FGMMForeground

Performs the Gaussian mixture model foreground subtraction.

Syntax

IppStatus ippiFGMMForeground_8u_C3R(const Ipp8u* pSrc, int srcStep, Ipp8u* pDst, int dstStep, IppiSize roi, IppFGMMState_8u_C3R* pState, IppFGMModel* pModel, double learning_rate);

Include Files

ippcv.h

Domain Dependencies

Headers: ippcore.h, ippvm.h, ipps.h, ippi.h

Libraries: ippcore.lib, ippvm.lib, ipps.lib, ippi.lib

Parameters

pSrc: Pointer to the source image.
srcStep: Distance, in bytes, between the starting points of consecutive lines in the source image.
pDst: Pointer to the one-channel Ipp8u mask of foreground.
dstStep: Distance, in bytes, between the starting points of consecutive lines in the destination image.
roi: Size of the source image ROI, in pixels.
learning_rate: Speed of algorithm learning.
pState: Pointer to the IppFGMMState_8u_C3R state structure.
pModel: Pointer to the IppFGMModel structure containing parameters for the model. If pModel is NULL, the parameters are the same as in a previous call.

Description

This function operates with ROI.

This function implements the Gaussian mixture model foreground subtraction described in [ZIVKOVIC04]. The foreground mask is stored in pDst.

Before using this function, you need to compute the size of the IppFGMMState_8u_C3R state structure and initialize the structure using the FGMMGetBufferSize and FGMMInit functions, respectively.

For an example on how to use this function, refer to the example provided with the FGMMBackground function description.

Return Values

ippStsNoErr	Indicates no error.
ippStsNullPtrErr	Indicates an error when pSrc, pDst, pModel, or pState is `NULL`.
ippStsSizeErr	Indicates an error when roi is less than, or equal to zero.
ippStsStepErr	Indicates an error when srcStep or dstStep is less than, or equal to zero.