1
0
mirror of https://github.com/opencv/opencv.git synced 2026-07-29 15:23:05 +04:00

Move objdetect HaarCascadeClassifier and HOGDescriptor to contrib xobjdetect (#25198)

* Move objdetect parts to contrib

* Move objdetect parts to contrib

* Minor fixes.
This commit is contained in:
WU Jia
2024-03-22 04:40:10 +08:00
committed by GitHub
parent 213e1a4d9d
commit aa5ea340f7
111 changed files with 22 additions and 741097 deletions
-352
View File
@@ -1,352 +0,0 @@
#include <iostream>
#include <fstream>
#include <string>
#include <sstream>
#include <iomanip>
#include <stdexcept>
#include <opencv2/core/ocl.hpp>
#include <opencv2/core/utility.hpp>
#include "opencv2/imgcodecs.hpp"
#include <opencv2/videoio.hpp>
#include <opencv2/highgui.hpp>
#include <opencv2/objdetect.hpp>
#include <opencv2/imgproc.hpp>
using namespace std;
using namespace cv;
class App
{
public:
App(CommandLineParser& cmd);
void run();
void handleKey(char key);
void hogWorkBegin();
void hogWorkEnd();
string hogWorkFps() const;
void workBegin();
void workEnd();
string workFps() const;
private:
App operator=(App&);
//Args args;
bool running;
bool make_gray;
double scale;
double resize_scale;
int win_width;
int win_stride_width, win_stride_height;
int gr_threshold;
int nlevels;
double hit_threshold;
bool gamma_corr;
int64 hog_work_begin;
double hog_work_fps;
int64 work_begin;
double work_fps;
string img_source;
string vdo_source;
string output;
int camera_id;
bool write_once;
};
int main(int argc, char** argv)
{
const char* keys =
"{ h help | | print help message }"
"{ i input | | specify input image}"
"{ c camera | -1 | enable camera capturing }"
"{ v video | vtest.avi | use video as input }"
"{ g gray | | convert image to gray one or not}"
"{ s scale | 1.0 | resize the image before detect}"
"{ o output | output.avi | specify output path when input is images}";
CommandLineParser cmd(argc, argv, keys);
if (cmd.has("help"))
{
cmd.printMessage();
return EXIT_SUCCESS;
}
App app(cmd);
try
{
app.run();
}
catch (const Exception& e)
{
return cout << "error: " << e.what() << endl, 1;
}
catch (const exception& e)
{
return cout << "error: " << e.what() << endl, 1;
}
catch(...)
{
return cout << "unknown exception" << endl, 1;
}
return EXIT_SUCCESS;
}
App::App(CommandLineParser& cmd)
{
cout << "\nControls:\n"
<< "\tESC - exit\n"
<< "\tm - change mode GPU <-> CPU\n"
<< "\tg - convert image to gray or not\n"
<< "\to - save output image once, or switch on/off video save\n"
<< "\t1/q - increase/decrease HOG scale\n"
<< "\t2/w - increase/decrease levels count\n"
<< "\t3/e - increase/decrease HOG group threshold\n"
<< "\t4/r - increase/decrease hit threshold\n"
<< endl;
make_gray = cmd.has("gray");
resize_scale = cmd.get<double>("s");
vdo_source = samples::findFileOrKeep(cmd.get<string>("v"));
img_source = cmd.get<string>("i");
output = cmd.get<string>("o");
camera_id = cmd.get<int>("c");
win_width = 48;
win_stride_width = 8;
win_stride_height = 8;
gr_threshold = 8;
nlevels = 13;
hit_threshold = 1.4;
scale = 1.05;
gamma_corr = true;
write_once = false;
cout << "Group threshold: " << gr_threshold << endl;
cout << "Levels number: " << nlevels << endl;
cout << "Win width: " << win_width << endl;
cout << "Win stride: (" << win_stride_width << ", " << win_stride_height << ")\n";
cout << "Hit threshold: " << hit_threshold << endl;
cout << "Gamma correction: " << gamma_corr << endl;
cout << endl;
}
void App::run()
{
running = true;
VideoWriter video_writer;
Size win_size(win_width, win_width * 2);
Size win_stride(win_stride_width, win_stride_height);
// Create HOG descriptors and detectors here
HOGDescriptor hog(win_size, Size(16, 16), Size(8, 8), Size(8, 8), 9, 1, -1,
HOGDescriptor::L2Hys, 0.2, gamma_corr, cv::HOGDescriptor::DEFAULT_NLEVELS);
hog.setSVMDetector( HOGDescriptor::getDaimlerPeopleDetector() );
while (running)
{
VideoCapture vc;
UMat frame;
if (vdo_source!="")
{
vc.open(vdo_source.c_str());
if (!vc.isOpened())
throw runtime_error(string("can't open video file: " + vdo_source));
vc >> frame;
}
else if (camera_id != -1)
{
vc.open(camera_id);
if (!vc.isOpened())
{
stringstream msg;
msg << "can't open camera: " << camera_id;
throw runtime_error(msg.str());
}
vc >> frame;
}
else
{
imread(img_source).copyTo(frame);
if (frame.empty())
throw runtime_error(string("can't open image file: " + img_source));
}
UMat img_aux, img, img_to_show;
// Iterate over all frames
while (running && !frame.empty())
{
workBegin();
// Change format of the image
if (make_gray) cvtColor(frame, img_aux, COLOR_BGR2GRAY );
else frame.copyTo(img_aux);
// Resize image
if (abs(scale-1.0)>0.001)
{
Size sz((int)((double)img_aux.cols/resize_scale), (int)((double)img_aux.rows/resize_scale));
resize(img_aux, img, sz, 0, 0, INTER_LINEAR_EXACT);
}
else img = img_aux;
img.copyTo(img_to_show);
hog.nlevels = nlevels;
vector<Rect> found;
// Perform HOG classification
hogWorkBegin();
hog.detectMultiScale(img, found, hit_threshold, win_stride,
Size(0, 0), scale, gr_threshold);
hogWorkEnd();
// Draw positive classified windows
for (size_t i = 0; i < found.size(); i++)
{
rectangle(img_to_show, found[i], Scalar(0, 255, 0), 3);
}
putText(img_to_show, ocl::useOpenCL() ? "Mode: OpenCL" : "Mode: CPU", Point(5, 25), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
putText(img_to_show, "FPS (HOG only): " + hogWorkFps(), Point(5, 65), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
putText(img_to_show, "FPS (total): " + workFps(), Point(5, 105), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
imshow("opencv_hog", img_to_show);
if (vdo_source!="" || camera_id!=-1) vc >> frame;
workEnd();
if (output!="" && write_once)
{
if (img_source!="") // write image
{
write_once = false;
imwrite(output, img_to_show);
}
else //write video
{
if (!video_writer.isOpened())
{
video_writer.open(output, VideoWriter::fourcc('x','v','i','d'), 24,
img_to_show.size(), true);
if (!video_writer.isOpened())
throw std::runtime_error("can't create video writer");
}
if (make_gray) cvtColor(img_to_show, img, COLOR_GRAY2BGR);
else cvtColor(img_to_show, img, COLOR_BGRA2BGR);
video_writer << img;
}
}
handleKey((char)waitKey(3));
}
}
}
void App::handleKey(char key)
{
switch (key)
{
case 27:
running = false;
break;
case 'm':
case 'M':
ocl::setUseOpenCL(!cv::ocl::useOpenCL());
cout << "Switched to " << (ocl::useOpenCL() ? "OpenCL enabled" : "CPU") << " mode\n";
break;
case 'g':
case 'G':
make_gray = !make_gray;
cout << "Convert image to gray: " << (make_gray ? "YES" : "NO") << endl;
break;
case '1':
scale *= 1.05;
cout << "Scale: " << scale << endl;
break;
case 'q':
case 'Q':
scale /= 1.05;
cout << "Scale: " << scale << endl;
break;
case '2':
nlevels++;
cout << "Levels number: " << nlevels << endl;
break;
case 'w':
case 'W':
nlevels = max(nlevels - 1, 1);
cout << "Levels number: " << nlevels << endl;
break;
case '3':
gr_threshold++;
cout << "Group threshold: " << gr_threshold << endl;
break;
case 'e':
case 'E':
gr_threshold = max(0, gr_threshold - 1);
cout << "Group threshold: " << gr_threshold << endl;
break;
case '4':
hit_threshold+=0.25;
cout << "Hit threshold: " << hit_threshold << endl;
break;
case 'r':
case 'R':
hit_threshold = max(0.0, hit_threshold - 0.25);
cout << "Hit threshold: " << hit_threshold << endl;
break;
case 'c':
case 'C':
gamma_corr = !gamma_corr;
cout << "Gamma correction: " << gamma_corr << endl;
break;
case 'o':
case 'O':
write_once = !write_once;
break;
}
}
inline void App::hogWorkBegin()
{
hog_work_begin = getTickCount();
}
inline void App::hogWorkEnd()
{
int64 delta = getTickCount() - hog_work_begin;
double freq = getTickFrequency();
hog_work_fps = freq / delta;
}
inline string App::hogWorkFps() const
{
stringstream ss;
ss << hog_work_fps;
return ss.str();
}
inline void App::workBegin()
{
work_begin = getTickCount();
}
inline void App::workEnd()
{
int64 delta = getTickCount() - work_begin;
double freq = getTickFrequency();
work_fps = freq / delta;
}
inline string App::workFps() const
{
stringstream ss;
ss << work_fps;
return ss.str();
}
-253
View File
@@ -1,253 +0,0 @@
#include "opencv2/objdetect.hpp"
#include "opencv2/highgui.hpp"
#include "opencv2/imgproc.hpp"
#include "opencv2/core/ocl.hpp"
#include <iostream>
using namespace std;
using namespace cv;
static void help()
{
cout << "\nThis program demonstrates the cascade recognizer. Now you can use Haar or LBP features.\n"
"This classifier can recognize many kinds of rigid objects, once the appropriate classifier is trained.\n"
"It's most known use is for faces.\n"
"Usage:\n"
"./ufacedetect [--cascade=<cascade_path> this is the primary trained classifier such as frontal face]\n"
" [--nested-cascade[=nested_cascade_path this an optional secondary classifier such as eyes]]\n"
" [--scale=<image scale greater or equal to 1, try 1.3 for example>]\n"
" [--try-flip]\n"
" [filename|camera_index]\n\n"
"see facedetect.cmd for one call:\n"
"./ufacedetect --cascade=\"../../data/haarcascades/haarcascade_frontalface_alt.xml\" --nested-cascade=\"../../data/haarcascades/haarcascade_eye_tree_eyeglasses.xml\" --scale=1.3\n\n"
"During execution:\n\tHit any key to quit.\n"
"\tUsing OpenCV version " << CV_VERSION << "\n" << endl;
}
void detectAndDraw( UMat& img, Mat& canvas, CascadeClassifier& cascade,
CascadeClassifier& nestedCascade,
double scale, bool tryflip );
int main( int argc, const char** argv )
{
VideoCapture capture;
UMat frame, image;
Mat canvas;
string inputName;
bool tryflip;
CascadeClassifier cascade, nestedCascade;
double scale;
cv::CommandLineParser parser(argc, argv,
"{cascade|data/haarcascades/haarcascade_frontalface_alt.xml|}"
"{nested-cascade|data/haarcascades/haarcascade_eye_tree_eyeglasses.xml|}"
"{help h ||}{scale|1|}{try-flip||}{@filename||}"
);
if (parser.has("help"))
{
help();
return 0;
}
string cascadeName = samples::findFile(parser.get<string>("cascade"));
string nestedCascadeName = samples::findFileOrKeep(parser.get<string>("nested-cascade"));
scale = parser.get<double>("scale");
tryflip = parser.has("try-flip");
inputName = parser.get<string>("@filename");
if ( !parser.check())
{
parser.printErrors();
help();
return -1;
}
if ( !nestedCascade.load( nestedCascadeName ) )
cerr << "WARNING: Could not load classifier cascade for nested objects: " << nestedCascadeName << endl;
if( !cascade.load( cascadeName ) )
{
cerr << "ERROR: Could not load classifier cascade: " << cascadeName << endl;
help();
return -1;
}
cout << "old cascade: " << (cascade.isOldFormatCascade() ? "TRUE" : "FALSE") << endl;
if( inputName.empty() || (isdigit(inputName[0]) && inputName.size() == 1) )
{
int camera = inputName.empty() ? 0 : inputName[0] - '0';
if(!capture.open(camera))
cout << "Capture from camera #" << camera << " didn't work" << endl;
}
else
{
inputName = samples::findFileOrKeep(inputName);
imread(inputName, IMREAD_COLOR).copyTo(image);
if( image.empty() )
{
if(!capture.open( inputName ))
cout << "Could not read " << inputName << endl;
}
}
if( capture.isOpened() )
{
cout << "Video capturing has been started ..." << endl;
for(;;)
{
capture >> frame;
if( frame.empty() )
break;
detectAndDraw( frame, canvas, cascade, nestedCascade, scale, tryflip );
char c = (char)waitKey(10);
if( c == 27 || c == 'q' || c == 'Q' )
break;
}
}
else
{
cout << "Detecting face(s) in " << inputName << endl;
if( !image.empty() )
{
detectAndDraw( image, canvas, cascade, nestedCascade, scale, tryflip );
waitKey(0);
}
else if( !inputName.empty() )
{
/* assume it is a text file containing the
list of the image filenames to be processed - one per line */
FILE* f = fopen( inputName.c_str(), "rt" );
if( f )
{
char buf[1000+1];
while( fgets( buf, 1000, f ) )
{
int len = (int)strlen(buf);
while( len > 0 && isspace(buf[len-1]) )
len--;
buf[len] = '\0';
cout << "file " << buf << endl;
imread(samples::findFile(buf), IMREAD_COLOR).copyTo(image);
if( !image.empty() )
{
detectAndDraw( image, canvas, cascade, nestedCascade, scale, tryflip );
char c = (char)waitKey(0);
if( c == 27 || c == 'q' || c == 'Q' )
break;
}
else
{
cerr << "Aw snap, couldn't read image " << buf << endl;
}
}
fclose(f);
}
}
}
return 0;
}
void detectAndDraw( UMat& img, Mat& canvas, CascadeClassifier& cascade,
CascadeClassifier& nestedCascade,
double scale, bool tryflip )
{
double t = 0;
vector<Rect> faces, faces2;
const static Scalar colors[] =
{
Scalar(255,0,0),
Scalar(255,128,0),
Scalar(255,255,0),
Scalar(0,255,0),
Scalar(0,128,255),
Scalar(0,255,255),
Scalar(0,0,255),
Scalar(255,0,255)
};
static UMat gray, smallImg;
t = (double)getTickCount();
cvtColor( img, gray, COLOR_BGR2GRAY );
double fx = 1 / scale;
resize( gray, smallImg, Size(), fx, fx, INTER_LINEAR_EXACT );
equalizeHist( smallImg, smallImg );
cascade.detectMultiScale( smallImg, faces,
1.1, 3, 0
//|CASCADE_FIND_BIGGEST_OBJECT
//|CASCADE_DO_ROUGH_SEARCH
|CASCADE_SCALE_IMAGE,
Size(30, 30) );
if( tryflip )
{
flip(smallImg, smallImg, 1);
cascade.detectMultiScale( smallImg, faces2,
1.1, 2, 0
//|CASCADE_FIND_BIGGEST_OBJECT
//|CASCADE_DO_ROUGH_SEARCH
|CASCADE_SCALE_IMAGE,
Size(30, 30) );
for( vector<Rect>::const_iterator r = faces2.begin(); r != faces2.end(); ++r )
{
faces.push_back(Rect(smallImg.cols - r->x - r->width, r->y, r->width, r->height));
}
}
t = (double)getTickCount() - t;
img.copyTo(canvas);
double fps = getTickFrequency()/t;
static double avgfps = 0;
static int nframes = 0;
nframes++;
double alpha = nframes > 50 ? 0.01 : 1./nframes;
avgfps = avgfps*(1-alpha) + fps*alpha;
putText(canvas, cv::format("OpenCL: %s, fps: %.1f", ocl::useOpenCL() ? "ON" : "OFF", avgfps), Point(50, 30),
FONT_HERSHEY_SIMPLEX, 0.8, Scalar(0,255,0), 2);
for ( size_t i = 0; i < faces.size(); i++ )
{
Rect r = faces[i];
vector<Rect> nestedObjects;
Point center;
Scalar color = colors[i%8];
int radius;
double aspect_ratio = (double)r.width/r.height;
if( 0.75 < aspect_ratio && aspect_ratio < 1.3 )
{
center.x = cvRound((r.x + r.width*0.5)*scale);
center.y = cvRound((r.y + r.height*0.5)*scale);
radius = cvRound((r.width + r.height)*0.25*scale);
circle( canvas, center, radius, color, 3, 8, 0 );
}
else
rectangle( canvas, Point(cvRound(r.x*scale), cvRound(r.y*scale)),
Point(cvRound((r.x + r.width-1)*scale), cvRound((r.y + r.height-1)*scale)),
color, 3, 8, 0);
if( nestedCascade.empty() )
continue;
UMat smallImgROI = smallImg(r);
nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
1.1, 2, 0
//|CASCADE_FIND_BIGGEST_OBJECT
//|CASCADE_DO_ROUGH_SEARCH
//|CASCADE_DO_CANNY_PRUNING
|CASCADE_SCALE_IMAGE,
Size(30, 30) );
for ( size_t j = 0; j < nestedObjects.size(); j++ )
{
Rect nr = nestedObjects[j];
center.x = cvRound((r.x + nr.x + nr.width*0.5)*scale);
center.y = cvRound((r.y + nr.y + nr.height*0.5)*scale);
radius = cvRound((nr.width + nr.height)*0.25*scale);
circle( canvas, center, radius, color, 3, 8, 0 );
}
}
imshow( "result", canvas );
}