Skip to content

O
opencv
Commit 79ef454c authored by Vladislav Vinogradov's avatar Vladislav Vinogradov
Browse files
Options

Merge branch 'bgfg-gmg-optimized' into bgfg-gmg-merged

parents 827fa850 bfd9e610
Show whitespace changes
Inline Side-by-side
Showing with 269 additions and 503 deletions
modules/gpu/perf_cpu/perf_video.cpp
View file @ 79ef454c
......@@ -361,10 +361,9 @@ GPU_PERF_TEST(GMG, cv::gpu::DeviceInfo, std::string, Channels, MaxFeatures)
cv::BackgroundSubtractorGMG gmg;
gmg.set("maxFeatures", maxFeatures);
gmg.initializeType(frame, 0.0, 255.0);
gmg.initialize(frame.size(), 0.0, 255.0);
gmg(frame, fgmask);
gmg.updateBackgroundModel(zeros);
for (int i = 0; i < 150; ++i)
{
......@@ -387,7 +386,6 @@ GPU_PERF_TEST(GMG, cv::gpu::DeviceInfo, std::string, Channels, MaxFeatures)
startTimer(); next();
gmg(frame, fgmask);
gmg.updateBackgroundModel(zeros);
stopTimer();
}
}
......
modules/video/include/opencv2/video/background_segm.hpp
View file @ 79ef454c
......@@ -199,111 +199,20 @@ protected:
*/
class CV_EXPORTS BackgroundSubtractorGMG: public cv::BackgroundSubtractor
{
protected:
/**
* Used internally to represent a single feature in a histogram.
* Feature is a color and an associated likelihood (weight in the histogram).
*/
struct CV_EXPORTS HistogramFeatureGMG
{
/**
* Default constructor.
* Initializes likelihood of feature to 0, color remains uninitialized.
*/
HistogramFeatureGMG(){likelihood = 0.0;}
/**
* Copy constructor.
* Required to use HistogramFeatureGMG in a std::vector
* @see operator =()
*/
HistogramFeatureGMG(const HistogramFeatureGMG& orig){
color = orig.color; likelihood = orig.likelihood;
}
/**
* Assignment operator.
* Required to use HistogramFeatureGMG in a std::vector
*/
HistogramFeatureGMG& operator =(const HistogramFeatureGMG& orig){
color = orig.color; likelihood = orig.likelihood; return *this;
}
/**
* Tests equality of histogram features.
* Equality is tested only by matching the color (feature), not the likelihood.
* This operator is used to look up an observed feature in a histogram.
*/
bool operator ==(HistogramFeatureGMG &rhs);
//! Regardless of the image datatype, it is quantized and mapped to an integer and represented as a vector.
vector<size_t> color;
//! Represents the weight of feature in the histogram.
float likelihood;
friend class PixelModelGMG;
};
/**
* Representation of the statistical model of a single pixel for use in the background subtraction
* algorithm.
*/
class CV_EXPORTS PixelModelGMG
{
public:
PixelModelGMG();
~PixelModelGMG();
/**
* Incorporate the last observed feature into the statistical model.
*
* @param learningRate The adaptation parameter for the histogram. -1.0 to use default. Value
* should be between 0.0 and 1.0, the higher the value, the faster the
* adaptation. 1.0 is limiting case where fast adaptation means no memory.
*/
void insertFeature(double learningRate = -1.0);
/**
* Set the feature last observed, to save before incorporating it into the statistical
* model with insertFeature().
*
* @param feature The feature (color) just observed.
*/
void setLastObservedFeature(BackgroundSubtractorGMG::HistogramFeatureGMG feature);
/**
* Set the upper limit for the number of features to store in the histogram. Use to adjust
* memory requirements.
*
* @param max size_t representing the max number of features.
*/
void setMaxFeatures(size_t max) {
maxFeatures = max; histogram.resize(max); histogram.clear();
}
/**
* Normalize the histogram, so sum of weights of all features = 1.0
*/
void normalizeHistogram();
/**
* Return the weight of a feature in the histogram. If the feature is not represented in the
* histogram, the weight returned is 0.0.
*/
double getLikelihood(HistogramFeatureGMG f);
PixelModelGMG& operator *=(const float &rhs);
//friend class BackgroundSubtractorGMG;
//friend class HistogramFeatureGMG;
private:
size_t numFeatures; //!< number of features in histogram
size_t maxFeatures; //!< max allowable features in histogram
std::list<HistogramFeatureGMG> histogram; //!< represents the histogram as a list of features
HistogramFeatureGMG lastObservedFeature;
//!< store last observed feature in case we need to add it to histogram
};
public:
BackgroundSubtractorGMG();
virtual ~BackgroundSubtractorGMG();
virtual AlgorithmInfo* info() const;
/**
* Validate parameters and set up data structures for appropriate image size.
* Must call before running on data.
* @param frameSize input frame size
* @param min minimum value taken on by pixels in image sequence. Usually 0
* @param max maximum value taken on by pixels in image sequence. e.g. 1.0 or 255
*/
void initialize(cv::Size frameSize, double min, double max);
/**
* Performs single-frame background subtraction and builds up a statistical background image
* model.
......@@ -313,28 +222,10 @@ public:
virtual void operator()(InputArray image, OutputArray fgmask, double learningRate=-1.0);
/**
* Validate parameters and set up data structures for appropriate image type. Must call before
* running on data.
* @param image One sample image from dataset
* @param min minimum value taken on by pixels in image sequence. Usually 0
* @param max maximum value taken on by pixels in image sequence. e.g. 1.0 or 255
*/
void initializeType(InputArray image, double min, double max);
/**
* Selectively update the background model. Only update background model for pixels identified
* as background.
* @param mask Mask image same size as images in sequence. Must be 8UC1 matrix, 255 for foreground
* and 0 for background.
*/
void updateBackgroundModel(InputArray mask);
/**
* Retrieve the greyscale image representing the probability that each pixel is foreground given
* the current estimated background model. Values are 0.0 (black) to 1.0 (white).
* @param img The 32FC1 image representing per-pixel probabilities that the pixel is foreground.
* Releases all inner buffers.
*/
void getPosteriorImage(OutputArray img);
void release();
protected:
//! Total number of distinct colors to maintain in histogram.
int maxFeatures;
//! Set between 0.0 and 1.0, determines how quickly features are "forgotten" from histograms.
......@@ -345,31 +236,25 @@ protected:
int quantizationLevels;
//! Prior probability that any given pixel is a background pixel. A sensitivity parameter.
double backgroundPrior;
//! Value above which pixel is determined to be FG.
double decisionThreshold;
//! Smoothing radius, in pixels, for cleaning up FG image.
int smoothingRadius;
//! Perform background model update
bool updateBackgroundModel;
double decisionThreshold; //!< value above which pixel is determined to be FG.
int smoothingRadius; //!< smoothing radius, in pixels, for cleaning up FG image.
double maxVal, minVal;
private:
double maxVal_;
double minVal_;
/*
* General Parameters
*/
int imWidth; //!< width of image.
int imHeight; //!< height of image.
size_t numPixels;
unsigned int numChannels; //!< Number of channels in image.
cv::Size frameSize_;
int frameNum_;
bool isDataInitialized;
//!< After general parameters are set, data structures must be initialized.
cv::Mat_<int> nfeatures_;
cv::Mat_<int> colors_;
cv::Mat_<float> weights_;
/*
* Data Structures
*/
vector<PixelModelGMG> pixels; //!< Probabilistic background models for each pixel in image.
int frameNum; //!< Frame number counter, used to count frames in training mode.
Mat posteriorImage; //!< Posterior probability image.
Mat fgMaskImage; //!< Foreground mask image.
cv::Mat buf_;
};
}
......
modules/video/src/bgfg_gmg.cpp
View file @ 79ef454c
......@@ -48,12 +48,7 @@
#include "precomp.hpp"
using namespace std;
namespace cv
{
BackgroundSubtractorGMG::BackgroundSubtractorGMG()
cv::BackgroundSubtractorGMG::BackgroundSubtractorGMG()
{
/*
* Default Parameter Values. Override with algorithm "set" method.
......@@ -65,391 +60,293 @@ BackgroundSubtractorGMG::BackgroundSubtractorGMG()
backgroundPrior = 0.8;
decisionThreshold = 0.8;
smoothingRadius = 7;
updateBackgroundModel = true;
}
void BackgroundSubtractorGMG::initializeType(InputArray _image, double min, double max)
cv::BackgroundSubtractorGMG::~BackgroundSubtractorGMG()
{
minVal = min;
maxVal = max;
if (minVal == maxVal)
{
CV_Error_(CV_StsBadArg,("minVal and maxVal cannot be the same."));
}
}
/*
* Parameter validation
*/
if (maxFeatures <= 0)
{
CV_Error_(CV_StsBadArg,
("maxFeatures parameter must be 1 or greater. Instead, it is %d.",maxFeatures));
}
if (learningRate < 0.0 || learningRate > 1.0)
{
CV_Error_(CV_StsBadArg,
("learningRate parameter must be in the range [0.0,1.0]. Instead, it is %f.",
learningRate));
}
if (numInitializationFrames < 1)
{
CV_Error_(CV_StsBadArg,
("numInitializationFrames must be at least 1. Instead, it is %d.",
numInitializationFrames));
}
if (quantizationLevels < 1)
{
CV_Error_(CV_StsBadArg,
("quantizationLevels must be at least 1 (preferably more). Instead it is %d.",
quantizationLevels));
}
if (backgroundPrior < 0.0 || backgroundPrior > 1.0)
{
CV_Error_(CV_StsBadArg,
("backgroundPrior must be a probability, between 0.0 and 1.0. Instead it is %f.",
backgroundPrior));
}
void cv::BackgroundSubtractorGMG::initialize(cv::Size frameSize, double min, double max)
{
CV_Assert(min < max);
CV_Assert(maxFeatures > 0);
CV_Assert(learningRate >= 0.0 && learningRate <= 1.0);
CV_Assert(numInitializationFrames >= 1);
CV_Assert(quantizationLevels >= 1 && quantizationLevels <= 255);
CV_Assert(backgroundPrior >= 0.0 && backgroundPrior <= 1.0);
/*
* Detect and accommodate the image depth
*/
Mat image = _image.getMat();
numChannels = image.channels();
minVal_ = min;
maxVal_ = max;
/*
* Color quantization [0 | | | | max] --> [0 | | max]
* (0) Use double as intermediary to convert all types to int.
* (i) Shift min to 0,
* (ii) max/(num intervals) = factor. x/factor * factor = quantized result, after integer operation.
*/
frameSize_ = frameSize;
frameNum_ = 0;
/*
* Data Structure Initialization
*/
imWidth = image.cols;
imHeight = image.rows;
numPixels = image.total();
pixels.resize(numPixels);
frameNum = 0;
// used to iterate through matrix of type unknown at compile time
//elemSize = image.elemSize();
//elemSize1 = image.elemSize1();
vector<PixelModelGMG>::iterator pixel;
vector<PixelModelGMG>::iterator pixel_end = pixels.end();
for (pixel = pixels.begin(); pixel != pixel_end; ++pixel)
{
pixel->setMaxFeatures(maxFeatures);
}
nfeatures_.create(frameSize_);
colors_.create(frameSize_.area(), maxFeatures);
weights_.create(frameSize_.area(), maxFeatures);
fgMaskImage = Mat::zeros(imHeight, imWidth, CV_8UC1); // 8-bit unsigned mask. 255 for FG, 0 for BG
posteriorImage = Mat::zeros(imHeight, imWidth, CV_32FC1); // float for storing probabilities. Can be viewed directly with imshow.
isDataInitialized = true;
nfeatures_.setTo(cv::Scalar::all(0));
}
void BackgroundSubtractorGMG::operator()(InputArray _image, OutputArray _fgmask, double newLearningRate)
namespace
{
if (!isDataInitialized)
float findFeature(int color, const int* colors, const float* weights, int nfeatures)
{
for (int i = 0; i < nfeatures; ++i)
{
CV_Error(CV_StsError,"BackgroundSubstractorGMG has not been initialized. Call initialize() first.\n");
if (color == colors[i])
return weights[i];
}
/*
* Update learning rate parameter, if desired
*/
if (newLearningRate != -1.0)
// not in histogram, so return 0.
return 0.0f;
}
void normalizeHistogram(float* weights, int nfeatures)
{
if (newLearningRate < 0.0 || newLearningRate > 1.0)
float total = 0.0f;
for (int i = 0; i < nfeatures; ++i)
total += weights[i];
if (total != 0.0f)
{
CV_Error(CV_StsOutOfRange,"Learning rate for Operator () must be between 0.0 and 1.0.\n");
for (int i = 0; i < nfeatures; ++i)
weights[i] /= total;
}
this->learningRate = newLearningRate;
}
Mat image = _image.getMat();
_fgmask.create(imHeight,imWidth,CV_8U);
fgMaskImage = _fgmask.getMat(); // 8-bit unsigned mask. 255 for FG, 0 for BG
/*
* Iterate over pixels in image
*/
// grab data at each pixel (1,2,3 channels, int, float, etc.)
// grab data as an array of bytes. Then, send that array to a function that reads data into vector of appropriate types... and quantizing... before saving as a feature, which is a vector of flexitypes, so code can be portable.
// multiple channels do have sequential storage, use mat::elemSize() and mat::elemSize1()
vector<PixelModelGMG>::iterator pixel;
vector<PixelModelGMG>::iterator pixel_end = pixels.end();
size_t i;
//#pragma omp parallel
for (i = 0, pixel=pixels.begin(); pixel != pixel_end; ++i,++pixel)
bool insertFeature(int color, float weight, int* colors, float* weights, int& nfeatures, int maxFeatures)
{
HistogramFeatureGMG newFeature;
newFeature.color.clear();
int irow = int(i / imWidth);
int icol = i % imWidth;
for (size_t c = 0; c < numChannels; ++c)
int idx = -1;
for (int i = 0; i < nfeatures; ++i)
{
/*
* Perform quantization. in each channel. (color-min)*(levels)/(max-min).
* Shifts min to 0 and scales, finally casting to an int.
*/
double color;
switch(image.depth())
if (color == colors[i])
{
case CV_8U: color = image.ptr<uchar>(irow)[icol * numChannels + c]; break;
case CV_8S: color = image.ptr<schar>(irow)[icol * numChannels + c]; break;
case CV_16U: color = image.ptr<ushort>(irow)[icol * numChannels + c]; break;
case CV_16S: color = image.ptr<short>(irow)[icol * numChannels + c]; break;
case CV_32S: color = image.ptr<int>(irow)[icol * numChannels + c]; break;
case CV_32F: color = image.ptr<float>(irow)[icol * numChannels + c]; break;
case CV_64F: color = image.ptr<double>(irow)[icol * numChannels + c]; break;
default: color = 0; break;
// feature in histogram
weight += weights[i];
idx = i;
break;
}
size_t quantizedColor = (size_t)((color-minVal)*quantizationLevels/(maxVal-minVal));
newFeature.color.push_back(quantizedColor);
}
// now that the feature is ready for use, put it in the histogram
if (frameNum > numInitializationFrames) // typical operation
if (idx >= 0)
{
newFeature.likelihood = float(learningRate);
/*
* (1) Query histogram to find posterior probability of feature under model.
*/
float likelihood = (float)pixel->getLikelihood(newFeature);
// move feature to beginning of list
// see Godbehere, Matsukawa, Goldberg (2012) for reasoning behind this implementation of Bayes rule
float posterior = float((likelihood*backgroundPrior)/(likelihood*backgroundPrior+(1-likelihood)*(1-backgroundPrior)));
::memmove(colors + 1, colors, idx * sizeof(int));
::memmove(weights + 1, weights, idx * sizeof(float));
/*
* (2) feed posterior probability into the posterior image
*/
int row,col;
col = i%imWidth;
row = int(i-col)/imWidth;
posteriorImage.at<float>(row,col) = (1.0f-posterior);
colors[0] = color;
weights[0] = weight;
}
pixel->setLastObservedFeature(newFeature);
else if (nfeatures == maxFeatures)
{
// discard oldest feature
::memmove(colors + 1, colors, (nfeatures - 1) * sizeof(int));
::memmove(weights + 1, weights, (nfeatures - 1) * sizeof(float));
colors[0] = color;
weights[0] = weight;
}
/*
* (3) Perform filtering and threshold operations to yield final mask image.
*
* 2 options. First is morphological open/close as before. Second is "median filtering" which Jon Barron says is good to remove noise
*/
Mat thresholdedPosterior;
threshold(posteriorImage,thresholdedPosterior,decisionThreshold,1.0,THRESH_BINARY);
thresholdedPosterior.convertTo(fgMaskImage,CV_8U,255); // convert image to integer space for further filtering and mask creation
medianBlur(fgMaskImage,fgMaskImage,smoothingRadius);
else
{
colors[nfeatures] = color;
weights[nfeatures] = weight;
fgMaskImage.copyTo(_fgmask);
++nfeatures;
++frameNum; // keep track of how many frames we have processed
}
return true;
}
void BackgroundSubtractorGMG::getPosteriorImage(OutputArray _img)
{
_img.create(Size(imWidth,imHeight),CV_32F);
Mat img = _img.getMat();
posteriorImage.copyTo(img);
return false;
}
}
void BackgroundSubtractorGMG::updateBackgroundModel(InputArray _mask)
namespace
{
CV_Assert(_mask.size() == Size(imWidth,imHeight)); // mask should be same size as image
Mat maskImg = _mask.getMat();
//#pragma omp parallel
for (int i = 0; i < imHeight; ++i)
template <int cn> struct Quantization_
{
//#pragma omp parallel
for (int j = 0; j < imWidth; ++j)
template <typename T>
static inline int apply(T val, double minVal, double maxVal, int quantizationLevels)
{
if (frameNum <= numInitializationFrames + 1)
int res = 0;
res |= static_cast<int>((val[0] - minVal) * quantizationLevels / (maxVal - minVal));
res |= static_cast<int>((val[1] - minVal) * quantizationLevels / (maxVal - minVal)) << 8;
res |= static_cast<int>((val[2] - minVal) * quantizationLevels / (maxVal - minVal)) << 16;
return res;
}
};
template <> struct Quantization_<1>
{
// insert previously observed feature into the histogram. -1.0 parameter indicates training.
pixels[i*imWidth+j].insertFeature(-1.0);
if (frameNum >= numInitializationFrames+1) // training is done, normalize
template <typename T>
static inline int apply(T val, double minVal, double maxVal, int quantizationLevels)
{
pixels[i*imWidth+j].normalizeHistogram();
}
return static_cast<int>((val - minVal) * quantizationLevels / (maxVal - minVal));
}
// if mask is 0, pixel is identified as a background pixel, so update histogram.
else if (maskImg.at<uchar>(i,j) == 0)
};
template <typename T> struct Quantization
{
pixels[i*imWidth+j].insertFeature(learningRate); // updates the histogram for the next iteration.
}
}
static int apply(const void* src_, int x, double minVal, double maxVal, int quantizationLevels)
{
const T* src = static_cast<const T*>(src_);
return Quantization_<cv::DataType<T>::channels>::apply(src[x], minVal, maxVal, quantizationLevels);
}
}
};
BackgroundSubtractorGMG::~BackgroundSubtractorGMG()
{
class GMG_LoopBody : public cv::ParallelLoopBody
{
public:
GMG_LoopBody(const cv::Mat& frame, const cv::Mat& fgmask, const cv::Mat_<int>& nfeatures, const cv::Mat_<int>& colors, const cv::Mat_<float>& weights,
int maxFeatures, double learningRate, int numInitializationFrames, int quantizationLevels, double backgroundPrior, double decisionThreshold,
double maxVal, double minVal, int frameNum, bool updateBackgroundModel) :
frame_(frame), fgmask_(fgmask), nfeatures_(nfeatures), colors_(colors), weights_(weights),
maxFeatures_(maxFeatures), learningRate_(learningRate), numInitializationFrames_(numInitializationFrames),
quantizationLevels_(quantizationLevels), backgroundPrior_(backgroundPrior), decisionThreshold_(decisionThreshold),
maxVal_(maxVal), minVal_(minVal), frameNum_(frameNum), updateBackgroundModel_(updateBackgroundModel)
{
}
}
void operator() (const cv::Range& range) const;
BackgroundSubtractorGMG::PixelModelGMG::PixelModelGMG()
{
numFeatures = 0;
maxFeatures = 0;
}
private:
const cv::Mat frame_;
BackgroundSubtractorGMG::PixelModelGMG::~PixelModelGMG()
{
mutable cv::Mat_<uchar> fgmask_;
}
mutable cv::Mat_<int> nfeatures_;
mutable cv::Mat_<int> colors_;
mutable cv::Mat_<float> weights_;
void BackgroundSubtractorGMG::PixelModelGMG::setLastObservedFeature(HistogramFeatureGMG f)
{
this->lastObservedFeature = f;
}
int maxFeatures_;
double learningRate_;
int numInitializationFrames_;
int quantizationLevels_;
double backgroundPrior_;
double decisionThreshold_;
bool updateBackgroundModel_;
double BackgroundSubtractorGMG::PixelModelGMG::getLikelihood(BackgroundSubtractorGMG::HistogramFeatureGMG f)
{
std::list<HistogramFeatureGMG>::iterator feature = histogram.begin();
std::list<HistogramFeatureGMG>::iterator feature_end = histogram.end();
double maxVal_;
double minVal_;
int frameNum_;
};
for (feature = histogram.begin(); feature != feature_end; ++feature)
void GMG_LoopBody::operator() (const cv::Range& range) const
{
// comparing only feature color, not likelihood. See equality operator for HistogramFeatureGMG
if (f == *feature)
typedef int (*func_t)(const void* src_, int x, double minVal, double maxVal, int quantizationLevels);
static const func_t funcs[6][4] =
{
return feature->likelihood;
}
}
{Quantization<uchar>::apply, 0, Quantization<cv::Vec3b>::apply, Quantization<cv::Vec4b>::apply},
{0,0,0,0},
{Quantization<ushort>::apply, 0, Quantization<cv::Vec3w>::apply, Quantization<cv::Vec4w>::apply},
{0,0,0,0},
{0,0,0,0},
{Quantization<float>::apply, 0, Quantization<cv::Vec3f>::apply, Quantization<cv::Vec4f>::apply},
};
return 0.0; // not in histogram, so return 0.
}
const func_t func = funcs[frame_.depth()][frame_.channels() - 1];
CV_Assert(func != 0);
void BackgroundSubtractorGMG::PixelModelGMG::insertFeature(double learningRate)
{
for (int y = range.start, featureIdx = y * frame_.cols; y < range.end; ++y)
{
const uchar* frame_row = frame_.ptr(y);
int* nfeatures_row = nfeatures_[y];
uchar* fgmask_row = fgmask_[y];
std::list<HistogramFeatureGMG>::iterator feature;
std::list<HistogramFeatureGMG>::iterator swap_end;
std::list<HistogramFeatureGMG>::iterator last_feature = histogram.end();
/*
* If feature is in histogram already, add the weights, and move feature to front.
* If there are too many features, remove the end feature and push new feature to beginning
*/
if (learningRate == -1.0) // then, this is a training-mode update.
for (int x = 0; x < frame_.cols; ++x, ++featureIdx)
{
/*
* (1) Check if feature already represented in histogram
*/
lastObservedFeature.likelihood = 1.0;
int nfeatures = nfeatures_row[x];
int* colors = colors_[featureIdx];
float* weights = weights_[featureIdx];
int newFeatureColor = func(frame_row, x, minVal_, maxVal_, quantizationLevels_);
for (feature = histogram.begin(); feature != last_feature; ++feature)
bool isForeground = false;
if (frameNum_ >= numInitializationFrames_)
{
if (lastObservedFeature == *feature) // feature in histogram
// typical operation
const double weight = findFeature(newFeatureColor, colors, weights, nfeatures);
// see Godbehere, Matsukawa, Goldberg (2012) for reasoning behind this implementation of Bayes rule
const double posterior = (weight * backgroundPrior_) / (weight * backgroundPrior_ + (1.0 - weight) * (1.0 - backgroundPrior_));
isForeground = ((1.0 - posterior) > decisionThreshold_);
// update histogram.
if (updateBackgroundModel_)
{
feature->likelihood += lastObservedFeature.likelihood;
// now, move feature to beginning of list and break the loop
HistogramFeatureGMG tomove = *feature;
histogram.erase(feature);
histogram.push_front(tomove);
return;
}
}
if (numFeatures == maxFeatures)
for (int i = 0; i < nfeatures; ++i)
weights[i] *= 1.0f - learningRate_;
bool inserted = insertFeature(newFeatureColor, learningRate_, colors, weights, nfeatures, maxFeatures_);
if (inserted)
{
histogram.pop_back(); // discard oldest feature
histogram.push_front(lastObservedFeature);
normalizeHistogram(weights, nfeatures);
nfeatures_row[x] = nfeatures;
}
else
{
histogram.push_front(lastObservedFeature);
++numFeatures;
}
}
else
else if (updateBackgroundModel_)
{
/*
* (1) Scale entire histogram by scaling factor
* (2) Scale input feature.
* (3) Check if feature already represented. If so, simply add.
* (4) If feature is not represented, remove old feature, distribute weight evenly among existing features, add in new feature.
*/
*this *= float(1.0-learningRate);
lastObservedFeature.likelihood = float(learningRate);
// training-mode update
for (feature = histogram.begin(); feature != last_feature; ++feature)
{
if (lastObservedFeature == *feature) // feature in histogram
{
lastObservedFeature.likelihood += feature->likelihood;
histogram.erase(feature);
histogram.push_front(lastObservedFeature);
return; // done with the update.
insertFeature(newFeatureColor, 1.0f, colors, weights, nfeatures, maxFeatures_);
if (frameNum_ == numInitializationFrames_ - 1)
normalizeHistogram(weights, nfeatures);
}
fgmask_row[x] = (uchar)(-isForeground);
}
if (numFeatures == maxFeatures)
{
histogram.pop_back(); // discard oldest feature
histogram.push_front(lastObservedFeature);
normalizeHistogram();
}
else
{
histogram.push_front(lastObservedFeature);
++numFeatures;
}
}
}
BackgroundSubtractorGMG::PixelModelGMG& BackgroundSubtractorGMG::PixelModelGMG::operator *=(const float &rhs)
void cv::BackgroundSubtractorGMG::operator ()(InputArray _frame, OutputArray _fgmask, double newLearningRate)
{
/*
* Used to scale histogram by a constant factor
*/
list<HistogramFeatureGMG>::iterator feature;
list<HistogramFeatureGMG>::iterator last_feature = histogram.end();
for (feature = histogram.begin(); feature != last_feature; ++feature)
{
feature->likelihood *= rhs;
}
return *this;
}
cv::Mat frame = _frame.getMat();
void BackgroundSubtractorGMG::PixelModelGMG::normalizeHistogram()
{
/*
* First, calculate the total weight in the histogram
*/
list<HistogramFeatureGMG>::iterator feature;
list<HistogramFeatureGMG>::iterator last_feature = histogram.end();
double total = 0.0;
for (feature = histogram.begin(); feature != last_feature; ++feature)
{
total += feature->likelihood;
}
CV_Assert(frame.depth() == CV_8U || frame.depth() == CV_16U || frame.depth() == CV_32F);
CV_Assert(frame.channels() == 1 || frame.channels() == 3 || frame.channels() == 4);
/*
* Then, if weight is not 0, divide every feature by the total likelihood to re-normalize.
*/
for (feature = histogram.begin(); feature != last_feature; ++feature)
if (newLearningRate != -1.0)
{
if (total != 0.0)
feature->likelihood = float(feature->likelihood / total);
CV_Assert(newLearningRate >= 0.0 && newLearningRate <= 1.0);
learningRate = newLearningRate;
}
}
bool BackgroundSubtractorGMG::HistogramFeatureGMG::operator ==(HistogramFeatureGMG &rhs)
{
CV_Assert(color.size() == rhs.color.size());
if (frame.size() != frameSize_)
initialize(frame.size(), 0.0, frame.depth() == CV_8U ? 255.0 : frame.depth() == CV_16U ? std::numeric_limits<ushort>::max() : 1.0);
std::vector<size_t>::iterator color_a;
std::vector<size_t>::iterator color_b;
std::vector<size_t>::iterator color_a_end = this->color.end();
for (color_a = color.begin(), color_b = rhs.color.begin(); color_a != color_a_end; ++color_a, ++color_b)
{
if (*color_a != *color_b)
_fgmask.create(frameSize_, CV_8UC1);
cv::Mat fgmask = _fgmask.getMat();
GMG_LoopBody body(frame, fgmask, nfeatures_, colors_, weights_,
maxFeatures, learningRate, numInitializationFrames, quantizationLevels, backgroundPrior, decisionThreshold,
maxVal_, minVal_, frameNum_, updateBackgroundModel);
cv::parallel_for_(cv::Range(0, frame.rows), body);
if (smoothingRadius > 0)
{
return false;
}
cv::medianBlur(fgmask, buf_, smoothingRadius);
cv::swap(fgmask, buf_);
}
return true;
// keep track of how many frames we have processed
++frameNum_;
}
void cv::BackgroundSubtractorGMG::release()
{
frameSize_ = cv::Size();
nfeatures_.release();
colors_.release();
weights_.release();
buf_.release();
}
modules/video/src/video_init.cpp
View file @ 79ef454c
......@@ -78,7 +78,9 @@ CV_INIT_ALGORITHM(BackgroundSubtractorGMG, "BackgroundSubtractor.GMG",
obj.info()->addParam(obj, "smoothingRadius", obj.smoothingRadius,false,0,0,
"Radius of smoothing kernel to filter noise from FG mask image.");
obj.info()->addParam(obj, "decisionThreshold", obj.decisionThreshold,false,0,0,
"Threshold for FG decision rule. Pixel is FG if posterior probability exceeds threshold."));
"Threshold for FG decision rule. Pixel is FG if posterior probability exceeds threshold.");
obj.info()->addParam(obj, "updateBackgroundModel", obj.updateBackgroundModel,false,0,0,
"Perform background model update."));
bool initModule_video(void)
{
......
modules/video/test/test_backgroundsubtractor_gbh.cpp
View file @ 79ef454c
......@@ -115,43 +115,43 @@ void CV_BackgroundSubtractorTest::run(int)
{
rng.fill(simImage,RNG::UNIFORM,(unsigned char)(minuc/2+maxuc/2),maxuc);
if (i == 0)
fgbg->initializeType(simImage,minuc,maxuc);
fgbg->initialize(simImage.size(),minuc,maxuc);
}
else if (type == CV_8S)
{
rng.fill(simImage,RNG::UNIFORM,(char)(minc/2+maxc/2),maxc);
if (i==0)
fgbg->initializeType(simImage,minc,maxc);
fgbg->initialize(simImage.size(),minc,maxc);
}
else if (type == CV_16U)
{
rng.fill(simImage,RNG::UNIFORM,(unsigned int)(minui/2+maxui/2),maxui);
if (i==0)
fgbg->initializeType(simImage,minui,maxui);
fgbg->initialize(simImage.size(),minui,maxui);
}
else if (type == CV_16S)
{
rng.fill(simImage,RNG::UNIFORM,(int)(mini/2+maxi/2),maxi);
if (i==0)
fgbg->initializeType(simImage,mini,maxi);
fgbg->initialize(simImage.size(),mini,maxi);
}
else if (type == CV_32F)
{
rng.fill(simImage,RNG::UNIFORM,(float)(minf/2.0+maxf/2.0),maxf);
if (i==0)
fgbg->initializeType(simImage,minf,maxf);
fgbg->initialize(simImage.size(),minf,maxf);
}
else if (type == CV_32S)
{
rng.fill(simImage,RNG::UNIFORM,(long int)(minli/2+maxli/2),maxli);
if (i==0)
fgbg->initializeType(simImage,minli,maxli);
fgbg->initialize(simImage.size(),minli,maxli);
}
else if (type == CV_64F)
{
rng.fill(simImage,RNG::UNIFORM,(double)(mind/2.0+maxd/2.0),maxd);
if (i==0)
fgbg->initializeType(simImage,mind,maxd);
fgbg->initialize(simImage.size(),mind,maxd);
}
/**
......@@ -159,7 +159,6 @@ void CV_BackgroundSubtractorTest::run(int)
*/
(*fgbg)(simImage,fgmask);
Mat fullbg = Mat::zeros(simImage.rows, simImage.cols, CV_8U);
fgbg->updateBackgroundModel(fullbg);
//! fgmask should be entirely background during training
code = cvtest::cmpEps2( ts, fgmask, fullbg, 0, false, "The training foreground mask" );
......
samples/cpp/bgfg_gmg.cpp
View file @ 79ef454c
......@@ -7,7 +7,6 @@
#include <opencv2/opencv.hpp>
#include <iostream>
#include <sstream>
using namespace cv;
......@@ -28,70 +27,56 @@ static void help()
int main(int argc, char** argv)
{
help();
initModule_video();
setUseOptimized(true);
setNumThreads(8);
Ptr<BackgroundSubtractorGMG> fgbg = Algorithm::create<BackgroundSubtractorGMG>("BackgroundSubtractor.GMG");
if (fgbg == NULL)
if (fgbg.empty())
{
CV_Error(CV_StsError,"Failed to create Algorithm\n");
std::cerr << "Failed to create BackgroundSubtractor.GMG Algorithm." << std::endl;
return -1;
}
fgbg->set("smoothingRadius",7);
fgbg->set("decisionThreshold",0.7);
fgbg->set("initializationFrames", 20);
fgbg->set("decisionThreshold", 0.7);
VideoCapture cap;
if( argc > 1 )
if (argc > 1)
cap.open(argv[1]);
else
cap.open(0);
if (!cap.isOpened())
{
std::cout << "error: cannot read video. Try moving video file to sample directory.\n";
std::cerr << "Cannot read video. Try moving video file to sample directory." << std::endl;
return -1;
}
Mat img, downimg, downimg2, fgmask, upfgmask, posterior, upposterior;
Mat frame, fgmask, segm;
namedWindow("FG Segmentation", WINDOW_NORMAL);
bool first = true;
namedWindow("posterior");
namedWindow("fgmask");
namedWindow("FG Segmentation");
int i = 0;
for (;;)
{
std::stringstream txt;
txt << "frame: ";
txt << i++;
cap >> frame;
cap >> img;
putText(img,txt.str(),Point(20,40),FONT_HERSHEY_SIMPLEX,0.8,Scalar(1.0,0.0,0.0));
if (frame.empty())
break;
(*fgbg)(frame, fgmask);
frame.copyTo(segm);
add(frame, Scalar(100, 100, 0), segm, fgmask);
imshow("FG Segmentation", segm);
resize(img,downimg,Size(160,120),0,0,INTER_NEAREST); // Size(cols, rows) or Size(width,height)
if (first)
{
fgbg->initializeType(downimg,0,255);
first = false;
}
if (img.empty())
{
return 0;
}
(*fgbg)(downimg,fgmask);
fgbg->updateBackgroundModel(Mat::zeros(120,160,CV_8U));
fgbg->getPosteriorImage(posterior);
resize(fgmask,upfgmask,Size(640,480),0,0,INTER_NEAREST);
Mat coloredFG = Mat::zeros(480,640,CV_8UC3);
coloredFG.setTo(Scalar(100,100,0),upfgmask);
resize(posterior,upposterior,Size(640,480),0,0,INTER_NEAREST);
imshow("posterior",upposterior);
imshow("fgmask",upfgmask);
resize(img, downimg2, Size(640, 480),0,0,INTER_LINEAR);
imshow("FG Segmentation",downimg2 + coloredFG);
int c = waitKey(30);
if( c == 'q' || c == 'Q' || (c & 255) == 27 )
if (c == 'q' || c == 'Q' || (c & 255) == 27)
break;
}
return 0;
}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment