#include #include #include using namespace cv; using namespace cv::dnn; #include #include using namespace std; const size_t inWidth = 300; const size_t inHeight = 300; const double inScaleFactor = 1.0; const Scalar meanVal(104.0, 177.0, 123.0); const char* about = "This sample uses Single-Shot Detector " "(https://arxiv.org/abs/1512.02325) " "with ResNet-10 architecture to detect faces on camera/video/image.\n" "More information about the training is available here: " "/samples/dnn/face_detector/how_to_train_face_detector.txt\n" ".caffemodel model's file is available here: " "/samples/dnn/face_detector/res10_300x300_ssd_iter_140000.caffemodel\n" ".prototxt file is available here: " "/samples/dnn/face_detector/deploy.prototxt\n"; const char* params = "{ help | false | print usage }" "{ proto | | model configuration (deploy.prototxt) }" "{ model | | model weights (res10_300x300_ssd_iter_140000.caffemodel) }" "{ camera_device | 0 | camera device number }" "{ video | | video or image for detection }" "{ min_confidence | 0.5 | min confidence }"; int main(int argc, char** argv) { CommandLineParser parser(argc, argv, params); if (parser.get("help")) { cout << about << endl; parser.printMessage(); return 0; } String modelConfiguration = parser.get("proto"); String modelBinary = parser.get("model"); //! [Initialize network] dnn::Net net = readNetFromCaffe(modelConfiguration, modelBinary); //! [Initialize network] if (net.empty()) { cerr << "Can't load network by using the following files: " << endl; cerr << "prototxt: " << modelConfiguration << endl; cerr << "caffemodel: " << modelBinary << endl; cerr << "Models are available here:" << endl; cerr << "/samples/dnn/face_detector" << endl; cerr << "or here:" << endl; cerr << "https://github.com/opencv/opencv/tree/master/samples/dnn/face_detector" << endl; exit(-1); } VideoCapture cap; if (parser.get("video").empty()) { int cameraDevice = parser.get("camera_device"); cap = VideoCapture(cameraDevice); if(!cap.isOpened()) { cout << "Couldn't find camera: " << cameraDevice << endl; return -1; } } else { cap.open(parser.get("video")); if(!cap.isOpened()) { cout << "Couldn't open image or video: " << parser.get("video") << endl; return -1; } } for(;;) { Mat frame; cap >> frame; // get a new frame from camera/video or read image if (frame.empty()) { waitKey(); break; } if (frame.channels() == 4) cvtColor(frame, frame, COLOR_BGRA2BGR); //! [Prepare blob] Mat inputBlob = blobFromImage(frame, inScaleFactor, Size(inWidth, inHeight), meanVal, false, false); //Convert Mat to batch of images //! [Prepare blob] //! [Set input blob] net.setInput(inputBlob, "data"); //set the network input //! [Set input blob] //! [Make forward pass] Mat detection = net.forward("detection_out"); //compute output //! [Make forward pass] vector layersTimings; double freq = getTickFrequency() / 1000; double time = net.getPerfProfile(layersTimings) / freq; Mat detectionMat(detection.size[2], detection.size[3], CV_32F, detection.ptr()); ostringstream ss; ss << "FPS: " << 1000/time << " ; time: " << time << " ms"; putText(frame, ss.str(), Point(20,20), 0, 0.5, Scalar(0,0,255)); float confidenceThreshold = parser.get("min_confidence"); for(int i = 0; i < detectionMat.rows; i++) { float confidence = detectionMat.at(i, 2); if(confidence > confidenceThreshold) { int xLeftBottom = static_cast(detectionMat.at(i, 3) * frame.cols); int yLeftBottom = static_cast(detectionMat.at(i, 4) * frame.rows); int xRightTop = static_cast(detectionMat.at(i, 5) * frame.cols); int yRightTop = static_cast(detectionMat.at(i, 6) * frame.rows); Rect object((int)xLeftBottom, (int)yLeftBottom, (int)(xRightTop - xLeftBottom), (int)(yRightTop - yLeftBottom)); rectangle(frame, object, Scalar(0, 255, 0)); ss.str(""); ss << confidence; String conf(ss.str()); String label = "Face: " + conf; int baseLine = 0; Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine); rectangle(frame, Rect(Point(xLeftBottom, yLeftBottom - labelSize.height), Size(labelSize.width, labelSize.height + baseLine)), Scalar(255, 255, 255), CV_FILLED); putText(frame, label, Point(xLeftBottom, yLeftBottom), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0,0,0)); } } imshow("detections", frame); if (waitKey(1) >= 0) break; } return 0; } // main