Open Source Computer Vision
cv::gpu::MOG_GPU Class Reference

#include <gpu.hpp>

Public Member Functions

 MOG_GPU (int nmixtures=-1)
 the default constructor More...
void initialize (Size frameSize, int frameType)
 re-initiaization method More...
void operator() (const GpuMat &frame, GpuMat &fgmask, float learningRate=0.0f, Stream &stream=Stream::Null())
 the update operator More...
void getBackgroundImage (GpuMat &backgroundImage, Stream &stream=Stream::Null()) const
 computes a background image which are the mean of all background gaussians More...
void release ()
 releases all inner buffers More...

Public Attributes

int history
float varThreshold
float backgroundRatio
float noiseSigma

Detailed Description

Gaussian Mixture-based Backbround/Foreground Segmentation Algorithm

The class implements the following algorithm: "An improved adaptive background mixture model for real-time tracking with shadow detection" P. KadewTraKuPong and R. Bowden, Proc. 2nd European Workshp on Advanced Video-Based Surveillance Systems, 2001."

Constructor & Destructor Documentation


cv::gpu::MOG_GPU::MOG_GPU ( int  nmixtures = -1)

the default constructor

Member Function Documentation

§ getBackgroundImage()

void cv::gpu::MOG_GPU::getBackgroundImage ( GpuMat backgroundImage,
Stream stream = Stream::Null() 
) const

computes a background image which are the mean of all background gaussians

§ initialize()

void cv::gpu::MOG_GPU::initialize ( Size  frameSize,
int  frameType 

re-initiaization method

§ operator()()

void cv::gpu::MOG_GPU::operator() ( const GpuMat frame,
GpuMat fgmask,
float  learningRate = 0.0f,
Stream stream = Stream::Null() 

the update operator

§ release()

void cv::gpu::MOG_GPU::release ( )

releases all inner buffers

Member Data Documentation

§ backgroundRatio

float cv::gpu::MOG_GPU::backgroundRatio

§ history

int cv::gpu::MOG_GPU::history

§ noiseSigma

float cv::gpu::MOG_GPU::noiseSigma

§ varThreshold

float cv::gpu::MOG_GPU::varThreshold

The documentation for this class was generated from the following file: