note
  • An example using the optical flow algorithm described by Gunnar Farneback can be found at opencv_source_code/samples/cpp/fback.cpp
  • (Python) An example using the optical flow algorithm described by Gunnar Farneback can be found at opencv_source_code/samples/python/opt_flow.py

§ calcOpticalFlowPyrLK()

void cv::calcOpticalFlowPyrLK ( InputArray  prevImg,
InputArray  nextImg,
InputArray  prevPts,
InputOutputArray  nextPts,
OutputArray  status,
OutputArray  err,
Size  winSize = Size(21, 21),
int  maxLevel = 3,
TermCriteria  criteria = TermCriteria(TermCriteria::COUNT+TermCriteria::EPS, 30, 0.01),
int  flags = 0,
double  minEigThreshold = 1e-4 
)
Python:
nextPts, status, err=cv.calcOpticalFlowPyrLK(prevImg, nextImg, prevPts, nextPts[, status[, err[, winSize[, maxLevel[, criteria[, flags[, minEigThreshold]]]]]]])

Calculates an optical flow for a sparse feature set using the iterative Lucas-Kanade method with pyramids.

Parameters
prevImgfirst 8-bit input image or pyramid constructed by buildOpticalFlowPyramid.
nextImgsecond input image or pyramid of the same size and the same type as prevImg.
prevPtsvector of 2D points for which the flow needs to be found; point coordinates must be single-precision floating-point numbers.
nextPtsoutput vector of 2D points (with single-precision floating-point coordinates) containing the calculated new positions of input features in the second image; when OPTFLOW_USE_INITIAL_FLOW flag is passed, the vector must have the same size as in the input.
statusoutput status vector (of unsigned chars); each element of the vector is set to 1 if the flow for the corresponding features has been found, otherwise, it is set to 0.
erroutput vector of errors; each element of the vector is set to an error for the corresponding feature, type of the error measure can be set in flags parameter; if the flow wasn't found then the error is not defined (use the status parameter to find such cases).
winSizesize of the search window at each pyramid level.
maxLevel0-based maximal pyramid level number; if set to 0, pyramids are not used (single level), if set to 1, two levels are used, and so on; if pyramids are passed to input then algorithm will use as many levels as pyramids have but no more than maxLevel.
criteriaparameter, specifying the termination criteria of the iterative search algorithm (after the specified maximum number of iterations criteria.maxCount or when the search window moves by less than criteria.epsilon.
flagsoperation flags:
  • OPTFLOW_USE_INITIAL_FLOW uses initial estimations, stored in nextPts; if the flag is not set, then prevPts is copied to nextPts and is considered the initial estimate.
  • OPTFLOW_LK_GET_MIN_EIGENVALS use minimum eigen values as an error measure (see minEigThreshold description); if the flag is not set, then L1 distance between patches around the original and a moved point, divided by number of pixels in a window, is used as a error measure.
minEigThresholdthe algorithm calculates the minimum eigen value of a 2x2 normal matrix of optical flow equations (this matrix is called a spatial gradient matrix in [18]), divided by number of pixels in a window; if this value is less than minEigThreshold, then a corresponding feature is filtered out and its flow is not processed, so it allows to remove bad points and get a performance boost.

The function implements a sparse iterative version of the Lucas-Kanade optical flow in pyramids. See [18] . The function is parallelized with the TBB library.

Note
  • An example using the Lucas-Kanade optical flow algorithm can be found at opencv_source_code/samples/cpp/lkdemo.cpp
  • (Python) An example using the Lucas-Kanade optical flow algorithm can be found at opencv_source_code/samples/python/lk_track.py
  • (Python) An example using the Lucas-Kanade tracker for homography matching can be found at opencv_source_code/samples/python/lk_homography.py
Examples:
lkdemo.cpp.

§ CamShift()

RotatedRect cv::CamShift ( InputArray  probImage,
Rect window,
TermCriteria  criteria 
)
Python:
retval, window=cv.CamShift(probImage, window, criteria)

Finds an object center, size, and orientation.

Parameters
probImageBack projection of the object histogram. See calcBackProject.
windowInitial search window.
criteriaStop criteria for the underlying meanShift. returns (in old interfaces) Number of iterations CAMSHIFT took to converge The function implements the CAMSHIFT object tracking algorithm [21] . First, it finds an object center using meanShift and then adjusts the window size and finds the optimal rotation. The function returns the rotated rectangle structure that includes the object position, size, and orientation. The next position of the search window can be obtained with RotatedRect::boundingRect()

See the OpenCV sample camshiftdemo.c that tracks colored objects.

Note
  • (Python) A sample explaining the camshift tracking algorithm can be found at opencv_source_code/samples/python/camshift.py
Examples:
camshiftdemo.cpp.

§ createOptFlow_DualTVL1()

Ptr<DualTVL1OpticalFlow> cv::createOptFlow_DualTVL1 ( )
Python:
retval=cv.createOptFlow_DualTVL1()

Creates instance of cv::DenseOpticalFlow.

§ estimateRigidTransform()

Mat cv::estimateRigidTransform ( InputArray  src,
InputArray  dst,
bool  fullAffine 
)
Python:
retval=cv.estimateRigidTransform(src, dst, fullAffine)

Computes an optimal affine transformation between two 2D point sets.

Parameters
srcFirst input 2D point set stored in std::vector or Mat, or an image stored in Mat.
dstSecond input 2D point set of the same size and the same type as A, or another image.
fullAffineIf true, the function finds an optimal affine transformation with no additional restrictions (6 degrees of freedom). Otherwise, the class of transformations to choose from is limited to combinations of translation, rotation, and uniform scaling (4 degrees of freedom).

The function finds an optimal affine transform [A|b] (a 2 x 3 floating-point matrix) that approximates best the affine transformation between:

Two point sets
Two raster images. In this case, the function first finds some features in the src image and
finds the corresponding features in dst image. After that, the problem is reduced to the first
case.

In case of point sets, the problem is formulated as follows: you need to find a 2x2 matrix A and 2x1 vector b so that:

\[[A^*|b^*] = arg \min _{[A|b]} \sum _i \| \texttt{dst}[i] - A { \texttt{src}[i]}^T - b \| ^2\]

where src[i] and dst[i] are the i-th points in src and dst, respectively \([A|b]\) can be either arbitrary (when fullAffine=true ) or have a form of

\[\begin{bmatrix} a_{11} & a_{12} & b_1 \\ -a_{12} & a_{11} & b_2 \end{bmatrix}\]

when fullAffine=false.

See also
estimateAffine2D, estimateAffinePartial2D, getAffineTransform, getPerspectiveTransform, findHomography

§ findTransformECC()

double cv::findTransformECC ( InputArray  templateImage,
InputArray  inputImage,
InputOutputArray  warpMatrix,
int  motionType = MOTION_AFFINE,
TermCriteria  criteria = TermCriteria(TermCriteria::COUNT+TermCriteria::EPS, 50, 0.001),
InputArray  inputMask = noArray() 
)
Python:
retval, warpMatrix=cv.findTransformECC(templateImage, inputImage, warpMatrix[, motionType[, criteria[, inputMask]]])

Finds the geometric transform (warp) between two images in terms of the ECC criterion [46] .

Parameters
templateImagesingle-channel template image; CV_8U or CV_32F array.
inputImagesingle-channel input image which should be warped with the final warpMatrix in order to provide an image similar to templateImage, same type as temlateImage.
warpMatrixfloating-point \(2\times 3\) or \(3\times 3\) mapping matrix (warp).
motionTypeparameter, specifying the type of motion:
  • MOTION_TRANSLATION sets a translational motion model; warpMatrix is \(2\times 3\) with the first \(2\times 2\) part being the unity matrix and the rest two parameters being estimated.
  • MOTION_EUCLIDEAN sets a Euclidean (rigid) transformation as motion model; three parameters are estimated; warpMatrix is \(2\times 3\).
  • MOTION_AFFINE sets an affine motion model (DEFAULT); six parameters are estimated; warpMatrix is \(2\times 3\).
  • MOTION_HOMOGRAPHY sets a homography as a motion model; eight parameters are estimated;`warpMatrix` is \(3\times 3\).
criteriaparameter, specifying the termination criteria of the ECC algorithm; criteria.epsilon defines the threshold of the increment in the correlation coefficient between two iterations (a negative criteria.epsilon makes criteria.maxcount the only termination criterion). Default values are shown in the declaration above.
inputMaskAn optional mask to indicate valid values of inputImage.

The function estimates the optimum transformation (warpMatrix) with respect to ECC criterion ([46]), that is

\[\texttt{warpMatrix} = \texttt{warpMatrix} = \arg\max_{W} \texttt{ECC}(\texttt{templateImage}(x,y),\texttt{inputImage}(x',y'))\]

where

\[\begin{bmatrix} x' \\ y' \end{bmatrix} = W \cdot \begin{bmatrix} x \\ y \\ 1 \end{bmatrix}\]

(the equation holds with homogeneous coordinates for homography). It returns the final enhanced correlation coefficient, that is the correlation coefficient between the template image and the final warped input image. When a \(3\times 3\) matrix is given with motionType =0, 1 or 2, the third row is ignored.

Unlike findHomography and estimateRigidTransform, the function findTransformECC implements an area-based alignment that builds on intensity similarities. In essence, the function updates the initial transformation that roughly aligns the images. If this information is missing, the identity warp (unity matrix) is used as an initialization. Note that if images undergo strong displacements/rotations, an initial transformation that roughly aligns the images is necessary (e.g., a simple euclidean/similarity transform that allows for the images showing the same image content approximately). Use inverse warping in the second image to take an image close to the first one, i.e. use the flag WARP_INVERSE_MAP with warpAffine or warpPerspective. See also the OpenCV sample image_alignment.cpp that demonstrates the use of the function. Note that the function throws an exception if algorithm does not converges.

See also
estimateAffine2D, estimateAffinePartial2D, findHomography
Examples:
image_alignment.cpp.

§ meanShift()

int cv::meanShift ( InputArray  probImage,
Rect window,
TermCriteria  criteria 
)
Python:
retval, window=cv.meanShift(probImage, window, criteria)

Finds an object on a back projection image.

Parameters
probImageBack projection of the object histogram. See calcBackProject for details.
windowInitial search window.
criteriaStop criteria for the iterative search algorithm. returns : Number of iterations CAMSHIFT took to converge. The function implements the iterative object search algorithm. It takes the input back projection of an object and the initial position. The mass center in window of the back projection image is computed and the search window center shifts to the mass center. The procedure is repeated until the specified number of iterations criteria.maxCount is done or until the window center shifts by less than criteria.epsilon. The algorithm is used inside CamShift and, unlike CamShift , the search window size or orientation do not change during the search. You can simply pass the output of calcBackProject to this function. But better results can be obtained if you pre-filter the back projection and remove the noise. For example, you can do this by retrieving connected components with findContours , throwing away contours with small area ( contourArea ), and rendering the remaining contours with drawContours.