#include <gpu.hpp>

Public Member Functions
	GMG_GPU ()

void	initialize (Size frameSize, float min=0.0f, float max=255.0f)

void	operator() (const GpuMat &frame, GpuMat &fgmask, float learningRate=-1.0f, Stream &stream=Stream::Null())

void	release ()
	Releases all inner buffers. More...

Public Attributes
int	maxFeatures
	Total number of distinct colors to maintain in histogram. More...

float	learningRate
	Set between 0.0 and 1.0, determines how quickly features are "forgotten" from histograms. More...

int	numInitializationFrames
	Number of frames of video to use to initialize histograms. More...

int	quantizationLevels
	Number of discrete levels in each channel to be used in histograms. More...

float	backgroundPrior
	Prior probability that any given pixel is a background pixel. A sensitivity parameter. More...

float	decisionThreshold
	Value above which pixel is determined to be FG. More...

int	smoothingRadius
	Smoothing radius, in pixels, for cleaning up FG image. More...

bool	updateBackgroundModel
	Perform background model update. More...

Detailed Description

Background Subtractor module. Takes a series of images and returns a sequence of mask (8UC1) images of the same size, where 255 indicates Foreground and 0 represents Background. This class implements an algorithm described in "Visual Tracking of Human Visitors under Variable-Lighting Conditions for a Responsive Audio Art Installation," A. Godbehere, A. Matsukawa, K. Goldberg, American Control Conference, Montreal, June 2012.

Constructor & Destructor Documentation

§ GMG_GPU()

cv::gpu::GMG_GPU::GMG_GPU ( )

Member Function Documentation

§ initialize()

void cv::gpu::GMG_GPU::initialize	(	Size	frameSize,
		float	min = `0.0f`,
		float	max = `255.0f`
	)

Validate parameters and set up data structures for appropriate frame size.

Parameters

frameSize	Input frame size
min	Minimum value taken on by pixels in image sequence. Usually 0
max	Maximum value taken on by pixels in image sequence. e.g. 1.0 or 255

§ operator()()

void cv::gpu::GMG_GPU::operator()	(	const GpuMat &	frame,
		GpuMat &	fgmask,
		float	learningRate = `-1.0f`,
		Stream &	stream = `Stream::Null()`
	)

Performs single-frame background subtraction and builds up a statistical background image model.

Parameters

frame	Input frame
fgmask	Output mask image representing foreground and background pixels
learningRate	determines how quickly features are “forgotten” from histograms
stream	Stream for the asynchronous version

§ release()

void cv::gpu::GMG_GPU::release ( )

Releases all inner buffers.

Member Data Documentation

§ backgroundPrior

float cv::gpu::GMG_GPU::backgroundPrior

Prior probability that any given pixel is a background pixel. A sensitivity parameter.

§ decisionThreshold

float cv::gpu::GMG_GPU::decisionThreshold

Value above which pixel is determined to be FG.

§ learningRate

float cv::gpu::GMG_GPU::learningRate

Set between 0.0 and 1.0, determines how quickly features are "forgotten" from histograms.

§ maxFeatures

int cv::gpu::GMG_GPU::maxFeatures

Total number of distinct colors to maintain in histogram.

§ numInitializationFrames

int cv::gpu::GMG_GPU::numInitializationFrames

Number of frames of video to use to initialize histograms.

§ quantizationLevels

int cv::gpu::GMG_GPU::quantizationLevels

Number of discrete levels in each channel to be used in histograms.

§ smoothingRadius

int cv::gpu::GMG_GPU::smoothingRadius

Smoothing radius, in pixels, for cleaning up FG image.

§ updateBackgroundModel

bool cv::gpu::GMG_GPU::updateBackgroundModel

Perform background model update.

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

gpu/include/opencv2/gpu/gpu.hpp

Public Member Functions

Public Attributes