#include <iostream>
#include <time.h>
vector< float > get_svm_detector(
const Ptr< SVM >& svm );
void convert_to_ml(
const std::vector< Mat > & train_samples,
Mat& trainData );
void load_images(
const String & dirname, vector< Mat > & img_lst,
bool showImages );
void sample_neg(
const vector< Mat > & full_neg_lst, vector< Mat > & neg_lst,
const Size &
size );
void computeHOGs(
const Size wsize,
const vector< Mat > & img_lst, vector< Mat > & gradient_lst,
bool use_flip );
void test_trained_detector(
String obj_det_filename,
String test_dir,
String videofilename );
vector< float > get_svm_detector(
const Ptr< SVM >& svm )
{
Mat sv = svm->getSupportVectors();
const int sv_total = sv.
rows;
double rho = svm->getDecisionFunction( 0, alpha, svidx );
vector< float > hog_detector( sv.
cols + 1 );
memcpy( &hog_detector[0], sv.
ptr(), sv.
cols*
sizeof( hog_detector[0] ) );
hog_detector[sv.
cols] = (float)-rho;
return hog_detector;
}
void convert_to_ml(
const vector< Mat > & train_samples,
Mat& trainData )
{
const int rows = (int)train_samples.size();
const int cols = (int)
std::max( train_samples[0].cols, train_samples[0].rows );
for( size_t i = 0 ; i < train_samples.size(); ++i )
{
CV_Assert( train_samples[i].cols == 1 || train_samples[i].rows == 1 );
if( train_samples[i].cols == 1 )
{
tmp.copyTo( trainData.
row( (
int)i ) );
}
else if( train_samples[i].rows == 1 )
{
train_samples[i].copyTo( trainData.
row( (
int)i ) );
}
}
}
void load_images(
const String & dirname, vector< Mat > & img_lst,
bool showImages =
false )
{
vector< String > files;
for ( size_t i = 0; i < files.size(); ++i )
{
{
cout << files[i] << " is invalid!" << endl;
continue;
}
if ( showImages )
{
}
img_lst.push_back( img );
}
}
void sample_neg(
const vector< Mat > & full_neg_lst, vector< Mat > & neg_lst,
const Size &
size )
{
srand( (unsigned int)time( NULL ) );
for ( size_t i = 0; i < full_neg_lst.size(); i++ )
if ( full_neg_lst[i].cols > box.
width && full_neg_lst[i].rows > box.
height )
{
box.
x = rand() % ( full_neg_lst[i].cols - box.
width );
box.
y = rand() % ( full_neg_lst[i].rows - box.
height );
Mat roi = full_neg_lst[i]( box );
}
}
void computeHOGs(
const Size wsize,
const vector< Mat > & img_lst, vector< Mat > & gradient_lst,
bool use_flip )
{
vector< float > descriptors;
for( size_t i = 0 ; i < img_lst.size(); i++ )
{
if ( img_lst[i].cols >= wsize.
width && img_lst[i].rows >= wsize.
height )
{
( img_lst[i].rows - wsize.
height ) / 2,
gradient_lst.push_back(
Mat( descriptors ).clone() );
if ( use_flip )
{
gradient_lst.push_back(
Mat( descriptors ).clone() );
}
}
}
}
void test_trained_detector(
String obj_det_filename,
String test_dir,
String videofilename )
{
cout << "Testing trained detector..." << endl;
hog.
load( obj_det_filename );
vector< String > files;
int delay = 0;
if ( videofilename != "" )
{
if ( videofilename.size() == 1 && isdigit( videofilename[0] ) )
cap.
open( videofilename[0] -
'0' );
else
cap.
open( videofilename );
}
obj_det_filename = "testing " + obj_det_filename;
for( size_t i=0;; i++ )
{
{
cap >> img;
delay = 1;
}
else if( i < files.size() )
{
}
{
return;
}
vector< Rect > detections;
vector< double > foundWeights;
for ( size_t j = 0; j < detections.size(); j++ )
{
Scalar color =
Scalar( 0, foundWeights[j] * foundWeights[j] * 200, 0 );
}
imshow( obj_det_filename, img );
{
return;
}
}
}
int main( int argc, char** argv )
{
const char* keys =
{
"{help h| | show help message}"
"{pd | | path of directory contains positive images}"
"{nd | | path of directory contains negative images}"
"{td | | path of directory contains test images}"
"{tv | | test video file name}"
"{dw | | width of the detector}"
"{dh | | height of the detector}"
"{f |false| indicates if the program will generate and use mirrored samples or not}"
"{d |false| train twice}"
"{t |false| test a trained detector}"
"{v |false| visualize training steps}"
"{fn |my_detector.yml| file name of trained SVM}"
};
if ( parser.has( "help" ) )
{
parser.printMessage();
exit( 0 );
}
int detector_width = parser.get< int >( "dw" );
int detector_height = parser.get< int >( "dh" );
bool test_detector = parser.get< bool >( "t" );
bool train_twice = parser.get< bool >( "d" );
bool visualization = parser.get< bool >( "v" );
bool flip_samples = parser.get< bool >( "f" );
if ( test_detector )
{
test_trained_detector( obj_det_filename, test_dir, videofilename );
exit( 0 );
}
if( pos_dir.empty() || neg_dir.empty() )
{
parser.printMessage();
cout << "Wrong number of parameters.\n\n"
<< "Example command line:\n" << argv[0] << " -dw=64 -dh=128 -pd=/INRIAPerson/96X160H96/Train/pos -nd=/INRIAPerson/neg -td=/INRIAPerson/Test/pos -fn=HOGpedestrian64x128.xml -d\n"
<< "\nExample command line for testing trained detector:\n" << argv[0] << " -t -fn=HOGpedestrian64x128.xml -td=/INRIAPerson/Test/pos";
exit( 1 );
}
vector< Mat > pos_lst, full_neg_lst, neg_lst, gradient_lst;
vector< int > labels;
clog << "Positive images are being loaded..." ;
load_images( pos_dir, pos_lst, visualization );
if ( pos_lst.size() > 0 )
{
clog << "...[done] " << pos_lst.size() << " files." << endl;
}
else
{
clog << "no image in " << pos_dir <<endl;
return 1;
}
Size pos_image_size = pos_lst[0].size();
if ( detector_width && detector_height )
{
pos_image_size =
Size( detector_width, detector_height );
}
else
{
for ( size_t i = 0; i < pos_lst.size(); ++i )
{
if( pos_lst[i].
size() != pos_image_size )
{
cout << "All positive images should be same size!" << endl;
exit( 1 );
}
}
pos_image_size = pos_image_size / 8 * 8;
}
clog << "Negative images are being loaded...";
load_images( neg_dir, full_neg_lst, visualization );
clog << "...[done] " << full_neg_lst.size() << " files." << endl;
clog << "Negative images are being processed...";
sample_neg( full_neg_lst, neg_lst, pos_image_size );
clog << "...[done] " << neg_lst.size() << " files." << endl;
clog << "Histogram of Gradients are being calculated for positive images...";
computeHOGs( pos_image_size, pos_lst, gradient_lst, flip_samples );
size_t positive_count = gradient_lst.size();
labels.assign( positive_count, +1 );
clog << "...[done] ( positive images count : " << positive_count << " )" << endl;
clog << "Histogram of Gradients are being calculated for negative images...";
computeHOGs( pos_image_size, neg_lst, gradient_lst, flip_samples );
size_t negative_count = gradient_lst.size() - positive_count;
labels.insert( labels.end(), negative_count, -1 );
clog << "...[done] ( negative images count : " << negative_count << " )" << endl;
convert_to_ml( gradient_lst, train_data );
clog << "Training SVM...";
svm->setCoef0( 0.0 );
svm->setDegree( 3 );
svm->setTermCriteria(
TermCriteria(TermCriteria::MAX_ITER + TermCriteria::EPS, 1000, 1e-3 ) );
svm->setGamma( 0 );
svm->setNu( 0.5 );
svm->setP( 0.1 );
svm->setC( 0.01 );
svm->setType( SVM::EPS_SVR );
clog << "...[done]" << endl;
if ( train_twice )
{
clog << "Testing trained detector on negative images. This might take a few minutes...";
vector< Rect > detections;
vector< double > foundWeights;
for ( size_t i = 0; i < full_neg_lst.size(); i++ )
{
if ( full_neg_lst[i].cols >= pos_image_size.
width && full_neg_lst[i].rows >= pos_image_size.
height )
else
detections.clear();
for ( size_t j = 0; j < detections.size(); j++ )
{
Mat detection = full_neg_lst[i]( detections[j] ).clone();
neg_lst.push_back( detection );
}
if ( visualization )
{
for ( size_t j = 0; j < detections.size(); j++ )
{
}
imshow(
"testing trained detector on negative images", full_neg_lst[i] );
}
}
clog << "...[done]" << endl;
gradient_lst.clear();
clog << "Histogram of Gradients are being calculated for positive images...";
computeHOGs( pos_image_size, pos_lst, gradient_lst, flip_samples );
positive_count = gradient_lst.size();
clog << "...[done] ( positive count : " << positive_count << " )" << endl;
clog << "Histogram of Gradients are being calculated for negative images...";
computeHOGs( pos_image_size, neg_lst, gradient_lst, flip_samples );
negative_count = gradient_lst.size() - positive_count;
clog << "...[done] ( negative count : " << negative_count << " )" << endl;
labels.clear();
labels.assign(positive_count, +1);
labels.insert(labels.end(), negative_count, -1);
clog << "Training SVM again...";
convert_to_ml( gradient_lst, train_data );
clog << "...[done]" << endl;
}
hog.
save( obj_det_filename );
test_trained_detector( obj_det_filename, test_dir, videofilename );
return 0;
}
Designed for command line parsing.
Definition: utility.hpp:818
n-dimensional dense array class
Definition: mat.hpp:811
CV_NODISCARD_STD Mat clone() const
Creates a full copy of the array and the underlying data.
Mat row(int y) const
Creates a matrix header for the specified matrix row.
uchar * ptr(int i0=0)
Returns a pointer to the specified matrix row.
_Tp & at(int i0=0)
Returns a reference to the specified array element.
int cols
Definition: mat.hpp:2116
size_t total() const
Returns the total number of array elements.
bool empty() const
Returns true if the array has no elements.
int rows
the number of rows and columns or (-1, -1) when the matrix has more than 2 dimensions
Definition: mat.hpp:2116
int type() const
Returns the type of a matrix element.
void push_back(const _Tp &elem)
Adds elements to the bottom of the matrix.
Template class for 2D rectangles.
Definition: types.hpp:439
_Tp x
x coordinate of the top-left corner
Definition: types.hpp:475
_Tp y
y coordinate of the top-left corner
Definition: types.hpp:476
_Tp width
width of the rectangle
Definition: types.hpp:477
_Tp height
height of the rectangle
Definition: types.hpp:478
Template class for specifying the size of an image or rectangle.
Definition: types.hpp:330
_Tp height
the height
Definition: types.hpp:358
_Tp width
the width
Definition: types.hpp:357
The class defining termination criteria for iterative algorithms.
Definition: types.hpp:875
Class for video capturing from video files, image sequences or cameras.
Definition: videoio.hpp:683
virtual bool open(const String &filename, int apiPreference=CAP_ANY)
Opens a video file or a capturing device or an IP video stream for video capturing.
virtual bool isOpened() const
Returns true if video capturing has been initialized already.
void transpose(InputArray src, OutputArray dst)
Transposes a matrix.
void flip(InputArray src, OutputArray dst, int flipCode)
Flips a 2D array around vertical, horizontal, or both axes.
void max(InputArray src1, InputArray src2, OutputArray dst)
Calculates per-element maximum of two arrays or an array and a scalar.
Rect2i Rect
Definition: types.hpp:484
std::string String
Definition: cvstd.hpp:152
Size2i Size
Definition: types.hpp:365
Scalar_< double > Scalar
Definition: types.hpp:691
std::shared_ptr< _Tp > Ptr
Definition: cvstd_wrapper.hpp:23
#define CV_64F
Definition: interface.h:79
#define CV_32FC1
Definition: interface.h:118
#define CV_32F
Definition: interface.h:78
#define CV_Assert(expr)
Checks a condition at runtime and throws exception if it fails.
Definition: base.hpp:342
void glob(String pattern, std::vector< String > &result, bool recursive=false)
@ LINEAR
linear (triangular) shape
Definition: types.hpp:55
@ WINDOW_NORMAL
the user can resize the window (no constraint) / also use to switch a fullscreen window to a normal s...
Definition: highgui.hpp:187
void imshow(const String &winname, InputArray mat)
Displays an image in the specified window.
int waitKey(int delay=0)
Waits for a pressed key.
void namedWindow(const String &winname, int flags=WINDOW_AUTOSIZE)
Creates a window.
CV_EXPORTS_W Mat imread(const String &filename, int flags=IMREAD_COLOR)
Loads an image from a file.
void cvtColor(InputArray src, OutputArray dst, int code, int dstCn=0)
Converts an image from one color space to another.
@ COLOR_BGR2GRAY
convert between RGB/BGR and grayscale, color conversions
Definition: imgproc.hpp:551
void rectangle(InputOutputArray img, Point pt1, Point pt2, const Scalar &color, int thickness=1, int lineType=LINE_8, int shift=0)
Draws a simple, thick, or filled up-right rectangle.
@ ROW_SAMPLE
each training sample is a row of samples
Definition: ml.hpp:98
GOpaque< Size > size(const GMat &src)
Gets dimensions from Mat.
"black box" representation of the file storage associated with a file on disk.
Definition: core.hpp:106
Implementation of HOG (Histogram of Oriented Gradients) descriptor and object detector.
Definition: objdetect.hpp:378
virtual void compute(InputArray img, std::vector< float > &descriptors, Size winStride=Size(), Size padding=Size(), const std::vector< Point > &locations=std::vector< Point >()) const
Computes HOG descriptors of given image.
virtual void save(const String &filename, const String &objname=String()) const
saves HOGDescriptor parameters and coefficients for the linear SVM classifier to a file
virtual void setSVMDetector(InputArray svmdetector)
Sets coefficients for the linear SVM classifier.
Size winSize
Detection window size. Align to block size and block stride. Default value is Size(64,...
Definition: objdetect.hpp:596
virtual bool load(const String &filename, const String &objname=String())
loads HOGDescriptor parameters and coefficients for the linear SVM classifier from a file
virtual void detectMultiScale(InputArray img, std::vector< Rect > &foundLocations, std::vector< double > &foundWeights, double hitThreshold=0, Size winStride=Size(), Size padding=Size(), double scale=1.05, double groupThreshold=2.0, bool useMeanshiftGrouping=false) const
Detects objects of different sizes in the input image. The detected objects are returned as a list of...