Generate 4-character code of codec used to compress the frames. For example, CV_FOURCC('P','I','M','1') is MPEG-1 codec, CV_FOURCC('M','J','P','G') is motion-jpeg codec etc.

Determined whether the specified node is occupied or not

This function performs the same as CV_MAKETYPE macro

Move to the next element in the sequence

forward reading the sequence reader

Calculates rotation matrix

Calculates absolute difference between two arrays. dst(I)c = abs(src1(I)c - src2(I)c). All the arrays must have the same data type and the same size (or ROI size)

Calculates absolute difference between array and scalar

Adds the whole image or its selected region to accumulator sum

Transforms grayscale image to binary image. Threshold calculated individually for each pixel. For the method CV_ADAPTIVE_THRESH_MEAN_C it is a mean of blockSize x blockSize pixel neighborhood, subtracted by param1. For the method CV_ADAPTIVE_THRESH_GAUSSIAN_C it is a weighted sum (gaussian) of blockSize x blockSize pixel neighborhood, subtracted by param1.

Adds one array to another one: dst(I)=src1(I)+src2(I) if mask(I)!=0All the arrays must have the same type, except the mask, and the same size (or ROI size)

Adds scalar value to every element in the source array src1 and stores the result in dst dst(I)=src(I)+value if mask(I)!=0 All the arrays must have the same type, except the mask, and the same size (or ROI size)

Calculated weighted sum of two arrays as following: dst(I)=src1(I)*alpha+src2(I)*beta+gamma All the arrays must have the same type and the same size (or ROI size)

Calculates per-element bit-wise logical conjunction of two arrays: dst(I)=src1(I) & src2(I) if mask(I)!=0 In the case of floating-point arrays their bit representations are used for the operation. All the arrays must have the same type, except the mask, and the same size

Calculates per-element bit-wise conjunction of array and scalar: dst(I)=src(I)&value if mask(I)!=0 Prior to the actual operation the scalar is converted to the same type as the arrays. In the case of floating-point arrays their bit representations are used for the operation. All the arrays must have the same type, except the mask, and the same size

Approximates one or more curves and returns the approximation result[s]. In case of multiple curves approximation the resultant tree will have the same structure as the input one (1:1 correspondence).

Calculates length or curve as sum of lengths of segments between subsequent points

Calculates the average value M of array elements, independently for each channel: N = sumI mask(I)!=0 Mc = 1/N * sumI,mask(I)!=0 arr(I)c If the array is IplImage and COI is set, the function processes the selected channel only and stores the average to the first scalar component (S0).

The function cvAvgSdv calculates the average value and standard deviation of array elements, independently for each channel

Update the BG code book model

Detect new blobs.

Release the blob detector

Create a BlobSeq

Get the specific blob from the blob sequence

Get the specific blob from the blob sequence

Get the number of blob in the blob sequence

Release the blob sequence

Add new blob to track it and assign to this blob personal ID

Get the blob of specific index from the auto blob tracker

Get the blob of specific id from the auto blob tracker

Get the number of blobs in the auto blob tracker

Get the forground mask

Process a image frame

Release the blob tracker auto

Delete blob by its index

Return pointer to specified by index blob

Return pointer to specified by index blob

Return number of currently tracked blobs

Release the blob tracker

Release the blob tracking post process module

Calculates the back project of the histogram. For each tuple of pixels at the same position of all input single-channel images the function puts the value of the histogram bin, corresponding to the tuple, to the destination image. In terms of statistics, the value of each output image pixel is probability of the observed tuple given the distribution (histogram).

Calculates the back project of the histogram. For each tuple of pixels at the same position of all input single-channel images the function puts the value of the histogram bin, corresponding to the tuple, to the destination image. In terms of statistics, the value of each output image pixel is probability of the observed tuple given the distribution (histogram).

Compares histogram, computed over each possible rectangular patch of the specified size in the input images, and stores the results to the output map dst.

Calculates the covariation matrix and, optionally, mean vector of the set of input vectors.

Calculates orthonormal eigen basis and the averaged object for a group of the input objects.

Computes earth mover distance and/or a lower boundary of the distance between the two weighted point configurations. One of the application desctibed in [RubnerSept98] is multi-dimensional histogram comparison for image retrieval. EMD is a transportation problem that is solved using some modification of simplex algorithm, thus the complexity is exponential in the worst case, though, it is much faster in average. In case of a real metric the lower boundary can be calculated even faster (using linear-time algorithm) and it can be used to determine roughly whether the two signatures are far enough so that they cannot relate to the same object.

Calculates the general motion direction in the selected region and returns the angle between 0 and 360. At first the function builds the orientation histogram and finds the basic orientation as a coordinate of the histogram maximum. After that the function calculates the shift relative to the basic orientation as a weighted sum of all orientation vectors: the more recent is the motion, the greater is the weight. The resultant angle is a circular sum of the basic orientation and the shift.

Calculates the histogram of one or more single-channel images. The elements of a tuple that is used to increment a histogram bin are taken at the same location from the corresponding input images.

Calculates the derivatives Dx and Dy of mhi and then calculates gradient orientation as: orientation(x,y)=arctan(Dy(x,y)/Dx(x,y)) where both Dx(x,y)' and Dy(x,y)' signs are taken into account (as in cvCartToPolar function). After that mask is filled to indicate where the orientation is valid (see delta1 and delta2 description).

Calculates optical flow for overlapped blocks block_size.width * block_size.height pixels each, thus the velocity fields are smaller than the original images. For every block in prev the functions tries to find a similar block in curr in some neighborhood of the original block or shifted by (velx(x0,y0),vely(x0,y0)) block as has been calculated by previous function call (if use_previous=1)

Computes dense optical flow using Gunnar Farneback’s algorithm

Computes flow for every pixel of the first input image using Horn & Schunck algorithm

Computes flow for every pixel of the first input image using Lucas & Kanade algorithm

Performs PCA analysis of the vector set. First, it uses cvCalcCovarMatrix to compute covariation matrix and then it finds its eigenvalues and eigenvectors. The output number of eigenvalues/eigenvectors should be less than or equal to MIN(rows(data),cols(data)).

Calculates 2D pair-wise geometrical histogram (PGH), described in [Iivarinen97], for the contour. The algorithm considers every pair of the contour edges. The angle between the edges and the minimum/maximum distances are determined for every pair. To do this each of the edges in turn is taken as the base, while the function loops through all the other edges. When the base edge and any other edge are considered, the minimum and maximum distances from the points on the non-base edge and line of the base edge are selected. The angle between the edges defines the row of the histogram in which all the bins that correspond to the distance between the calculated minimum and maximum distances are incremented (that is, the histogram is transposed relatively to [Iivarninen97] definition). The histogram can be used for contour matching

calculates the object probability density from the two histograms as: dist_hist(I)=0, if hist1(I)==0; dist_hist(I)=scale, if hist1(I)!=0 && hist2(I)>hist1(I); dist_hist(I)=hist2(I)*scale/hist1(I), if hist1(I)!=0 && hist2(I)<=hist1(I)

Calculates coordinates of virtual points. All virtual points corresponding to some vertex of original subdivision form (when connected together) a boundary of Voronoi cell of that point

Estimates intrinsic camera parameters and extrinsic parameters for each of the views

Computes various useful camera (sensor/lens) characteristics using the computed camera calibration matrix, image frame resolution in pixels and the physical aperture size

Implements CAMSHIFT object tracking algrorithm ([Bradski98]). First, it finds an object center using cvMeanShift and, after that, calculates the object size and orientation.

Finds the edges on the input image image and marks them in the output image edges using the Canny algorithm. The smallest of threshold1 and threshold2 is used for edge linking, the largest - to find initial segments of strong edges.

Checks that every array element is neither NaN nor Infinity. If CV_CHECK_RANGE is set, it also checks that every element is greater than or equal to minVal and less than maxVal.

Tests whether the input contour is convex or not. The contour must be simple, i.e. without self-intersections.

Draws a simple or filled circle with given center and radius. The circle is clipped by ROI rectangle.

Sets all histogram bins to 0 in case of dense histogram and removes all histogram bins in case of sparse array

Resets the top (free space boundary) of the storage to the very beginning. This function does not deallocate any memory. If the storage has a parent, the function returns all blocks to the parent.

clears (sets to zero) the particular element of dense array or deletes the element of sparse array. If the element does not exists, the function does nothing

Removes all elements from the sequence. The function does not return the memory to the storage, but this memory is reused later when new elements are added to the sequence. This function time complexity is O(1).

Calculates a part of the line segment which is entirely in the image. It returns 0 if the line segment is completely outside the image and 1 otherwise.

Compares the corresponding elements of two arrays and fills the destination mask array: dst(I)=src1(I) op src2(I), dst(I) is set to 0xff (all '1'-bits) if the particular relation between the elements is true and 0 otherwise. All the arrays must have the same type, except the destination, and the same size (or ROI size)

Compares the corresponding elements of array and scalar and fills the destination mask array: dst(I)=src(I) op scalar, where op is '=', '>', '>=', '<', '<=' or '!='. dst(I) is set to 0xff (all '1'-bits) if the particular relation between the elements is true and 0 otherwise. All the arrays must have the same size (or ROI size)

Compares two dense histograms

For every point in one of the two images of stereo-pair the function cvComputeCorrespondEpilines finds equation of a line that contains the corresponding point (i.e. projection of the same 3D point) in the other image. Each line is encoded by a vector of 3 elements l=[a,b,c]^T, so that: l^T*[x, y, 1]^T=0, or a*x + b*y + c = 0 From the fundamental matrix definition (see cvFindFundamentalMatrix discussion), line l2 for a point p1 in the first image (which_image=1) can be computed as: l2=F*p1 and the line l1 for a point p2 in the second image (which_image=1) can be computed as: l1=F^T*p2Line coefficients are defined up to a scale. They are normalized (a2+b2=1) are stored into correspondent_lines

Fills the samples arrays in the structure CvConDensation with values within specified ranges.

Estimates the subsequent stochastic model state from its current state

Calculates area of the whole contour or contour section.

Return the contour from its binary tree representation

Find the perimeter of the contour

Same as cvConvertScale(src, dest, 1, 0);

Converts 2D or 3D points from/to homogenious coordinates, or simply copies or transposes the array. In case if the input array dimensionality is larger than the output, each point coordinates are divided by the last coordinate

This function has several different purposes and thus has several synonyms. It copies one array to another with optional scaling, which is performed first, and/or optional type conversion, performed after: dst(I)=src(I)*scale + (shift,shift,...) All the channels of multi-channel arrays are processed independently. The type conversion is done with rounding and saturation, that is if a result of scaling + conversion can not be represented exactly by a value of destination array element type, it is set to the nearest representable value on the real axis. In case of scale=1, shift=0 no prescaling is done. This is a specially optimized case and it has the appropriate cvConvert synonym. If source and destination array types have equal types, this is also a special case that can be used to scale and shift a matrix or an image and that fits to cvScale synonym.

Similar to cvCvtScale but it stores absolute values of the conversion results: dst(I)=abs(src(I)*scale + (shift,shift,...)) The function supports only destination arrays of 8u (8-bit unsigned integers) type, for other types the function can be emulated by combination of cvConvertScale and cvAbs functions.

The function cvConvexHull2 finds convex hull of 2D point set using Sklansky's algorithm.

Finds all convexity defects of the input contour and returns a sequence of the CvConvexityDefect structures.

Copies selected elements from input array to output array: dst(I)=src(I) if mask(I)!=0. If any of the passed arrays is of IplImage type, then its ROI and COI fields are used. Both arrays must have the same type, the same number of dimensions and the same size. The function can also copy sparse arrays (mask is not supported in this case).

Makes a copy of the histogram. If the second histogram pointer *dst is NULL, a new histogram of the same size as src is created. Otherwise, both histograms must have equal types and sizes. Then the function copies the source histogram bins values to destination histogram and sets the same bin values ranges as in src.

Copies the source 2D array into interior of destination array and makes a border of the specified type around the copied area. The function is useful when one needs to emulate border type that is different from the one embedded into a specific algorithm implementation. For example, morphological functions, as well as most of other filtering functions in OpenCV, internally use replication border type, while the user may need zero border or a border, filled with 1's or 255's

Runs the Harris edge detector on image. Similarly to cvCornerMinEigenVal and cvCornerEigenValsAndVecs, for each pixel it calculates 2x2 gradient covariation matrix M over block_size x block_size neighborhood. Then, it stores det(M) - k*trace(M)^2 to the destination image. Corners in the image can be found as local maxima of the destination image.

Returns the number of non-zero elements in arr: result = sumI arr(I)!=0 In case of IplImage both ROI and COI are supported.

Create a BG code book model

Get a CC blob detector

Get a simple blob detector

Create blob tracker auto ver1

Simple blob tracker based on connected component tracking

Connected component tracking and mean-shift particle filter collion-resolver

Meanshift without connected-components

Blob tracker that integrates meanshift and connected components

Blob tracker that integrates meanshift and connected components:

Particle filtering via Bhattacharya coefficient, which is roughly the dot-product of two probability densities.

Allocates and initialized the CvCapture structure for reading a video stream from the camera. Currently two camera interfaces can be used on Windows: Video for Windows (VFW) and Matrox Imaging Library (MIL); and two on Linux: V4L and FireWire (IEEE1394).

Creates a child memory storage that is similar to simple memory storage except for the differences in the memory allocation/deallocation mechanism. When a child storage needs a new block to add to the block list, it tries to get this block from the parent. The first unoccupied parent block available is taken and excluded from the parent block list. If no blocks are available, the parent either allocates a block or borrows one from its own parent, if any. In other words, the chain, or a more complex structure, of memory storages where every storage is a child/parent of another is possible. When a child storage is released or even cleared, it returns all blocks to the parent. In other aspects, the child storage is the same as the simple storage.

Creates CvConDensation structure and returns pointer to the structure

Creates binary tree representation for the input contour and returns the pointer to its root.

Allocates and initialized the CvCapture structure for reading the video stream from the specified file. After the allocated structure is not used any more it should be released by cvReleaseCapture function.

Create a Gaussian background model

Creates the header and allocates data.

Allocates, initializes, and returns the structure IplImage.

Allocates CvKalman and all its matrices and initializes them somehow.

Constructs a balanced kd-tree index of the given feature vectors. The lifetime of the desc matrix must exceed that of the returned tree. I.e., no copy is made of the vectors.

Allocates header for the new matrix and underlying data, and returns a pointer to the created matrix. Matrices are stored row by row. All the rows are aligned by 4 bytes.

Creates a memory storage and returns pointer to it. Initially the storage is empty. All fields of the header, except the block_size, are set to 0.

Returns a Kalman blob tracking post process module

Returns a TimeAverExp blob tracking post process module

Returns a TimeAverRect blob tracking post process module

Allocates memory for the object structure and computes the object inverse matrix.

Creates a sequence and returns the pointer to it. The function allocates the sequence header in the storage block as one continuous chunk and sets the structure fields flags, elem_size, header_size and storage to passed values, sets delta_elems to the default value (that may be reassigned using cvSetSeqBlockSize function), and clears other header fields, including the space after the first sizeof(CvSeq) bytes

Constructs a spill tree index of the given feature vectors. The lifetime of the desc matrix must exceed that of the returned tree. I.e., no copy is made of the vectors.

Creates the stereo correspondence structure and initializes it. It is possible to override any of the parameters at any time between the calls to cvFindStereoCorrespondenceBM

Creates the stereo correspondence structure and initializes it.

Creates new subdivision

Creates an empty Delaunay subdivision, where 2d points can be added further using function cvSubdivDelaunay2DInsert. All the points to be added must be within the specified rectangle, otherwise a runtime error will be raised.

Calculates the cross product of two 3D vectors

Converts input image from one color space to another. The function ignores colorModel and channelSeq fields of IplImage header, so the source image color space should be specified correctly (including order of the channels in case of RGB space, e.g. BGR means 24-bit format with B0 G0 R0 B1 G1 R1 ... layout, whereas RGB means 24-bit format with R0 G0 B0 R1 G1 B1 ... layout).

This function is the opposite to cvSplit. If the destination array has N channels then if the first N input channels are not IntPtr.Zero, all they are copied to the destination array, otherwise if only a single source channel of the first N is not IntPtr.Zero, this particular channel is copied into the destination array, otherwise an error is raised. Rest of source channels (beyond the first N) must always be IntPtr.Zero. For IplImage cvCopy with COI set can be also used to insert a single channel into the image.

This function has several different purposes and thus has several synonyms. It copies one array to another with optional scaling, which is performed first, and/or optional type conversion, performed after: dst(I)=src(I)*scale + (shift,shift,...) All the channels of multi-channel arrays are processed independently. The type conversion is done with rounding and saturation, that is if a result of scaling + conversion can not be represented exactly by a value of destination array element type, it is set to the nearest representable value on the real axis. In case of scale=1, shift=0 no prescaling is done. This is a specially optimized case and it has the appropriate cvConvert synonym. If source and destination array types have equal types, this is also a special case that can be used to scale and shift a matrix or an image and that fits to cvScale synonym.

Copies the entire sequence or subsequence to the specified buffer and returns the pointer to the buffer

Performs forward or inverse transform of 1D or 2D floating-point array

Destroys the window with a given name

Returns determinant of the square matrix mat. The direct method is used for small matrices and Gaussian elimination is used for larger matrices. For symmetric positive-determined matrices it is also possible to run SVD with U=V=NULL and then calculate determinant as a product of the diagonal elements of W

Performs forward or inverse transform of 1D or 2D floating-point array In case of real (single-channel) data, the packed format, borrowed from IPL, is used to to represent a result of forward Fourier transform or input for inverse Fourier transform

Dilates the source image using the specified structuring element that determines the shape of a pixel neighborhood over which the maximum is taken The function supports the in-place mode. Dilation can be applied several (iterations) times. In case of color image each channel is processed independently

Calculates distance to closest zero pixel for all non-zero pixels of source image

Divides one array by another: dst(I)=scale * src1(I)/src2(I), if src1!=IntPtr.Zero; dst(I)=scale/src2(I), if src1==IntPtr.Zero; All the arrays must have the same type, and the same size (or ROI size)

Calculates and returns the Euclidean dot product of two arrays. src1 dot src2 = sumI(src1(I)*src2(I)) In case of multiple channel arrays the results for all channels are accumulated. In particular, cvDotProduct(a,a), where a is a complex vector, will return ||a||2. The function can process multi-dimensional arrays, row by row, layer by layer and so on.

Draws contour outlines in the image if thickness >=0 or fills area bounded by the contours if thickness<0.

Calculates all decomposition coefficients for the input object using the previously calculated eigen objects basis and the averaged object

Calculates an object projection to the eigen sub-space or, in other words, restores an object using previously calculated eigen objects basis, averaged object, and decomposition coefficients of the restored object.

Draws a simple or thick elliptic arc or fills an ellipse sector. The arc is clipped by ROI rectangle. A piecewise-linear approximation is used for antialiased arcs and thick arcs. All the angles are given in degrees.

Draws a simple or thick elliptic arc or fills an ellipse sector. The arc is clipped by ROI rectangle. A piecewise-linear approximation is used for antialiased arcs and thick arcs. All the angles are given in degrees.

The algorithm normalizes brightness and increases contrast of the image

Erodes the source image using the specified structuring element that determines the shape of a pixel neighborhood over which the minimum is taken: dst=erode(src,element): dst(x,y)=min((x',y') in element)) src(x+x',y+y') The function supports the in-place mode. Erosion can be applied several (iterations) times. In case of color image each channel is processed independently.

Returns the textual description for the specified error status code. In case of unknown status the function returns NULL pointer.

Calculates exponent of every element of input array: dst(I)=exp(src(I)) Maximum relative error is 7e-6. Currently, the function converts denormalized values to zeros on output

Extracts the contours of Maximally Stable Extremal Regions

Finds robust features in the image. For each feature it returns its location, size, orientation and optionally the descriptor, basic or extended. The function can be used for object tracking and localization, image stitching etc

Extract FAST keypoints

Get the forground mask from the forground detector

Update the FGDetector with new image

Release the forground detector

Fills convex polygon interior. This function is much faster than The function cvFillPoly and can fill not only the convex polygons but any monotonic polygon, i.e. a polygon whose contour intersects every horizontal line (scan line) twice at the most

Applies arbitrary linear filter to the image. In-place operation is supported. When the aperture is partially outside the image, the function interpolates outlier pixel values from the nearest pixels that is inside the image

Retrieves contours from the binary image and returns the number of retrieved contours. The pointer first_contour is filled by the function. It will contain pointer to the first most outer contour or IntPtr.Zero if no contours is detected (if the image is completely black). Other contours may be reached from first_contour using h_next and v_next links. The sample in cvDrawContours discussion shows how to use contours for connected component detection. Contours can be also used for shape analysis and object recognition - see squares.c in OpenCV sample directory

Estimates extrinsic camera parameters using known intrinsic parameters and and extrinsic parameters for each view. The coordinates of 3D object points and their correspondent 2D projections must be specified. This function also minimizes back-projection error

Searches feature tree for k nearest neighbors of given reference points.

Performs orthogonal range seaching on the given kd-tree. That is, it returns the set of vectors v in tr that satisfy bounds_min[i] <= v[i] <= bounds_max[i], 0 <= i < d, where d is the dimension of vectors in the tree. The function returns the number of such vectors found

Calculates fundamental matrix using one of four methods listed above and returns the number of fundamental matrices found (1 or 3) and 0, if no matrix is found.

Finds perspective transformation H=||hij|| between the source and the destination planes

Locates input point within subdivision. It finds subdivision vertex that is the closest to the input point. It is not necessarily one of vertices of the facet containing the input point, though the facet (located using cvSubdiv2DLocate) is used as a starting point.

Calculates disparity for stereo-pair

Calculates ellipse that fits best (in least-squares sense) to a set of 2D points. The meaning of the returned structure fields is similar to those in cvEllipse except that size stores the full lengths of the ellipse axises, not half-lengths

Fits line to 2D or 3D point set

Flips the array in one of different 3 ways (row and column indices are 0-based): dst(i,j)=src(rows(src)-i-1,j) if flip_mode = 0 dst(i,j)=src(i,cols(src1)-j-1) if flip_mode > 0 dst(i,j)=src(rows(src)-i-1,cols(src)-j-1) if flip_mode < 0

Performs generalized matrix multiplication: dst = alpha*op(src1)*op(src2) + beta*op(src3), where op(X) is X or XT

Return the particular array element

Return the particular array element

Return the particular array element

Retrieves the specified property of camera or video file

Retrieves the central moment, which in case of image moments is defined as: mu_{x_order,y_order}=sum_{x,y}(I(x,y)*(x-x_c)^{x_order} * (y-y_c)^{y_order}), where x_c=M10/M00, y_c=M01/M00 - coordinates of the gravity center

Return the header, corresponding to a specified column of the input array

Return the header, corresponding to a specified col span of the input array

returns the header, corresponding to a specified diagonal of the input array

Returns the current error mode

Returns the current error status - the value set with the last cvSetErrStatus call. Note, that in Leaf mode the program terminates immediately after error occured, so to always get control after the function call, one should call cvSetErrMode and set Parent or Silent error mode.

Finds a file node by name

Calculates seven Hu invariants

Returns image header for the input array that can be matrix - CvMat*, or image - IplImage*.

Returns channel of interest of the image (it returns 0 if all the channels are selected).

Returns channel of interest of the image (it returns 0 if all the channels are selected).

Returns matrix header for the input array that can be matrix - CvMat, image - IplImage or multi-dimensional dense array - CvMatND* (latter case is allowed only if allowND != 0) . In the case of matrix the function simply returns the input pointer. In the case of IplImage* or CvMatND* it initializes header structure with parameters of the current image ROI and returns pointer to this temporary structure. Because COI is not supported by CvMat, it is returned separately.

Finds the minimum and maximum histogram bins and their positions

Returns information about one of or all of the registered modules

Retrieves normalized central moment, which in case of image moments is defined as: eta_{x_order,y_order}=mu_{x_order,y_order} / M00^{(y_order+x_order)/2+1}, where mu_{x_order,y_order} is the central moment

Return the current number of threads that are used by parallelized (via OpenMP) OpenCV functions.

Returns the minimum number N that is greater to equal to size0, such that DFT of a vector of size N can be computed fast. In the current implementation N=2^p x 3^q x 5^r for some p, q, r.

Extracts pixels from src at sub-pixel accuracy and stores them to dst as follows: dst(x, y)= src( A_11 x'+A_12 y'+ b1, A_21 x'+A_22 y'+ b2), where A and b are taken from map_matrix: map_matrix = [ [A11 A12 b1], [ A21 A22 b2 ] ] x'=x-(width(dst)-1)*0.5, y'=y-(height(dst)-1)*0.5 where the values of pixels at non-integer coordinates A (x,y)^T + b are retrieved using bilinear interpolation. When the function needs pixels outside of the image, it uses replication border mode to reconstruct the values. Every channel of multiple-channel images is processed independently.

Fills output variables with low-level information about the array data. All output parameters are optional, so some of the pointers may be set to NULL. If the array is IplImage with ROI set, parameters of ROI are returned.

Return the particular element of single-channel array. If the array has multiple channels, runtime error is raised. Note that cvGet*D function can be used safely for both single-channel and multiple-channel arrays though they are a bit slower.

Return the particular element of single-channel array. If the array has multiple channels, runtime error is raised. Note that cvGet*D function can be used safely for both single-channel and multiple-channel arrays though they are a bit slower.

Return the particular element of single-channel array. If the array has multiple channels, runtime error is raised. Note that cvGet*D function can be used safely for both single-channel and multiple-channel arrays though they are a bit slower.

Extracts pixels from src: dst(x, y) = src(x + center.x - (width(dst)-1)*0.5, y + center.y - (height(dst)-1)*0.5) where the values of pixels at non-integer coordinates are retrieved using bilinear interpolation. Every channel of multiple-channel images is processed independently. Whereas the rectangle center must be inside the image, the whole rectangle may be partially occluded. In this case, the replication border mode is used to get pixel values beyond the image boundaries.

Return the header, corresponding to a specified row of the input array

Return the header, corresponding to a specified row span of the input array

Finds the element with the given index in the sequence and returns the pointer to it. If the element is not found, the function returns 0. The function supports negative indices, where -1 stands for the last sequence element, -2 stands for the one before last, etc. If the sequence is most likely to consist of a single sequence block or the desired element is likely to be located in the first block, then the macro CV_GET_SEQ_ELEM( elemType, seq, index ) should be used, where the parameter elemType is the type of sequence elements ( CvPoint for example), the parameter seq is a sequence, and the parameter index is the index of the desired element. The macro checks first whether the desired element belongs to the first block of the sequence and returns it if it does, otherwise the macro calls the main function GetSeqElem. Negative indices always cause the cvGetSeqElem call. The function has O(1) time complexity assuming that number of blocks is much smaller than the number of elements.

Returns number of rows (CvSize::height) and number of columns (CvSize::width) of the input matrix or image. In case of image the size of ROI is returned.

Retrieves the spatial moment, which in case of image moments is defined as: M_{x_order,y_order}=sum_{x,y}(I(x,y) * x^{x_order} * y^{y_order}) where I(x,y) is the intensity of the pixel (x, y).

Retrieve the star keypoint location from the specific image

Returns header, corresponding to a specified rectangle of the input array. In other words, it allows the user to treat a rectangular part of input array as a stand-alone array. ROI is taken into account by the function so the sub-array of ROI is actually extracted.

Calculates the binding rectangle for the given text string when a specified font is used

Returns the index, from 0 to cvGetNumThreads()-1, of the thread that called the function. It is a wrapper for the function omp_get_thread_num() from OpenMP runtime. The retrieved index may be used to access local-thread data inside the parallelized code fragments.

Finds corners with big eigenvalues in the image.

Finds rectangular regions in the given image that are likely to contain objects the cascade has been trained for and returns those regions as a sequence of rectangles. The function scans the image several times at different scales (see cvSetImagesForHaarClassifierCascade). Each time it considers overlapping regions in the image and applies the classifiers to the regions using cvRunHaarClassifierCascade. It may also apply some heuristics to reduce number of analyzed regions, such as Canny prunning. After it has proceeded and collected the candidate rectangles (regions that passed the classifier cascade), it groups them and returns a sequence of average rectangles for each large enough group. The default parameters (scale_factor=1.1, min_neighbors=3, flags=0) are tuned for accurate yet slow object detection. For a faster operation on real video images the settings are: scale_factor=1.2, min_neighbors=2, flags=CV_HAAR_DO_CANNY_PRUNING, min_size=<minimum possible face size> (for example, ~1/4 to 1/16 of the image area in case of video conferencing).

Finds circles in grayscale image using some modification of Hough transform

The function cvHoughLines2 implements a few variants of Hough transform for line detection

Initializes the font structure that can be passed to text rendering functions

Initializes the image header structure, pointer to which is passed by the user, and returns the pointer.

Initializes CvMatND structure allocated by the user

Initializes Delaunay triangulation

Pre-computes the undistortion map - coordinates of the corresponding pixel in the distorted image for every pixel in the corrected image. Then, the map (together with input and output images) can be passed to cvRemap function.

This function is an extended version of cvInitUndistortMap. That is, in addition to the correction of lens distortion, the function can also apply arbitrary perspective transformation R and finally it can scale and shift the image according to the new camera matrix

Reconstructs the selected image area from the pixel near the area boundary. The function may be used to remove dust and scratches from a scanned photo, or to remove undesirable objects from still images or video.

Performs range check for every element of the input array: dst(I)=lower(I)_0 <= src(I)_0 < upper(I)_0 For single-channel arrays, dst(I)=lower(I)_0 <= src(I)_0 < upper(I)_0 && lower(I)_1 <= src(I)_1 < upper(I)_1 For two-channel arrays etc. dst(I) is set to 0xff (all '1'-bits) if src(I) is within the range and 0 otherwise. All the arrays must have the same type, except the destination, and the same size (or ROI size)

Does the range check for every element of the input array: dst(I)=lower0 <= src(I)0 < upper0 for a single-channel array, dst(I)=lower0 <= src(I)0 < upper0 && lower1 <= src(I)1 < upper1 for a two-channel array etc. dst(I) is set to 0xff (all '1'-bits) if src(I) is within the range and 0 otherwise. All the arrays must have the same size (or ROI size)

Calculates one or more integral images for the source image Using these integral images, one may calculate sum, mean, standard deviation over arbitrary up-right or rotated rectangular region of the image in a constant time. It makes possible to do a fast blurring or fast block correlation with variable window size etc. In case of multi-channel images sums for each channel are accumulated independently.

Inverts matrix src1 and stores the result in src2

implements k-means algorithm that finds centers of cluster_count clusters and groups the input samples around the clusters. On output labels(i) contains a cluster index for sample stored in the i-th row of samples matrix

Calculates Laplacian of the source image by summing second x- and y- derivatives calculated using Sobel operator: dst(x,y) = d2src/dx2 + d2src/dy2 Specifying aperture_size=1 gives the fastest variant that is equal to convolving the image with the following kernel: |0 1 0| |1 -4 1| |0 1 0| Similar to cvSobel function, no scaling is done and the same combinations of input and output formats are supported.

Draws the line segment between pt1 and pt2 points in the image. The line is clipped by the image or ROI rectangle. For non-antialiased lines with integer coordinates the 8-connected or 4-connected Bresenham algorithm is used. Thick lines are drawn with rounding endings. Antialiased lines are drawn using Gaussian filtering.

The function emulates the human "foveal" vision and can be used for fast scale and rotation-invariant template matching, for object tracking etc.

Loads object from file. It provides a simple interface to cvRead. After object is loaded, the file storage is closed and all the temporary buffers are deleted. Thus, to load a dynamic structure, such as sequence, contour or graph, one should pass a valid destination memory storage to the function.

Loads an image from the specified file and returns the pointer to the loaded image. Currently the following file formats are supported: Windows bitmaps - BMP, DIB; JPEG files - JPEG, JPG, JPE; Portable Network Graphics - PNG; Portable image format - PBM, PGM, PPM; Sun rasters - SR, RAS; TIFF files - TIFF, TIF; OpenEXR HDR images - EXR; JPEG 2000 images - jp2.

Calculates natural logarithm of absolute value of every element of input array: dst(I)=log(abs(src(I))), src(I)!=0 dst(I)=C, src(I)=0 Where C is large negative number (-700 in the current implementation)

The function emulates the human "foveal" vision and can be used for fast scale and rotation-invariant template matching, for object tracking etc.

Fills the destination array with values from the look-up table. Indices of the entries are taken from the source array. That is, the function processes each element of src as following: dst(I)=lut[src(I)+DELTA] where DELTA=0 if src has depth CV_8U, and DELTA=128 if src has depth CV_8S

Calculates the weighted distance between two vectors and returns it

initializes the histogram, which header and bins are allocated by user. No cvReleaseHist need to be called afterwards. Only dense histograms can be initialized this way.

Initializes sequence header for array. The sequence header as well as the sequence block are allocated by the user (for example, on stack). No data is copied by the function. The resultant sequence will consists of a single block and have IntPtr.Zero storage pointer, thus, it is possible to read its elements, but the attempts to add elements to the sequence will raise an error in most cases

A fast inline substitution for cvInitMatHeader. Namely, it is equivalent to: CvMat mat; cvInitMatHeader( &mat, rows, cols, type, data, CV_AUTOSTEP );

Calculates the value of the matching measure for two contour trees. The similarity measure is calculated level by level from the binary tree roots. If at the certain level difference between contours becomes less than threshold, the reconstruction process is interrupted and the current difference is returned

Compares two shapes. The 3 implemented methods all use Hu moments

This function is similiar to cvCalcBackProjectPatch. It slids through image, compares overlapped patches of size wxh with templ using the specified method and stores the comparison results to result

Calculates per-element maximum of two arrays: dst(I)=max(src1(I), src2(I)) All the arrays must have a single channel, the same data type and the same size (or ROI size).

Finds minimum area rectangle that contains both input rectangles inside

Iterates to find the object center given its back projection and initial position of search window. The iterations are made until the search window center moves by less than the given value and/or until the function has done the maximum number of iterations.

This function is the opposite to cvSplit. If the destination array has N channels then if the first N input channels are not IntPtr.Zero, all they are copied to the destination array, otherwise if only a single source channel of the first N is not IntPtr.Zero, this particular channel is copied into the destination array, otherwise an error is raised. Rest of source channels (beyond the first N) must always be IntPtr.Zero. For IplImage cvCopy with COI set can be also used to insert a single channel into the image.

Calculates per-element minimum of two arrays: dst(I)=min(src1(I),src2(I)) All the arrays must have a single channel, the same data type and the same size (or ROI size).

Finds a circumscribed rectangle of the minimal area for 2D point set by building convex hull for the set and applying rotating calipers technique to the hull.

Finds the minimal circumscribed circle for 2D point set using iterative algorithm. It returns nonzero if the resultant circle contains all the input points and zero otherwise (i.e. algorithm failed)

Finds minimum and maximum element values and their positions. The extremums are searched over the whole array, selected ROI (in case of IplImage) or, if mask is not IntPtr.Zero, in the specified array region. If the array has more than one channel, it must be IplImage with COI set. In case if multi-dimensional arrays min_loc->x and max_loc->x will contain raw (linear) positions of the extremums

Calculates minimum of array and scalar: dst(I)=min(src(I), value) All the arrays must have a single channel, the same data type and the same size (or ROI size).

Calculates spatial and central moments up to the third order and writes them to moments. The moments may be used then to calculate gravity center of the shape, its area, main axises and various shape characeteristics including 7 Hu invariants.

Performs advanced morphological transformations.

Calculates per-element product of two arrays: dst(I)=scale*src1(I)*src2(I) All the arrays must have the same type, and the same size (or ROI size)

Performs per-element multiplication of the two CCS-packed or complex matrices that are results of real or complex Fourier transform.

Adds product of 2 images or thier selected regions to accumulator acc

Calculates the product of src and its transposition. The function evaluates dst=(src-delta)*(src-delta)^T if order=0, and dst=(src-delta)^T*(src-delta) otherwise.

Creates a window which can be used as a placeholder for images and trackbars. Created windows are reffered by their names. If the window with such a name already exists, the function does nothing.

Returns the calculated norm. The multiple-channel array are treated as single-channel, that is, the results for all channels are combined.

normalizes the input array so that it's norm or value range takes the certain value(s).

Normalizes the histogram bins by scaling them, such that the sum of the bins becomes equal to factor

Inverses every bit of every array element:

Opens file storage for reading or writing data. In the latter case a new file is created or existing file is rewritten. Type of the read of written file is determined by the filename extension: .xml for XML, and .yml or .yaml for YAML

Calculates per-element bit-wise disjunction of two arrays: dst(I)=src1(I)|src2(I) In the case of floating-point arrays their bit representations are used for the operation. All the arrays must have the same type, except the mask, and the same size

Calculates per-element bit-wise disjunction of array and scalar: dst(I)=src(I)|value if mask(I)!=0 Prior to the actual operation the scalar is converted to the same type as the arrays. In the case of floating-point arrays their bit representations are used for the operation. All the arrays must have the same type, except the mask, and the same size

Transforms every element of src (by treating it as 2D or 3D vector) in the following way: (x, y, z) -> (x'/w, y'/w, z'/w) or (x, y) -> (x'/w, y'/w), where (x', y', z', w') = mat4x4 * (x, y, z, 1) or (x', y', w') = mat3x3 * (x, y, 1) and w = w' if w'!=0, inf otherwise

Raises every element of input array to p: dst(I)=src(I)p, if p is integer dst(I)=abs(src(I))p, otherwise That is, for non-integer power exponent the absolute values of input array elements are used. However, it is possible to get true values for negative values using some extra operations, as the following sample, computing cube root of array elements, shows: CvSize size = cvGetSize(src); CvMat* mask = cvCreateMat( size.height, size.width, CV_8UC1 ); cvCmpS( src, 0, mask, CV_CMP_LT ); /* find negative elements */ cvPow( src, dst, 1./3 ); cvSubRS( dst, cvScalarAll(0), dst, mask ); /* negate the results of negative inputs */ cvReleaseMat( &mask ); For some values of power, such as integer values, 0.5 and -0.5, specialized faster algorithms are used.

Projects vectors to the specified subspace

Computes projections of 3D points to the image plane given intrinsic and extrinsic camera parameters. Optionally, the function computes jacobians - matrices of partial derivatives of image points as functions of all the input parameters w.r.t. the particular parameters, intrinsic and/or extrinsic. The jacobians are used during the global optimization in cvCalibrateCamera2 and cvFindExtrinsicCameraParams2. The function itself is also used to compute back-projection error for with current intrinsic and extrinsic parameters. Note, that with intrinsic and/or extrinsic parameters set to special values, the function can be used to compute just extrinsic transformation or just intrinsic transformation (i.e. distortion of a sparse set of points).

Renders the text in the image with the specified font and color. The printed text is clipped by ROI rectangle. Symbols that do not belong to the specified font are replaced with the rectangle symbol.

Performs downsampling step of Gaussian pyramid decomposition. First it convolves source image with the specified filter and then downsamples the image by rejecting even rows and columns.

The function cvPyrSegmentation implements image segmentation by pyramids. The pyramid builds up to the level level. The links between any pixel a on level i and its candidate father pixel b on the adjacent level are established if p(c(a),c(b))>threshold1. After the connected components are defined, they are joined into several clusters. Any two segments A and B belong to the same cluster, if p(c(A),c(B))>threshold2. The input image has only one channel, then p(c1,c2)=|c1-c2|. If the input image has three channels (red, green and blue), then p(c1,c2)=0.3*(c1r-c2r)+0.59 * (c1g-c2g)+0.11 *(c1b-c2b) . There may be more than one connected component per a cluster.

Performs up-sampling step of Gaussian pyramid decomposition. First it upsamples the source image by injecting even zero rows and columns and then convolves result with the specified filter multiplied by 4 for interpolation. So the destination image is four times larger than the source image.

Grabs a frame from camera or video file, decompresses and returns it. This function is just a combination of cvGrabFrame and cvRetrieveFrame in one call. The returned image should not be released or modified by user.

Return the value of the specified bin of 1D histogram. In case of sparse histogram the function returns 0, if the bin is not present in the histogram, and no new bin is created.

Return the value of the specified bin of 2D histogram. In case of sparse histogram the function returns 0, if the bin is not present in the histogram, and no new bin is created.

Return the value of the specified bin of 3D histogram. In case of sparse histogram the function returns 0, if the bin is not present in the histogram, and no new bin is created.

Fills the destination array with uniformly or normally distributed random numbers.

Shuffles the matrix by swapping randomly chosen pairs of the matrix elements on each iteration (where each element may contain several components in case of multi-channel arrays)

Initializes the matrix as following: arr(i,j)=(end-start)*(i*cols(arr)+j)/(cols(arr)*rows(arr))

Decodes user object (creates object in a native representation from the file storage subtree) and returns it

Draws a rectangle with two opposite corners pt1 and pt2

Reduces matrix to a vector by treating the matrix rows/columns as a set of 1D vectors and performing the specified operation on the vectors until a single row/column is obtained.

Release the BG code book model

The function cvReleaseCapture releases the CvCapture structure allocated by cvCreateFileCapture or cvCreateCameraCapture

Releases the structure CvConDensation (see cvConDensation) and frees all memory previously allocated for the structure.

Deallocates the given kd-tree

Closes the file associated with the storage and releases all the temporary structures. It must be called after all I/O operations with the storage are finished

Deallocates the cascade that has been created manually or loaded using cvLoadHaarClassifierCascade or cvLoad

Releases the histogram (header and the data). The pointer to histogram is cleared by the function. If *hist pointer is already NULL, the function does nothing.

Releases the header and the image data.

Releases the header.

Releases the structure CvKalman and all underlying matrices

Decrements the matrix data reference counter and releases matrix header

Deallocates all storage memory blocks or returns them to the parent, if any. Then it deallocates the storage header and clears the pointer to the storage. All children of the storage must be released before the parent is released.

The function cvReleasePOSITObject releases memory previously allocated by the function cvCreatePOSITObject.

Releases the stereo correspondence structure and all the associated internal buffers

Releases the stereo correspondence structure and all the associated internal buffers

Releases the structuring element.

Finishes writing to video file and releases the structure.

Similar to other geometrical transformations, some interpolation method (specified by user) is used to extract pixels with non-integer coordinates.

Fills the destination array with source array tiled: dst(i,j)=src(i mod rows(src), j mod cols(src))So the destination array may be as larger as well as smaller than the source array

Transforms 1-channel disparity map to 3-channel image, a 3D surface.

Releases image ROI. After that the whole image is considered selected.

initializes CvMat header so that it points to the same data as the original array but has different shape - different number of channels, different number of rows or both

Resizes image src so that it fits exactly to dst. If ROI is set, the function consideres the ROI as supported as usual

Converts a rotation vector to rotation matrix or vice versa. Rotation vector is a compact representation of rotation matrix. Direction of the rotation vector is the rotation axis and the length of the vector is the rotation angle around the axis. The rotation matrix R, corresponding to the rotation vector r.

Calculates weighted sum of input image image and the accumulator acc so that acc becomes a running average of frame sequence: acc(x,y)=(1-alpha) * acc(x,y) + alpha * image(x,y) if mask(x,y)!=0 where alpha regulates update speed (how fast accumulator forgets about previous frames).

Implements a particular case of application of line iterators. The function reads all the image points lying on the line between pt1 and pt2, including the ending points, and stores them into the buffer

Saves the image to the specified file. The image format is chosen depending on the filename extension, see cvLoadImage. Only 8-bit single-channel or 3-channel (with 'BGR' channel order) images can be saved using this function. If the format, depth or channel order is different, use cvCvtScale and cvCvtColor to convert it before saving, or use universal cvSave to save the image to XML or YAML format

Finds all the motion segments and marks them in segMask with individual values each (1,2,...). It also returns a sequence of CvConnectedComp structures, one per each motion components. After than the motion direction for every component can be calculated with cvCalcGlobalOrientation using extracted mask of the particular component (using cvCmp)

Shifts the sequence elements from the inserted position to the nearest end of the sequence and copies the element content there if the pointer is not IntPtr.Zero

Removes element from sequence end.

Removes element from sequence beginning.

Removes several elements from either end of the sequence. If the number of the elements to be removed exceeds the total number of elements in the sequence, the function removes as many elements as possible

Adds an element to the end of sequence and retuns pointer to the allocated element. If the input element is NULL, the function simply allocates a space for one more element.

Adds an element to the front of sequence and retuns pointer to the allocated element. If the input element is NULL, the function simply allocates a space for one more element.

Adds several elements to either end of the sequence. The elements are added to the sequence in the same order as they are arranged in the input array but they can fall into different sequence blocks.

Removes element from sequence middle

Copies scalar value to every selected element of the destination array: arr(I)=value if mask(I)!=0 If array arr is of IplImage type, then is ROI used, but COI must not be set

Assign the new value to the particular element of array

Sets the specified property of video capturing

Assigns user data to the array header.

Sets the specified error mode.

Sets the error status to the specified value. Mostly, the function is used to reset the error status (set to it CV_StsOk) to recover after error. In other cases it is more natural to call cvError or CV_ERROR.

Initializes scaled identity matrix: arr(i,j)=value if i=j, 0 otherwise

Sets the channel of interest to a given value. Value 0 means that all channels are selected, 1 means that the first channel is selected etc. If ROI is NULL and coi != 0, ROI is allocated.

Sets the image ROI to a given rectangle. If ROI is NULL and the value of the parameter rect is not equal to the whole image, ROI is allocated.

The function cvSetMemoryManager sets user-defined memory managment functions (substitutors for malloc and free) that will be called by cvAlloc, cvFree and higher-level functions (e.g. cvCreateImage)

Sets the number of threads that are used by parallelized OpenCV functions.

Assign the new value to the particular element of single-channel array

Assign the new value to the particular element of single-channel array

Assign the new value to the particular element of single-channel array

Assign the new value to the particular element of single-channel array

Clears the array. In case of dense arrays (CvMat, CvMatND or IplImage) cvZero(array) is equivalent to cvSet(array,cvScalarAll(0),0), in case of sparse arrays all the elements are removed

Shows the image in the specified window

Smooths image using one of several methods. Every of the methods has some features and restrictions listed below Blur with no scaling works with single-channel images only and supports accumulation of 8-bit to 16-bit format (similar to cvSobel and cvLaplace) and 32-bit floating point to 32-bit floating-point format. Simple blur and Gaussian blur support 1- or 3-channel, 8-bit and 32-bit floating point images. These two methods can process images in-place. Median and bilateral filters work with 1- or 3-channel 8-bit images and can not process images in-place.

The Sobel operators combine Gaussian smoothing and differentiation so the result is more or less robust to the noise. Most often, the function is called with (xorder=1, yorder=0, aperture_size=3) or (xorder=0, yorder=1, aperture_size=3) to calculate first x- or y- image derivative. The first case corresponds to

 
              |-1  0  1|
              |-2  0  2|
              |-1  0  1|

kernel and the second one corresponds to

              |-1 -2 -1|
              | 0  0  0|
              | 1  2  1|

or

              | 1  2  1|
              | 0  0  0|
              |-1 -2 -1|

kernel, depending on the image origin (origin field of IplImage structure). No scaling is done, so the destination image usually has larger by absolute value numbers than the source image. To avoid overflow, the function requires 16-bit destination image if the source image is 8-bit. The result can be converted back to 8-bit using cvConvertScale or cvConvertScaleAbs functions. Besides 8-bit images the function can process 32-bit floating-point images. Both source and destination must be single-channel images of equal size or ROI size

finds real roots of a cubic equation: coeffs[0]*x^3 + coeffs[1]*x^2 + coeffs[2]*x + coeffs[3] = 0 (if coeffs is 4-element vector) or x^3 + coeffs[0]*x^2 + coeffs[1]*x + coeffs[2] = 0 (if coeffs is 3-element vector)

Finds all real and complex roots of any degree polynomial with real coefficients

Divides a multi-channel array into separate single-channel arrays. Two modes are available for the operation. If the source array has N channels then if the first N destination channels are not IntPtr.Zero, all they are extracted from the source array, otherwise if only a single destination channel of the first N is not IntPtr.Zero, this particular channel is extracted, otherwise an error is raised. Rest of destination channels (beyond the first N) must always be IntPtr.Zero. For IplImage cvCopy with COI set can be also used to extract a single channel from the image

Adds the input image image or its selected region, raised to power 2, to the accumulator sqsum

Initializes the reader state

Estimates transformation between the 2 cameras making a stereo pair. If we have a stereo camera, where the relative position and orientatation of the 2 cameras is fixed, and if we computed poses of an object relative to the fist camera and to the second camera, (R1, T1) and (R2, T2), respectively (that can be done with cvFindExtrinsicCameraParams2), obviously, those poses will relate to each other, i.e. given (R1, T1) it should be possible to compute (R2, T2) - we only need to know the position and orientation of the 2nd camera relative to the 1st camera. That's what the described function does. It computes (R, T) such that: R2=R*R1, T2=R*T1 + T

computes the rotation matrices for each camera that (virtually) make both camera image planes the same plane. Consequently, that makes all the epipolar lines parallel and thus simplifies the dense stereo correspondence problem. On input the function takes the matrices computed by cvStereoCalibrate and on output it gives 2 rotation matrices and also 2 projection matrices in the new coordinates. The function is normally called after cvStereoCalibrate that computes both camera matrices, the distortion coefficients, R and T

computes the rectification transformations without knowing intrinsic parameters of the cameras and their relative position in space, hence the suffix "Uncalibrated". Another related difference from cvStereoRectify is that the function outputs not the rectification transformations in the object (3D) space, but the planar perspective transformations, encoded by the homography matrices H1 and H2. The function implements the following algorithm [Hartley99].

Subtracts one array from another one: dst(I)=src1(I)-src2(I) if mask(I)!=0 All the arrays must have the same type, except the mask, and the same size (or ROI size)

Locates input point within subdivision

Inserts a single point to subdivision and modifies the subdivision topology appropriately. If a points with same coordinates exists already, no new points is added. The function returns pointer to the allocated point. No virtual points coordinates is calculated at this stage.

Subtracts every element of source array from a scalar: dst(I)=value-src(I) if mask(I)!=0 All the arrays must have the same type, except the mask, and the same size (or ROI size)

Subtracts a scalar from every element of the source array: dst(I)=src(I)-value if mask(I)!=0 All the arrays must have the same type, except the mask, and the same size (or ROI size)

Calculates sum S of array elements, independently for each channel Sc = sumI arr(I)c If the array is IplImage and COI is set, the function processes the selected channel only and stores the sum to the first scalar component (S0).

Create a CvSURFParams using the specific values

Decomposes matrix A into a product of a diagonal matrix and two orthogonal matrices: A=U*W*VT Where W is diagonal matrix of singular values that can be coded as a 1D vector of singular values and U and V. All the singular values are non-negative and sorted (together with U and and V columns) in descenting order.

Clears histogram bins that are below the specified threshold

Applies fixed-level thresholding to single-channel array. The function is typically used to get bi-level (binary) image out of grayscale image (cvCmpS could be also used for this purpose) or for removing a noise, i.e. filtering out pixels with too small or too large values. There are several types of thresholding the function supports that are determined by threshold_type

Returns sum of diagonal elements of the matrix src1.

Performs matrix transformation of every element of array src and stores the results in dst Both source and destination arrays should have the same depth and the same size or selected ROI size. transmat and shiftvec should be real floating-point matrices.

Transposes matrix src1: dst(i,j)=src(j,i) Note that no complex conjugation is done in case of complex matrix. Conjugation should be done separately: look at the sample code in cvXorS for example

Transforms the image to compensate radial and tangential lens distortion. The camera matrix and distortion parameters can be determined using cvCalibrateCamera2. For every pixel in the output image the function computes coordinates of the corresponding location in the input image using the formulae in the section beginning. Then, the pixel value is computed using bilinear interpolation. If the resolution of images is different from what was used at the calibration stage, fx, fy, cx and cy need to be adjusted appropriately, while the distortion coefficients remain the same.

Similar to cvInitUndistortRectifyMap and is opposite to it at the same time. The functions are similar in that they both are used to correct lens distortion and to perform the optional perspective (rectification) transformation. They are opposite because the function cvInitUndistortRectifyMap does actually perform the reverse transformation in order to initialize the maps properly, while this function does the forward transformation.

Updates the motion history image as following: mhi(x,y)=timestamp if silhouette(x,y)!=0 0 if silhouette(x,y)=0 and mhi(x,y)<timestamp-duration mhi(x,y) otherwise That is, MHI pixels where motion occurs are set to the current timestamp, while the pixels where motion happened far ago are cleared.

Waits for key event infinitely (delay <= 0) or for "delay" milliseconds.

Transforms source image using the specified matrix

Transforms source image using the specified matrix

Implements one of the variants of watershed, non-parametric marker-based segmentation algorithm, described in [Meyer92] Before passing the image to the function, user has to outline roughly the desired regions in the image markers with positive (>0) indices, i.e. every region is represented as one or more connected components with the pixel values 1, 2, 3 etc. Those components will be "seeds" of the future image regions. All the other pixels in markers, which relation to the outlined regions is not known and should be defined by the algorithm, should be set to 0's. On the output of the function, each pixel in markers is set to one of values of the "seed" components, or to -1 at boundaries between the regions.

Writes/appends one frame to video file.

Calculates per-element bit-wise logical conjunction of two arrays: dst(I)=src1(I)^src2(I) if mask(I)!=0 In the case of floating-point arrays their bit representations are used for the operation. All the arrays must have the same type, except the mask, and the same size

Calculates per-element bit-wise conjunction of array and scalar: dst(I)=src(I)^value if mask(I)!=0 Prior to the actual operation the scalar is converted to the same type as the arrays. In the case of floating-point arrays their bit representations are used for the operation. All the arrays must have the same type, except the mask, and the same size

Clears the array. In case of dense arrays (CvMat, CvMatND or IplImage) cvZero(array) is equivalent to cvSet(array,cvScalarAll(0),0), in case of sparse arrays all the elements are removed

The file name of the cv library

The file name of the cvaux library

An error handler which will ignore any error and continute

The default Exception callback to handle Error thrown by OpenCV

The file name of the cxcore library

The file name of the cvextern library

The file name of the highgui library