void InitUtils::initDetectors(CascadeClassifier &faceCascade, CascadeClassifier &eyeCascade1, CascadeClassifier &eyeCascade2, char *faceCascadeFilename, char *eyeCascadeFilename1, char *eyeCascadeFilename2)
{
// Load the Face Detection cascade classifier xml file.
try { // Surround the OpenCV call by a try/catch block so we can give a useful error message!
faceCascade.load(faceCascadeFilename);
} catch (cv::Exception &e) {}
if ( faceCascade.empty() ) {
AfxMessageBox("ERROR: Could not load Face Detection cascade classifier");
return;
}
// Load the Eye Detection cascade classifier xml file.
try { // Surround the OpenCV call by a try/catch block so we can give a useful error message!
eyeCascade1.load(eyeCascadeFilename1);
} catch (cv::Exception &e) {}
if ( eyeCascade1.empty() ) {
AfxMessageBox("ERROR: Could not load 1st Eye Detection cascade classifier");
return;
}
// Load the Eye Detection cascade classifier xml file.
try { // Surround the OpenCV call by a try/catch block so we can give a useful error message!
eyeCascade2.load(eyeCascadeFilename2);
} catch (cv::Exception &e) {}
if ( eyeCascade2.empty() ) {
AfxMessageBox("ERROR: Could not load 2st Eye Detection cascade classifier");
return;
}
}
bool loocvTest(const char* trained_model_fname,int model_type,const char* fname,int label)
{
if(face_cascade.empty())
initFaceCascade();
Ptr<FaceRecognizer> model=g_trainer.load(trained_model_fname,model_type);
if(model.empty())
{
printf("Fail to load trained model, please re-train the model\n");
return false;
}
Mat frame=imread(fname,CV_LOAD_IMAGE_GRAYSCALE);
if(frame.empty())
{
printf("Fail to load loocv file\n");
return false;
}
int predictLabel=-1;
double confidence=0.;
predictLabel=model->predict(frame);
string class_name=g_trainer.label(predictLabel);
printf("predict: %s\n",class_name.c_str());
return (predictLabel==label);
}
// Function main
int main(int argc, const char** argv )
{
// Load the cascade
CascadeClassifier faceDetector;
string inputimg = argv[1];
string outputimg = argv[2];
try {
faceDetector.load(faceCascadeFilename);
} catch (cv::Exception e) {}
if ( faceDetector.empty() ) {
cerr << "ERROR: Couldn't load Face Detector (";
cerr << faceCascadeFilename << ")!" << endl;
exit(1);
}
// Read the image file
Mat img = imread(inputimg , CV_LOAD_IMAGE_COLOR);
//imshow("Original", img);
// Apply the classifier to the frame
if (!img.empty()){
detectAndDisplay(img, faceDetector, outputimg);
}
else{
printf(" --(!) No captured frame -- Break!");
}
waitKey(0);
return 0;
}
void detectAndDraw( Mat& img,
CascadeClassifier& cascade, CascadeClassifier& nestedCascade,
double scale)
{
int i = 0;
double t = 0;
vector<Rect> faces;
const static Scalar colors[] = { CV_RGB(255,0,0),
// CV_RGB(0,128,255),
// CV_RGB(0,255,255),
// CV_RGB(0,255,0),
// CV_RGB(255,128,0),
// CV_RGB(255,255,0),
// CV_RGB(255,0,0),
// CV_RGB(255,0,255)
} ;
Mat gray, smallImg( cvRound (img.rows/scale), cvRound(img.cols/scale), CV_8UC1 );
cvtColor( img, gray, CV_BGR2GRAY );
resize( gray, smallImg, smallImg.size(), 0, 0, INTER_LINEAR );
equalizeHist( smallImg, smallImg );
t = (double)cvGetTickCount();
cascade.detectMultiScale( smallImg, faces,
1.1, 2, 0
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
t = (double)cvGetTickCount() - t;
printf( "detection time = %g ms\n", t/((double)cvGetTickFrequency()*1000.) );
for( vector<Rect>::const_iterator r = faces.begin(); r != faces.end(); r++, i++ )
{
Mat smallImgROI;
vector<Rect> nestedObjects;
Point center;
Scalar color = colors[i%8];
int radius;
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( img, center, radius, color, 3, 8, 0 );
if( nestedCascade.empty() )
continue;
smallImgROI = smallImg(*r);
nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
1.1, 2, 0
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
for( vector<Rect>::const_iterator nr = nestedObjects.begin(); nr != nestedObjects.end(); nr++ )
{
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( img, center, radius, color, 3, 8, 0 );
}
}
cv::imshow( "result", img );
}
void doCapture(const char* trained_model_fname,int model_type)
{
if(doing_capture) return;
if(face_cascade.empty())
initFaceCascade();
Ptr<FaceRecognizer> model=g_trainer.load(trained_model_fname,model_type);
if(model.empty())
{
printf("Fail to load trained model, please re-train the model\n");
return;
}
frame_cnt=0;
doing_capture=true;
printf("Start capturing, press Q to stop\n");
CvCapture* capture=0;
Mat frame;
capture = cvCaptureFromCAM( 0 );
if( capture )
{
while( true )
{
//double t = (double)cvGetTickCount();
frame = cvQueryFrame( capture );
if( !frame.empty() )
{
detectAndRecognize(frame,model);
}
else
{ printf(" --(!) No captured frame -- Break!"); break; }
//t = (double)cvGetTickCount() - t;printf( "time = %g ms\n", t/((double)cvGetTickFrequency()*1000.) );
int c = waitKey(10);
if( (char)c == 'q' ) { break; }
++frame_cnt;
}
cvReleaseCapture(&capture);
}
else
{
printf("Fail to access the Camera\n");
}
cvDestroyWindow(CAPTURE_WND_NAME);
doing_capture=false;
}
static CascadeClassifier *
gst_face_blur_load_profile (GstFaceBlur * filter, gchar * profile)
{
CascadeClassifier *cascade;
cascade = new CascadeClassifier (profile);
if (cascade->empty ()) {
GST_ERROR_OBJECT (filter, "Invalid profile file: %s", profile);
delete cascade;
return NULL;
}
return cascade;
}
static void loadFaceDetector( CascadeClassifier &faceDetector, QString path )
{
try {
faceDetector.load( path.toLocal8Bit().data() );
} catch( cv::Exception e ) {}
if( faceDetector.empty() ) {
std::cerr<< "ERROR:counldn't load face detector";
exit(1);
}
}
static int
kms_face_detect_init_cascade()
{
if (!cascade.load(HAAR_CONF_FILE))
{
fprintf(stderr,"Error charging cascade");
return -1;
}
if (cascade.empty())
fprintf(stderr,"****CASCADE IS EMPTY***********");
return 0;
}
// Load the face and 1 or 2 eye detection XML classifiers.
void initDetectors(CascadeClassifier &faceCascade,
CascadeClassifier &eyeCascade1, CascadeClassifier &eyeCascade2)
{
// Load the Face Detection cascade classifier xml file.
try { // Surround the OpenCV call by a try/catch block so we can give a useful error message!
faceCascade.load(faceCascadeFilename);
} catch (cv::Exception &e) {}
if ( faceCascade.empty() ) {
cerr << "ERROR: Could not load Face Detection cascade classifier [" << faceCascadeFilename << "]!" << endl;
cerr << "Copy the file from your OpenCV data folder (eg: '/usr/local/opencv/share/lbpcascades') into this WebcamFaceRec folder." << endl;
exit(1);
}
cout << "Loaded the Face Detection cascade classifier [" << faceCascadeFilename << "]." << endl;
// Load the Eye Detection cascade classifier xml file.
try { // Surround the OpenCV call by a try/catch block so we can give a useful error message!
eyeCascade1.load(eyeCascadeFilename1);
} catch (cv::Exception &e) {}
if ( eyeCascade1.empty() ) {
cerr << "ERROR: Could not load 1st Eye Detection cascade classifier [" << eyeCascadeFilename1 << "]!" << endl;
cerr << "Copy the file from your OpenCV data folder (eg: '/usr/local/opencv/share/haarcascades') into this WebcamFaceRec folder." << endl;
exit(1);
}
cout << "Loaded the 1st Eye Detection cascade classifier [" << eyeCascadeFilename1 << "]." << endl;
// Load the Eye Detection cascade classifier xml file.
try { // Surround the OpenCV call by a try/catch block so we can give a useful error message!
eyeCascade2.load(eyeCascadeFilename2);
} catch (cv::Exception &e) {}
if ( eyeCascade2.empty() ) {
cerr << "Could not load 2nd Eye Detection cascade classifier [" << eyeCascadeFilename2 << "]." << endl;
// Dont exit if the 2nd eye detector did not load, because we have the 1st eye detector at least.
//exit(1);
}
else
cout << "Loaded the 2nd Eye Detection cascade classifier [" << eyeCascadeFilename2 << "]." << endl;
}
JNIEXPORT jboolean JNICALL Java_org_opencv_objdetect_CascadeClassifier_empty_10
(JNIEnv* env, jclass , jlong self)
{
static const char method_name[] = "objdetect::empty_10()";
try {
LOGD("%s", method_name);
CascadeClassifier* me = (CascadeClassifier*) self; //TODO: check for NULL
bool _retval_ = me->empty( );
return _retval_;
} catch(const std::exception &e) {
throwJavaException(env, &e, method_name);
} catch (...) {
throwJavaException(env, 0, method_name);
}
return 0;
}
int main (int argc, char ** argv)
{
// read params from stdin
param par = zpracujParametry(argc, argv);
// load LP cascade detector (.xml file)
CascadeClassifier cascade;
cascade.load(par.detector);
if (cascade.empty()){
cout << "Could not load cascade classifier" << endl;
exit(1);
}
// process image or dataset of images
if (!par.inputList.empty())
processList(par, cascade);
return 0;
}
/*
* In this function it is possible to initialize the variables.
* For example, we set edge_value to 125 and the filter type to
* edge filter. This values can be changed via set_properties
*/
static void
kms_eye_detect_init (KmsEyeDetect *
eye_detect)
{
int ret=0;
eye_detect->priv = KMS_EYE_DETECT_GET_PRIVATE (eye_detect);
eye_detect->priv->img_width = 320;
eye_detect->priv->img_height = 240;
eye_detect->priv->img_orig = NULL;
eye_detect->priv->scale_o2f=1.0;
eye_detect->priv->scale_o2e=1.0;
eye_detect->priv->view_eyes=0;
eye_detect->priv->events_queue= g_queue_new();
eye_detect->priv->detect_event=0;
eye_detect->priv->meta_data=0;
eye_detect->priv->faces= new vector<Rect>;
eye_detect->priv->eyes_l= new vector<Rect>;
eye_detect->priv->eyes_r= new vector<Rect>;
eye_detect->priv->num_frames_to_process=0;
eye_detect->priv->frames_with_no_detection_el=0;
eye_detect->priv->frames_with_no_detection_er=0;
eye_detect->priv->process_x_every_4_frames=PROCESS_ALL_FRAMES;
eye_detect->priv->num_frame=0;
eye_detect->priv->scale_factor=DEFAULT_SCALE_FACTOR;
eye_detect->priv->width_to_process=EYE_WIDTH;
eye_detect->priv->server_events =SERVER_EVENTS;
eye_detect->priv->events_ms =EVENTS_MS;
if (fcascade.empty())
if (kms_eye_detect_init_cascade() < 0)
std::cout << "Error: init cascade" << std::endl;
if (ret != 0)
GST_DEBUG ("Error reading the haar cascade configuration file");
g_rec_mutex_init(&eye_detect->priv->mutex);
}
/*
* In this function it is possible to initialize the variables.
* For example, we set edge_value to 125 and the filter type to
* edge filter. This values can be changed via set_properties
*/
static void
kms_face_detect_init (KmsFaceDetect *
face_detect)
{
int ret=0;
face_detect->priv = KMS_FACE_DETECT_GET_PRIVATE (face_detect);
face_detect->priv->scale=1.0;
face_detect->priv->img_width = DEFAULT_WIDTH;
face_detect->priv->img_height = DEFAULT_HEIGHT;
face_detect->priv->img_orig = NULL;
face_detect->priv->events_queue= g_queue_new();
face_detect->priv->detect_event=0;
face_detect->priv->meta_data=0;
face_detect->priv->faces_detected= new vector<Rect>;
face_detect->priv->num_frames_to_process=0;
face_detect->priv->process_x_every_4_frames=PROCESS_ALL_FRAMES;
face_detect->priv->num_frame=0;
face_detect->priv->width_to_process=DEFAULT_WIDTH;
face_detect->priv->scale_factor=DEFAULT_SCALE_FACTOR;
face_detect->priv->cv_mem_storage=cvCreateMemStorage(0);
face_detect->priv->face_seq =cvCreateSeq (0, sizeof (CvSeq), sizeof (CvRect),
face_detect->priv->cv_mem_storage);
face_detect->priv->show_faces = 0;
if (cascade.empty())
if (kms_face_detect_init_cascade() < 0)
std::cout << "Error: init cascade" << std::endl;
face_detect->priv->cascade = & cascade;
if (ret != 0)
GST_DEBUG ("Error reading the haar cascade configuration file");
g_rec_mutex_init(&face_detect->priv->mutex);
}
/*
* In this function it is possible to initialize the variables.
* For example, we set edge_value to 125 and the filter type to
* edge filter. This values can be changed via set_properties
*/
static void
kms_mouth_detect_init (KmsMouthDetect *
mouth_detect)
{
std::cout << "En mouth detect init" << std::endl;
int ret=0;
mouth_detect->priv = KMS_MOUTH_DETECT_GET_PRIVATE (mouth_detect);
mouth_detect->priv->scale_f2m=1.0;
mouth_detect->priv->scale_m2o=1.0;
mouth_detect->priv->scale_o2f=1.0;
mouth_detect->priv->img_width = 320;
mouth_detect->priv->img_height = 240;
mouth_detect->priv->img_orig = NULL;
mouth_detect->priv->view_mouths=0;
mouth_detect->priv->events_queue= g_queue_new();
mouth_detect->priv->detect_event=0;
mouth_detect->priv->meta_data=0;
mouth_detect->priv->faces= new vector<Rect>;
mouth_detect->priv->mouths= new vector<Rect>;
mouth_detect->priv->num_frames_to_process=0;
mouth_detect->priv->process_x_every_4_frames=PROCESS_ALL_FRAMES;
mouth_detect->priv->num_frame=0;
mouth_detect->priv->scale_factor=DEFAULT_SCALE_FACTOR;
mouth_detect->priv->width_to_process=MOUTH_WIDTH;
if (fcascade.empty())
if (kms_mouth_detect_init_cascade() < 0)
std::cout << "Error: init cascade" << std::endl;
if (ret != 0)
GST_DEBUG ("Error reading the haar cascade configuration file");
g_rec_mutex_init(&mouth_detect->priv->mutex);
std::cout << "En mouth detect init END" << std::endl;
}
/*
* In this function it is possible to initialize the variables.
* For example, we set edge_value to 125 and the filter type to
* edge filter. This values can be changed via set_properties
*/
static void
kms_ear_detect_init (KmsEarDetect *
ear_detect)
{
int ret=0;
ear_detect->priv = KMS_EAR_DETECT_GET_PRIVATE (ear_detect);
ear_detect->priv->scale_f2e=1.0;
ear_detect->priv->scale_e2o=1.0;
ear_detect->priv->scale_f2o=1.0;
ear_detect->priv->img_width = 320;
ear_detect->priv->img_height = 240;
ear_detect->priv->img_orig = NULL;
ear_detect->priv->view_ears=-1;
ear_detect->priv->show_faces=1;
ear_detect->priv->discard=1;
ear_detect->priv->faces= new vector<Rect>;
ear_detect->priv->ears= new vector<Rect>;
ear_detect->priv->rear= new vector<Rect>;
ear_detect->priv->lear= new vector<Rect>;
ear_detect->priv->num_frames_to_process=0;
ear_detect->priv->process_x_every_4_frames=PROCESS_ALL_FRAMES;
ear_detect->priv->num_frame=0;
ear_detect->priv->scale_factor=DEFAULT_SCALE_FACTOR;
ear_detect->priv->width_to_process=EAR_WIDTH;
ear_detect->priv->frames_with_no_detection=0;
if (fcascade.empty())
if (kms_ear_detect_init_cascade() < 0)
GST_DEBUG("Error: init cascade");
if (ret != 0)
GST_DEBUG ("Error reading the haar cascade configuration file");
g_rec_mutex_init(&ear_detect->priv->mutex);
}
bool detectAndNormalize(Mat frame,Mat& res,int action=0)
{
if(face_cascade.empty())
initFaceCascade();
res=frame;
if( !frame.empty() )
{
std::vector<Rect> faces;
Mat frame_gray;
cvtColor( frame, frame_gray, CV_BGR2GRAY );
//equalizeHist( frame_gray, frame_gray );
face_cascade.detectMultiScale( frame_gray, faces, 1.1, 2, 0|CV_HAAR_SCALE_IMAGE, Size(30, 30) );
if(faces.size()==0)
{
return false;
}
// first face
Mat faceROI = frame( faces[0] ); // rgb
cv::resize(faceROI,faceROI,cv::Size(NORM_IMG_WIDTH,NORM_IMG_HEIGHT));
res=faceROI;
if(action>=ENorm_Gray)
cvtColor( res, res, CV_BGR2GRAY );
if(action>ENorm_Equalize)
equalizeHist( res, res );
return true;
}
return false;
}
/*
* In this function it is possible to initialize the variables.
* For example, we set edge_value to 125 and the filter type to
* edge filter. This values can be changed via set_properties
*/
static void
kms_nose_detect_init (KmsNoseDetect *
nose_detect)
{
int ret=0;
nose_detect->priv = KMS_NOSE_DETECT_GET_PRIVATE (nose_detect);
nose_detect->priv->img_width = 320;
nose_detect->priv->img_height = 240;
nose_detect->priv->img_orig = NULL;
nose_detect->priv->scale_f2n=1.0;
nose_detect->priv->scale_n2o=1.0;
nose_detect->priv->scale_o2f=1.0;
nose_detect->priv->view_noses=0;
nose_detect->priv->events_queue= g_queue_new();
nose_detect->priv->detect_event=0;
nose_detect->priv->meta_data=0;
nose_detect->priv->faces= new vector<Rect>;
nose_detect->priv->noses= new vector<Rect>;
nose_detect->priv->num_frames_to_process=0;
nose_detect->priv->process_x_every_4_frames=PROCESS_ALL_FRAMES;
nose_detect->priv->num_frame=0;
nose_detect->priv->width_to_process=NOSE_WIDTH;
nose_detect->priv->scale_factor=DEFAULT_SCALE_FACTOR;
if (fcascade.empty())
if (kms_nose_detect_init_cascade() < 0)
std::cout << "Error: init cascade" << std::endl;
if (ret != 0)
GST_DEBUG ("Error reading the haar cascade configuration file");
g_rec_mutex_init(&nose_detect->priv->mutex);
}
int main(int argc, char** argv)
{
OpenNI2Grabber grabber;
bool isRunning = false;
const int timeoutMs = 1000;
//1.0 api version
Mat frame, frame_copy, image_size;
vector<Rect> faces;
vector< vector<Point> > contours;
cascade.load(cascade_name);
if( cascade.empty() ) {
fprintf( stderr, "ERROR: Could not load classifier cascade\n" );
return -1;
}
// attempt to start the grabber
if(grabber.initialize())
{
if(grabber.start())
{
isRunning = grabber.isRunning();
}
}
else
{
std::cout << "Unable to initialize OpenNI2Grabber, program terminating!" << std::endl;
return 0;
}
// acquire frames until program termination
std::cout << "Press 'q' to halt acquisition..." << std::endl;
Mat depthImage, colorImage;
Mat depthImageDraw;
Mat depthImage8U;
int flag = -1;
ofstream myfile;
myfile.open ("direction.txt");
while(isRunning)
{
// wait for a new image frame
if(grabber.waitForFrame(timeoutMs))
{
// update the display for both frames
if(grabber.getDepthFrame(depthImage) && grabber.getColorFrame(colorImage))
{
depthImage.convertTo(depthImageDraw, -1, 32);
depthImageDraw.convertTo(depthImageDraw, CV_8UC1, 1.0/256.0);
imshow("8", depthImageDraw);
threshold(depthImageDraw,depthImageDraw,190, 255,4);
medianBlur(depthImageDraw,depthImageDraw,5);
threshold(depthImageDraw,depthImageDraw,95, 255,3);
imshow("trun2", depthImageDraw);
findContours(depthImageDraw,contours,CV_RETR_EXTERNAL,CV_CHAIN_APPROX_NONE);
drawContours(colorImage,contours,-1,Scalar(0,0,255),2);
/// Get the moments
vector<Moments> mu(contours.size() );
vector<Point2f> mc( contours.size() );
vector<float> oldX( contours.size() );
vector<float> oldY( contours.size() );
for( int i = 0; i < contours.size(); i++ )
{
if(contourArea(contours[i])<5500 && contourArea(contours[i])>1000) {
mu[i] = moments( contours[i], false );
mc[i] = Point2f( mu[i].m10/mu[i].m00 , mu[i].m01/mu[i].m00 );
circle( colorImage, mc[i], 4, Scalar(0,255,0), -1, 8, 0 );
newpoint[1] = mc[i].x;
newpoint[2] = mc[i].y;
difference[1] = newpoint[1]-oldpoint[1];
difference[2] = newpoint[2]-oldpoint[2];
if (difference[1] < -diff_threshold_rl)
{
cout << "RIGHT TO LEFT RRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRRR \n";
}
else if (difference[1] > diff_threshold_rl)
{
cout << "LEFT TO RIGHT LLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLL\n";
}
else if (difference[2] < -diff_threshold_tb)
{
cout << "TOP TO BOTTOM TTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTTT\n";
}
else if (difference[2] > diff_threshold_tb)
{
cout << "BOTTOM TO TOP BBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBBB\n";
}
oldpoint[1] = newpoint[1];
oldpoint[2] = newpoint[2];
}
}
imshow("rgb", colorImage);
}
}
else
{
std::cout << "No new frames received in " << timeoutMs << " ms..." << std::endl;
}
// check for program termination
char key = (char) cv::waitKey(1);
if(key == 'q' || key == 'Q')
{
std::cout << "Terminating program..." << std::endl;
isRunning = false;
}
// check for Blob
char key2 = (char) cv::waitKey(1);
if(key2 == 'b' || key2 == 'B')
{
std::cout << "Checking for blobs" << std::endl;
}
}
// stop the acquisition
grabber.stop();
myfile.close();
return 0;
}
void detectAndDraw( Mat& img, CascadeClassifier& cascade,
CascadeClassifier& nestedCascade,
double scale, bool tryflip )
{
int i = 0;
double t = 0;
vector<Rect> faces, faces2;
CascadeClassifier nosecascade, mouthcascade;
const static Scalar colors[] = { CV_RGB(0,0,255),
CV_RGB(0,128,255),
CV_RGB(0,255,255),
CV_RGB(0,255,0),
CV_RGB(255,128,0),
CV_RGB(255,255,0),
CV_RGB(255,0,0),
CV_RGB(255,0,255)} ;
Mat gray, smallImg( cvRound (img.rows/scale), cvRound(img.cols/scale), CV_8UC1 );
cvtColor( img, gray, CV_BGR2GRAY );
resize( gray, smallImg, smallImg.size(), 0, 0, INTER_LINEAR );
equalizeHist( smallImg, smallImg );
t = (double)cvGetTickCount();
cascade.detectMultiScale( smallImg, faces,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
if( tryflip )
{
flip(smallImg, smallImg, 1);
cascade.detectMultiScale( smallImg, faces2,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
|CV_HAAR_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)cvGetTickCount() - t;
printf( "detection time = %g ms\n", t/((double)cvGetTickFrequency()*1000.) );
if( !nosecascade.load( "haarcascade_mcs_mouth.xml" ) )
{
cerr << "ERROR: Could not load classifier cascade" << endl;
}
if( !nosecascade.load( "haarcascade_mcs_nose.xml" ) )
{
cerr << "ERROR: Could not load classifier cascade" << endl;
}
for( vector<Rect>::const_iterator r = faces.begin(); r != faces.end(); r++, i++ )
{
Mat smallImgROI;
vector<Rect> nestedObjects, noseObjects, mouthObjects;
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( img, center, radius, colors[0], 3, 8, 0 );
}
else
rectangle( img, cvPoint(cvRound(r->x*scale), cvRound(r->y*scale)),
cvPoint(cvRound((r->x + r->width-1)*scale), cvRound((r->y + r->height-1)*scale)),
colors[0], 3, 8, 0);
if( nestedCascade.empty() )
continue;
smallImgROI = smallImg(*r);
nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
//|CV_HAAR_DO_CANNY_PRUNING
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
for( vector<Rect>::const_iterator nr = nestedObjects.begin(); nr != nestedObjects.end(); nr++ )
{
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( img, center, radius, colors[1], 3, 8, 0 );
}
nosecascade.detectMultiScale( smallImgROI, noseObjects,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
//|CV_HAAR_DO_CANNY_PRUNING
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
for( vector<Rect>::const_iterator nr = noseObjects.begin(); nr != noseObjects.end(); nr++ )
{
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( img, center, radius, colors[2], 3, 8, 0 );
}
mouthcascade.detectMultiScale( smallImgROI, mouthObjects,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
//|CV_HAAR_DO_CANNY_PRUNING
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
for( vector<Rect>::const_iterator nr = mouthObjects.begin(); nr != mouthObjects.end(); nr++ )
{
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( img, center, radius, colors[3], 3, 8, 0 );
}
}
cv::imshow( "result", img );
}
void detectAndDraw( Mat& img, CascadeClassifier& cascade,
CascadeClassifier& nestedCascade,
double scale, bool tryflip )
{
int i = 0;
double t = 0;
//建立用于存放人脸的向量容器
vector<Rect> faces, faces2;
//定义一些颜色，用来标示不同的人脸
const static Scalar colors[] = { CV_RGB(0,0,255),
CV_RGB(0,128,255),
CV_RGB(0,255,255),
CV_RGB(0,255,0),
CV_RGB(255,128,0),
CV_RGB(255,255,0),
CV_RGB(255,0,0),
CV_RGB(255,0,255)} ;
//建立缩小的图片，加快检测速度
//nt cvRound (double value) 对一个double型的数进行四舍五入，并返回一个整型数！
Mat gray, smallImg( cvRound (img.rows/scale), cvRound(img.cols/scale), CV_8UC1 );
//转成灰度图像，Harr特征基于灰度图
cvtColor( img, gray, CV_BGR2GRAY );
//改变图像大小，使用双线性差值
resize( gray, smallImg, smallImg.size(), 0, 0, INTER_LINEAR );
//变换后的图像进行直方图均值化处理
equalizeHist( smallImg, smallImg );
//程序开始和结束插入此函数获取时间，经过计算求得算法执行时间
t = (double)cvGetTickCount();
//检测人脸
//detectMultiScale函数中smallImg表示的是要检测的输入图像为smallImg，faces表示检测到的人脸目标序列，1.1表示
//每次图像尺寸减小的比例为1.1，2表示每一个目标至少要被检测到3次才算是真的目标(因为周围的像素和不同的窗口大
//小都可以检测到人脸),CV_HAAR_SCALE_IMAGE表示不是缩放分类器来检测，而是缩放图像，Size(30, 30)为目标的
//最小最大尺寸
cascade.detectMultiScale( smallImg, faces,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30));
//如果使能，翻转图像继续检测
if( tryflip )
{
flip(smallImg, smallImg, 1);
cascade.detectMultiScale( smallImg, faces2,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
|CV_HAAR_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)cvGetTickCount() - t;
// qDebug( "detection time = %g ms\n", t/((double)cvGetTickFrequency()*1000.) );
int xPoint = 0;
int yPoint = 0;
for( vector<Rect>::const_iterator r = faces.begin(); r != faces.end(); r++, i++ )
{
Mat smallImgROI;
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 )
{
//标示人脸时在缩小之前的图像上标示，所以这里根据缩放比例换算回去
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( img, center, radius, color, 3, 8, 0 );
}
else
rectangle( img, cvPoint(cvRound(r->x*scale), cvRound(r->y*scale)),
cvPoint(cvRound((r->x + r->width-1)*scale), cvRound((r->y + r->height-1)*scale)),
color, 3, 8, 0);
if (r == faces.begin())
{
xPoint = 320-(center.x);
yPoint = 240-(center.y);
}
if( nestedCascade.empty() )
continue;
smallImgROI = smallImg(*r);
//同样方法检测人眼
nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
//|CV_HAAR_DO_CANNY_PRUNING
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
for( vector<Rect>::const_iterator nr = nestedObjects.begin(); nr != nestedObjects.end(); nr++ )
{
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( img, center, radius, color, 3, 8, 0 );
}
}
cv::imshow( "aaa", img );
callBackFun(xPoint, yPoint);
}
void findcars() //main function
{
int i = 0;
Mat img = storage.clone();
Mat temp;
if(img.empty() )
{
cout << endl << "detect not successful" << endl;
}
int cen_x;
int cen_y;
vector<Rect> cars;
const static Scalar colors[] = { CV_RGB(0,0,255),CV_RGB(0,255,0),CV_RGB(255,0,0),CV_RGB(255,255,0),CV_RGB(255,0,255),CV_RGB(0,255,255),CV_RGB(255,255,255),CV_RGB(128,0,0),CV_RGB(0,128,0),CV_RGB(0,0,128),CV_RGB(128,128,128),CV_RGB(0,0,0)};
Mat gray;
cvtColor( img, gray, CV_BGR2GRAY );
Mat resize_image(cvRound (img.rows), cvRound(img.cols), CV_8UC1 );
resize( gray, resize_image, resize_image.size(), 0, 0, INTER_LINEAR );
equalizeHist( resize_image, resize_image );
cascade.detectMultiScale( resize_image, cars,1.1,2,0,Size(10,10));
for( vector<Rect>::const_iterator main = cars.begin(); main != cars.end(); main++, i++ )
{
Mat resize_image_reg_of_interest;
vector<Rect> nestedcars;
Point center;
Scalar color = colors[i%8];
//getting points for bouding a rectangle over the car detected by main
int x0 = cvRound(main->x);
int y0 = cvRound(main->y);
int x1 = cvRound((main->x + main->width-1));
int y1 = cvRound((main->y + main->height-1));
if( checkcascade.empty() )
continue;
resize_image_reg_of_interest = resize_image(*main);
checkcascade.detectMultiScale( resize_image_reg_of_interest, nestedcars,1.1,2,0,Size(30,30));
for( vector<Rect>::const_iterator sub = nestedcars.begin(); sub != nestedcars.end(); sub++ ) //testing the detected car by main using checkcascade
{
center.x = cvRound((main->x + sub->x + sub->width*0.5)); //getting center points for bouding a circle over the car detected by checkcascade
cen_x = center.x;
center.y = cvRound((main->y + sub->y + sub->height*0.5));
cen_y = center.y;
if(cen_x>(x0+15) && cen_x<(x1-15) && cen_y>(y0+15) && cen_y<(y1-15)) //if centre of bounding circle is inside the rectangle boundary over a threshold the the car is certified
{
rectangle( image_main_result, cvPoint(x0,y0),
cvPoint(x1,y1),
color, 3, 8, 0); //detecting boundary rectangle over the final result
//masking the detected car to detect second car if present
Rect region_of_interest = Rect(x0, y0, x1-x0, y1-y0);
temp = storage(region_of_interest);
temp = Scalar(255,255,255);
num = num+1; //num if number of cars detected
}
}
}
if(image_main_result.empty() )
{
cout << endl << "result storage not successful" << endl;
}
}
void detectAndDraw( Mat& img, CascadeClassifier& cascade,
CascadeClassifier& nestedCascade,
double scale, bool tryflip )
{
//int cnt=0;
char file_name[128];
char dest_path[256];
int i = 0;
double t = 0;
vector<Rect> faces, faces2;
const static Scalar colors[] = { CV_RGB(0,0,255),
CV_RGB(0,128,255),
CV_RGB(0,255,255),
CV_RGB(0,255,0),
CV_RGB(255,128,0),
CV_RGB(255,255,0),
CV_RGB(255,0,0),
CV_RGB(255,0,255)} ;
Mat gray, smallImg( cvRound (img.rows/scale), cvRound(img.cols/scale), CV_8UC1 );
cvtColor( img, gray, CV_BGR2GRAY );
resize( gray, smallImg, smallImg.size(), 0, 0, INTER_LINEAR );
equalizeHist( smallImg, smallImg );
t = (double)cvGetTickCount();
cascade.detectMultiScale( smallImg, faces,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
if( tryflip )
{
flip(smallImg, smallImg, 1);
cascade.detectMultiScale( smallImg, faces2,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
|CV_HAAR_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)cvGetTickCount() - t;
//printf( "detection time = %g ms\n", t/((double)cvGetTickFrequency()*1000.) );
int cnt = 0;
for( vector<Rect>::const_iterator r = faces.begin(); r != faces.end(); r++, i++ )
{
Mat smallImgROI;
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( img, center, radius, color, 3, 8, 0 );
printf("%d %d [%d, %d]\n", r->x, r->y, r->width, r->height);
now_timeget(file_name, cnt);
cnt++;
cv::Mat cut_img(img, cv::Rect(r->x*scale, r->y*scale, r->width*scale, r->height*scale));
sprintf(dest_path, "/var/www/images/");
strncat(dest_path, file_name, 256);
cv::imwrite(dest_path, cut_img);
send_imgFileName((char*)file_name); //send to server!!
}
else
rectangle( img, cvPoint(cvRound(r->x*scale), cvRound(r->y*scale)),
cvPoint(cvRound((r->x + r->width-1)*scale), cvRound((r->y + r->height-1)*scale)),
color, 3, 8, 0);
if( nestedCascade.empty() )
continue;
smallImgROI = smallImg(*r);
nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
//|CV_HAAR_DO_CANNY_PRUNING
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
for( vector<Rect>::const_iterator nr = nestedObjects.begin(); nr != nestedObjects.end(); nr++ )
{
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( img, center, radius, color, 3, 8, 0 );
//cv::imwrite("result.jpg", img);
}
}
cv::imshow( "result", img );
}
// Search for both eyes within the given face image. Returns the eye centers in 'leftEye' and 'rightEye',
// or sets them to (-1,-1) if each eye was not found. Note that you can pass a 2nd eyeCascade if you
// want to search eyes using 2 different cascades. For example, you could use a regular eye detector
// as well as an eyeglasses detector, or a left eye detector as well as a right eye detector.
// Or if you don't want a 2nd eye detection, just pass an uninitialized CascadeClassifier.
// Can also store the searched left & right eye regions if desired.
void detectBothEyes(const Mat &face, CascadeClassifier &eyeCascade1, CascadeClassifier &eyeCascade2, Point &leftEye, Point &rightEye, Rect *searchedLeftEye, Rect *searchedRightEye)
{
// Skip the borders of the face, since it is usually just hair and ears, that we don't care about.
/*
// For "2splits.xml": Finds both eyes in roughly 60% of detected faces, also detects closed eyes.
const float EYE_SX = 0.12f;
const float EYE_SY = 0.17f;
const float EYE_SW = 0.37f;
const float EYE_SH = 0.36f;
*/
/*
// For mcs.xml: Finds both eyes in roughly 80% of detected faces, also detects closed eyes.
const float EYE_SX = 0.10f;
const float EYE_SY = 0.19f;
const float EYE_SW = 0.40f;
const float EYE_SH = 0.36f;
*/
// For default eye.xml or eyeglasses.xml: Finds both eyes in roughly 40% of detected faces, but does not detect closed eyes.
const float EYE_SX = 0.16f;
const float EYE_SY = 0.26f;
const float EYE_SW = 0.30f;
const float EYE_SH = 0.28f;
int leftX = cvRound(face.cols * EYE_SX);
int topY = cvRound(face.rows * EYE_SY);
int widthX = cvRound(face.cols * EYE_SW);
int heightY = cvRound(face.rows * EYE_SH);
int rightX = cvRound(face.cols * (1.0-EYE_SX-EYE_SW) ); // Start of right-eye corner
Mat topLeftOfFace = face(Rect(leftX, topY, widthX, heightY));
Mat topRightOfFace = face(Rect(rightX, topY, widthX, heightY));
Rect leftEyeRect, rightEyeRect;
// Return the search windows to the caller, if desired.
if (searchedLeftEye)
*searchedLeftEye = Rect(leftX, topY, widthX, heightY);
if (searchedRightEye)
*searchedRightEye = Rect(rightX, topY, widthX, heightY);
// Search the left region, then the right region using the 1st eye detector.
detectLargestObject(topLeftOfFace, eyeCascade1, leftEyeRect, topLeftOfFace.cols);
detectLargestObject(topRightOfFace, eyeCascade1, rightEyeRect, topRightOfFace.cols);
// If the eye was not detected, try a different cascade classifier.
if (leftEyeRect.width <= 0 && !eyeCascade2.empty()) {
detectLargestObject(topLeftOfFace, eyeCascade2, leftEyeRect, topLeftOfFace.cols);
//if (leftEyeRect.width > 0)
// cout << "2nd eye detector LEFT SUCCESS" << endl;
//else
// cout << "2nd eye detector LEFT failed" << endl;
}
//else
// cout << "1st eye detector LEFT SUCCESS" << endl;
// If the eye was not detected, try a different cascade classifier.
if (rightEyeRect.width <= 0 && !eyeCascade2.empty()) {
detectLargestObject(topRightOfFace, eyeCascade2, rightEyeRect, topRightOfFace.cols);
//if (rightEyeRect.width > 0)
// cout << "2nd eye detector RIGHT SUCCESS" << endl;
//else
// cout << "2nd eye detector RIGHT failed" << endl;
}
//else
// cout << "1st eye detector RIGHT SUCCESS" << endl;
if (leftEyeRect.width > 0) { // Check if the eye was detected.
leftEyeRect.x += leftX; // Adjust the left-eye rectangle because the face border was removed.
leftEyeRect.y += topY;
leftEye = Point(leftEyeRect.x + leftEyeRect.width/2, leftEyeRect.y + leftEyeRect.height/2);
}
else {
leftEye = Point(-1, -1); // Return an invalid point
}
if (rightEyeRect.width > 0) { // Check if the eye was detected.
rightEyeRect.x += rightX; // Adjust the right-eye rectangle, since it starts on the right side of the image.
rightEyeRect.y += topY; // Adjust the right-eye rectangle because the face border was removed.
rightEye = Point(rightEyeRect.x + rightEyeRect.width/2, rightEyeRect.y + rightEyeRect.height/2);
}
else {
rightEye = Point(-1, -1); // Return an invalid point
}
}
void detect(Mat& img, CascadeClassifier& cascade,
CascadeClassifier& nestedCascade, double scale) {
int i = 0;
double t = 0;
vector<Rect> faces;
Mat gray, smallImg;
cvtColor(img, gray, CV_BGR2GRAY);
resize(gray, smallImg, Size(), 1 / scale, 1 / scale, INTER_LINEAR);
equalizeHist(smallImg, smallImg);
t = (double) cvGetTickCount();
cascade.detectMultiScale(smallImg, faces, 1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
| CV_HAAR_SCALE_IMAGE, Size(30, 30));
t = (double) cvGetTickCount() - t;
// printf("detection time = %g ms\n",
// t / ((double) cvGetTickFrequency() * 1000.));
// Bounding boxes of all eyes found this frame, in full-size camera space
vector<Rect> allEyes;
for (vector<Rect>::const_iterator r = faces.begin(); r != faces.end();
r++, i++) {
Mat smallImgROI;
vector<Rect> nestedObjects;
if (nestedCascade.empty())
continue;
smallImgROI = smallImg(*r);
nestedCascade.detectMultiScale(smallImgROI, nestedObjects, 1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
//|CV_HAAR_DO_CANNY_PRUNING
| CV_HAAR_SCALE_IMAGE, Size(30, 30));
for (vector<Rect>::const_iterator e = nestedObjects.begin();
e != nestedObjects.end(); ++e) {
allEyes.push_back((*e + r->tl()) * scale);
}
}
// Find which tracked eyes are closest to the observed eyes this frame
vector<pair<int, int> > matching = assignTracksToEyes(eyeTracks, allEyes);
vector<bool> foundTracks(eyeTracks.size());
vector<bool> foundEyes(allEyes.size());
for (vector<pair<int, int> >::const_iterator trackToEye = matching.begin();
trackToEye != matching.end(); ++trackToEye) {
foundTracks[trackToEye->first] = true;
foundEyes[trackToEye->second] = true;
const Rect& eyeSrc = allEyes[trackToEye->second];
EyeTrack& track = eyeTracks[trackToEye->first];
record(track, img, eyeSrc);
}
// Forget any tracks that haven't been picked up for a while
for (int i = 0; i < eyeTracks.size(); ++i) {
if (!eyeTracks[i].lastSeen.empty() && !foundTracks[i]) {
int framesSinceLastSeen = ++(eyeTracks[i].numFramesSinceLastSeen);
if (framesSinceLastSeen > 5)
eyeTracks[i] = EyeTrack();
}
}
// Put any new eyes into a free slot, if possible
int j = 0;
for (int i = 0; i < allEyes.size(); ++i) {
if (!foundEyes[i]) {
while (j < eyeTracks.size() && !eyeTracks[j].lastSeen.empty())
j++;
if (j == eyeTracks.size())
break;
record(eyeTracks[j], img, allEyes[i]);
}
}
for (vector<EyeTrack>::iterator t = eyeTracks.begin(); t != eyeTracks.end();
++t) {
if (t->frames.size() >= 10) {
t->frames.erase(t->frames.begin(), t->frames.end() - 10);
t->lastSeen.erase(t->lastSeen.begin(), t->lastSeen.end() - 10);
}
}
i = 0;
for (vector<Rect>::const_iterator r = faces.begin(); r != faces.end();
++r, ++i) {
Scalar color = colors[i % 8];
rectangle(img, *r * scale, color, 3);
}
i = 0;
// for(vector<Rect>::const_iterator e = allEyes.begin(); e != allEyes.end(); ++e, ++i) {
// const Scalar& color = colors[i % maxEyes];
// rectangle(img, *e, color, 3);
// }
}
// the actual detection code
void detectAndDraw( Mat& img,
CascadeClassifier& cascade, CascadeClassifier& nestedCascade,
double scale)
{
/* BEGINNING OF CODE WE NEED TO REPLACE */
// initialize vars
int i = 0;
double t = 0;
vector<Rect> faces;
const static Scalar colors[] = { CV_RGB(0,0,255),
CV_RGB(0,128,255),
CV_RGB(0,255,255),
CV_RGB(0,255,0),
CV_RGB(255,128,0),
CV_RGB(255,255,0),
CV_RGB(255,0,0),
CV_RGB(255,0,255)} ;
Mat gray, smallImg( cvRound (img.rows/scale), cvRound(img.cols/scale), CV_8UC1 );
// take "img" and convert it to gray-scale: "gray." the rest of the code is processing the new "gray" img
cvtColor( img, gray, CV_BGR2GRAY );
resize( gray, smallImg, smallImg.size(), 0, 0, INTER_LINEAR );
equalizeHist( smallImg, smallImg );
// find the objects in the image that match the haar classifiers, store them in faces
t = (double)cvGetTickCount();
cascade.detectMultiScale( smallImg, faces,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
t = (double)cvGetTickCount() - t;
printf( "detection time = %g ms\n", t/((double)cvGetTickFrequency()*1000.) );
/* END OF CODE WE NEED TO REPLACE */
// detection done, faces stored as rects, now print the stuff to the image
for( vector<Rect>::const_iterator r = faces.begin(); r != faces.end(); r++, i++ )
{
Mat smallImgROI;
vector<Rect> nestedObjects;
Point center;
Scalar color = colors[i%8];
int radius;
// set the vars to values based off of the faces rects
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);
// draw the cascade circles
/* EDITED TO MAKE FULL CIRCLES, RATHER THAN EDGES, FOR COMPARISON */
circle( img, center, radius, color, -1 /*3*/, 8, 0 );
if( nestedCascade.empty() )
continue;
smallImgROI = smallImg(*r);
nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
//|CV_HAAR_DO_CANNY_PRUNING
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
// draw nested cascade circles
for( vector<Rect>::const_iterator nr = nestedObjects.begin(); nr != nestedObjects.end(); nr++ )
{
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( img, center, radius, color, -1 /*3*/, 8, 0 );
}
}
cv::imshow( "result", img );
}
void detectAndDraw( Mat& img, // <- aqui eh passado
CascadeClassifier& cascade, CascadeClassifier& nestedCascade,
double scale)
{
int i = 0;
double t = 0;
vector<Rect> faces; // <- o que a gnte quer
char filename[128];
static int filename_count = 0;
int radius;
const static Scalar colors[] = { CV_RGB(0,0,255),
CV_RGB(0,128,255),
CV_RGB(0,255,255),
CV_RGB(0,255,0),
CV_RGB(255,128,0),
CV_RGB(255,255,0),
CV_RGB(255,0,0),
CV_RGB(255,0,255)} ;
vector<int> compression_params;
compression_params.push_back(CV_IMWRITE_PNG_COMPRESSION);
compression_params.push_back(9);
Mat gray, smallImg( cvRound (img.rows/scale), cvRound(img.cols/scale), CV_8UC1 );
cvtColor( img, gray, CV_BGR2GRAY );
resize( gray, smallImg, smallImg.size(), 0, 0, INTER_LINEAR );
equalizeHist( smallImg, smallImg );
t = (double)cvGetTickCount();
//aqui detecta e coloca no faces, que é um array de retangulos. yep
cascade.detectMultiScale( smallImg, faces,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
t = (double)cvGetTickCount() - t;
printf( "detection time = %g ms\n", t/((double)cvGetTickFrequency()*1000.) );
for(vector<Rect>::const_iterator r = faces.begin(); r != faces.end(); r++, i++ )
{
Mat smallImgROI;
vector<Rect> nestedObjects;
Point center;
Scalar color = colors[i%8];
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);
if (radius != 4203968) {
sprintf(filename, "%d.png", ++filename_count);
printf("filename: %s\n", filename);
cv::imwrite(filename, img, compression_params);
}
circle( img, center, radius, color, 3, 8, 0 );
if( nestedCascade.empty() )
continue;
smallImgROI = smallImg(*r);
nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
//|CV_HAAR_DO_CANNY_PRUNING
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
for( vector<Rect>::const_iterator nr = nestedObjects.begin(); nr != nestedObjects.end(); nr++ )
{
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( img, center, radius, color, 3, 8, 0 );
}
}
cv::imshow( "result", img );
}
void detectAndDraw( Mat& img, IplImage* image,
CascadeClassifier& cascade, CascadeClassifier& nestedCascade,
double scale, IplImage* motion)
{
int i = 0;
double t = 0;
vector<Rect> faces;
const static Scalar colors[] = { CV_RGB(0,0,255),
CV_RGB(0,128,255),
CV_RGB(0,255,255),
CV_RGB(0,255,0),
CV_RGB(255,128,0),
CV_RGB(255,255,0),
CV_RGB(255,0,0),
CV_RGB(255,0,255)} ;
Mat gray, smallImg( cvRound (img.rows/scale), cvRound(img.cols/scale), CV_8UC1 );
cvtColor( img, gray, CV_BGR2GRAY );
static vector<Rect> old_faces;
static int occ = 0;
resize( gray, smallImg, smallImg.size(), 0, 0, INTER_LINEAR );
equalizeHist( smallImg, smallImg );
update_mhi(image, motion, 30);
t = (double)cvGetTickCount();
cascade.detectMultiScale( smallImg, faces,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
|CV_HAAR_DO_ROUGH_SEARCH
//|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
t = (double)cvGetTickCount() - t;
printf( "detection time = %g ms\n", t/((double)cvGetTickFrequency()*1000.) );
if (faces.empty())
{
if (occ++ == 20)
{
occ = 0;
old_faces.clear();
}
else
faces = old_faces;
}
else
old_faces = faces;
if (faces.size() == 0)
{
std::stringstream messagecpp;
std::string str_noob;
messagecpp << "up:1:" << 0 << ":" << 0;
str_noob = messagecpp.str();
const char *message_to_send = str_noob.c_str();
// server send and rcv!!
send(conn, message_to_send, strlen(message_to_send) + 1, MSG_OOB);
memset(&message, 0, MSG_SIZE);
size_recv = recv(conn, message, MSG_SIZE, MSG_PEEK);
if ( size_recv == -1)
{
perror("didn't received message");
close(sd);
return;
}
else if ( size_recv == 0)
{
perror("the peer closed the connexion");
close(sd);
return;
}
else {
std::cout << message << std::endl;
}
}
else
{
int cpt_loop = 0;
for( vector<Rect>::const_iterator r = faces.begin(); r != faces.end(); r++, i++ )
{
Mat smallImgROI;
vector<Rect> nestedObjects;
Point center;
Scalar color = colors[i%8];
int radius;
std::stringstream messagecpp;
std::string str_noob;
cpt_loop++;
messagecpp << "down:" << cpt_loop << ":" << r->x << ":" << r->y;
str_noob = messagecpp.str();
const char *message_to_send = str_noob.c_str();
//std::cout << str_noob << std::endl;
//std::cout << message_to_send << std::endl;
// server send and rcv!!
send(conn, message_to_send, strlen(message_to_send) + 1, MSG_OOB);
memset(&message, 0, MSG_SIZE);
size_recv = recv(conn, message, MSG_SIZE, MSG_PEEK);
if ( size_recv == -1)
{
perror("didn't received message");
close(sd);
return;
}
else if ( size_recv == 0)
{
perror("the peer closed the connexion");
close(sd);
return;
}
else {
std::cout << message << std::endl;
}
// fin de la partie server.
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);
//std::cout << "radius = " << radius << std::endl;
if (radius > 25)
continue;
circle( img, center, radius, color, 3, 8, 0 );
if( nestedCascade.empty() )
continue;
smallImgROI = smallImg(*r);
nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
//|CV_HAAR_DO_CANNY_PRUNING
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
for( vector<Rect>::const_iterator nr = nestedObjects.begin(); nr != nestedObjects.end(); nr++ )
{
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( img, center, radius, color, 3, 8, 0 );
}
}
}
cv::imshow( "result", img );
cvShowImage( "Motion", motion );
}
void detectAndDraw( Mat& img,
CascadeClassifier& cascade, CascadeClassifier& nestedCascade,
double scale, char* argv[])
{
int i = 0;
double t = 0;
vector<Rect> faces;
const static Scalar colors[] = { CV_RGB(0,0,255),
CV_RGB(0,128,255),
CV_RGB(0,255,255),
CV_RGB(0,255,0),
CV_RGB(255,128,0),
CV_RGB(255,255,0),
CV_RGB(255,0,0),
CV_RGB(255,0,255)} ;
Mat gray, smallImg( cvRound (img.rows/scale), cvRound(img.cols/scale), CV_8UC1 );
cvtColor( img, gray, CV_BGR2GRAY );
resize( gray, smallImg, smallImg.size(), 0, 0, INTER_LINEAR );
equalizeHist( smallImg, smallImg );
t = (double)cvGetTickCount();
cascade.detectMultiScale( smallImg, faces,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
t = (double)cvGetTickCount() - t;
for( vector<Rect>::const_iterator r = faces.begin(); r != faces.end(); r++, i++ )
{
Mat smallImgROI;
vector<Rect> nestedObjects;
Point center;
Scalar color = colors[i%8];
int radius;
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);
Rect rect = Rect(center.x - radius , center.y - radius , 2*radius , 2*radius );
Mat faceImage = gray(rect);
char s1[100];
sprintf(s1,"dataset/%s/%s_%d.jpg",argv[1],argv[1],count_face++);
imwrite(s1,faceImage);
//imshow( "result", faceImage );
//circle( img, center, radius, color, 3, 8, 0 );
rectangle(img, rect, Scalar(255,0,0));
if( nestedCascade.empty() )
continue;
smallImgROI = smallImg(*r);
nestedCascade.detectMultiScale( smallImgROI, nestedObjects,
1.1, 2, 0
//|CV_HAAR_FIND_BIGGEST_OBJECT
//|CV_HAAR_DO_ROUGH_SEARCH
//|CV_HAAR_DO_CANNY_PRUNING
|CV_HAAR_SCALE_IMAGE
,
Size(30, 30) );
for( vector<Rect>::const_iterator nr = nestedObjects.begin(); nr != nestedObjects.end(); nr++ )
{
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( img, center, radius, color, 3, 8, 0 );
Rect rect1 = Rect(center.x - radius , center.y - radius , 2*radius , 2*radius );
Mat faceImage1 = gray(rect1);
char s2[100];
sprintf(s2,"dataset/%s/%s_%d.jpg",argv[1],argv[1],count_face++);
imwrite(s2,faceImage1);
}
}
//cv::imshow( "result", img );
}
Mat detectAndDraw( Mat& img, CascadeClassifier& cascade,
CascadeClassifier& nestedCascade,
double scale, bool tryflip )
{
Mat img2;
Mat newROI;
//Converson to rgchromaticity space
img.copyTo(img2);
Mat M;
img.copyTo(M);
//for( int i = 0; i < img.rows; i++ ) {
// const int* ptr = img2.ptr<int>(i);
// float* dptr = M.ptr<float>(i);
// for( int j = 0; j < img.cols; j++ ) {
// dptr[3*j] = ptr[3*j+2]*1.0 /(ptr[3*j+0] + ptr[3*j+1] + ptr[3*j+2]);
// dptr[3*j+1] = ptr[3*j+1]*1.0 /(ptr[3*j+0] + ptr[3*j+1] + ptr[3*j+2]);
// dptr[3*j+2] = (ptr[3*j+0] + ptr[3*j+1] + ptr[3*j+2]);
// }
//}
//cvtColor(img,img2,COLOR_BGR2GRAY);
int i = 0;
double t = 0;
vector<Rect> faces, faces2;
const static Scalar colors[] = { CV_RGB(0,0,255),
CV_RGB(0,128,255),
CV_RGB(0,255,255),
CV_RGB(0,255,0),
CV_RGB(255,128,0),
CV_RGB(255,255,0),
CV_RGB(255,0,0),
CV_RGB(255,0,255)} ;
Mat gray, smallImg( cvRound (img.rows/scale), cvRound(img.cols/scale), CV_8UC1 );
cvtColor( img, gray, COLOR_BGR2GRAY );
resize( gray, smallImg, smallImg.size(), 0, 0, INTER_LINEAR );
equalizeHist( smallImg, smallImg );
t = (double)cvGetTickCount();
cascade.detectMultiScale( smallImg, faces,
1.1, 2, 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)cvGetTickCount() - t;
printf( "detection time = %g ms\n", t/((double)cvGetTickFrequency()*1000.) );
for( vector<Rect>::const_iterator r = faces.begin(); r != faces.end(); r++, i++ )
{
Mat smallImgROI;
vector<Rect> nestedObjects;
Point center;
Point faceCenter;
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);
faceCenter = center;
radius = cvRound((r->width + r->height)*0.25*scale);
circle( img, center, radius, color, 3, 8, 0 );
}
else
rectangle( img, cvPoint(cvRound(r->x*scale), cvRound(r->y*scale)),
cvPoint(cvRound((r->x + r->width-1)*scale), cvRound((r->y + r->height-1)*scale)),
color, 3, 8, 0);
if( nestedCascade.empty() )
continue;
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) );
int nestedFlag=0;
Scalar s1,s2;
float gvalue=0;
int count=0;
stringstream s;
for( vector<Rect>::const_iterator nr = nestedObjects.begin(); nr != nestedObjects.end(); nr++ )
{
center.x = cvRound((r->x + nr->x + nr->width*0.5)*scale);
center.y = cvRound((r->y + nr->y + nr->height*0.5)*scale);
//printf("%d",center.x);
radius = cvRound((nr->width + nr->height)*0.25*scale);
char c= waitKey(5);
if(center.x < faceCenter.x )
{
Mat finalc;
circle( img, center, radius, color, 3, 8, 0 );
newROI = img2(Rect(center.x-radius,center.y-radius,radius*2,radius*2));
newROI.copyTo(finalc);
//imshow("newROI",newROI);
int top=150-newROI.rows;
int left=150-newROI.cols;
//copyMakeBorder(finalCropped,finalCropped,top,0,left,0,BORDER_REPLICATE);
resize(finalc,finalCropped,Size(128,128));
vw << finalCropped;
}
}
// printf("%f\n",gvalue);
}
// cv::imshow( "result", img);
// cv::imshow( "newROI", newROI );
return img;
}
void detectAndDraw( Mat& img, CascadeClassifier& cascade,
CascadeClassifier& nestedCascade,
double scale, bool tryflip )
{
int i = 0;
double t = 0;
vector<Rect> faces, faces2;
const static Scalar colors[] = { CV_RGB(0,0,255),
CV_RGB(0,128,255),
CV_RGB(0,255,255),
CV_RGB(0,255,0),
CV_RGB(255,128,0),
CV_RGB(255,255,0),
CV_RGB(255,0,0),
CV_RGB(255,0,255)} ;
Mat gray, smallImg( cvRound (img.rows/scale), cvRound(img.cols/scale), CV_8UC1 );
cvtColor( img, gray, COLOR_BGR2GRAY );
resize( gray, smallImg, smallImg.size(), 0, 0, INTER_LINEAR );
equalizeHist( smallImg, smallImg );
t = (double)cvGetTickCount();
cascade.detectMultiScale( smallImg, faces,
1.1, 2, 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)cvGetTickCount() - t;
printf( "detection time = %g ms\n", t/((double)cvGetTickFrequency()*1000.) );
for( vector<Rect>::const_iterator r = faces.begin(); r != faces.end(); r++, i++ )
{
Mat smallImgROI;
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 )
{
Mat newImage;
img.copyTo(newImage);
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( img, center, radius, color, 3, 8, 0 );
radius=radius*0.8;
int hf=0.2*radius;
printf("size=%d\n",radius*2);
Rect roi(center.x-radius,center.y-radius,2*radius,2*radius+hf);
int se=20;
Rect roi_out(center.x-radius-se,center.y-radius-se,2*radius+2*se,2*radius+2*se+hf);
Rect roi_in(center.x-radius+se,center.y-radius+se,2*radius-2*se,2*radius-2*se);
Mat mask_smooth=Mat::zeros(img.rows,img.cols,CV_8U);
mask_smooth(roi_out)=255;
mask_smooth(roi_in)=0;
Mat image_roi=img(roi);
Mat mask=Mat::zeros(img.rows,img.cols,CV_8U);
mask(roi)=1;
Scalar avg_pic_intensity=mean(image_roi);
newImage(Rect(0,0,img.cols,img.rows))=avg_pic_intensity;
img.copyTo(newImage,mask);
Mat newImageBlurred;
blur(newImage,newImageBlurred,Size(20,20));
blur(mask_smooth,mask_smooth,Size(20,20));
newImageBlurred.copyTo(newImage,mask_smooth);
//newImage(roi)=image_roi;
imshow("blurred",newImageBlurred);
imwrite("OutputImage.jpg",newImage);
imshow("new",newImage);
imshow("mask",mask_smooth);
waitKey(0);
std::cout<<avg_pic_intensity;
/*for(int i=img.;i<img.rows;i++)
{
for(int j=0;j<img.cols;j++)
{
}
}*/
rectangle(img,cvPoint(center.x-radius,center.y-radius),cvPoint(center.x+radius,center.y+radius),avg_pic_intensity,3,8,0);
}
else
rectangle( img, cvPoint(cvRound(r->x*scale), cvRound(r->y*scale)),
cvPoint(cvRound((r->x + r->width-1)*scale), cvRound((r->y + r->height-1)*scale)),
color, 3, 8, 0);
if( nestedCascade.empty() )
continue;
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( vector<Rect>::const_iterator nr = nestedObjects.begin(); nr != nestedObjects.end(); nr++ )
{
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( img, center, radius, color, 3, 8, 0 );
}
}
cv::imshow( "result", img );
}
