1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247
|
#include <fstream> #include <sstream> #include <iostream> #include <vector>
#include <opencv2/dnn.hpp> #include <opencv2/imgproc.hpp> #include <opencv2/highgui.hpp>
const char* keys = "{help h usage ? | | Usage examples: \n\t\t./object_detection_yolo.out --image=dog.jpg \n\t\t./object_detection_yolo.out --video=run_sm.mp4}" "{image i |<none>| input image }" "{video v |<none>| input video }" ; using namespace cv; using namespace dnn; using namespace std;
float confThreshold = 0.5; float nmsThreshold = 0.4; int inpWidth = 416; int inpHeight = 416; vector<string> classes;
void postprocess(Mat& frame, const vector<Mat>& out);
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame);
vector<String> getOutputsNames(const Net& net);
int main(int argc, char** argv) { CommandLineParser parser(argc, argv, keys); parser.about("Use this script to run object detection using YOLO3 in OpenCV."); if (parser.has("help")) { parser.printMessage(); return 0; } string classesFile = "coco.names"; ifstream ifs(classesFile.c_str()); string line; while (getline(ifs, line)) classes.push_back(line);
String modelConfiguration = "yolov3.cfg"; String modelWeights = "yolov3.weights";
Net net = readNetFromDarknet(modelConfiguration, modelWeights); net.setPreferableBackend(DNN_BACKEND_OPENCV); net.setPreferableTarget(DNN_TARGET_CPU);
string str, outputFile; VideoCapture cap; VideoWriter video; Mat frame, blob;
try {
outputFile = "yolo_out_cpp.avi"; if (parser.has("image")) { str = parser.get<String>("image"); ifstream ifile(str); if (!ifile) throw("error"); cap.open(str); str.replace(str.end()-4, str.end(), "_yolo_out_cpp.jpg"); outputFile = str; } else if (parser.has("video")) { str = parser.get<String>("video"); ifstream ifile(str); if (!ifile) throw("error"); cap.open(str); str.replace(str.end()-4, str.end(), "_yolo_out_cpp.avi"); outputFile = str; } else cap.open(parser.get<int>("device"));
} catch(...) { cout << "Could not open the input image/video stream" << endl; return 0; }
if (!parser.has("image")) { video.open(outputFile, VideoWriter::fourcc('M','J','P','G'), 28, Size(cap.get(CAP_PROP_FRAME_WIDTH), cap.get(CAP_PROP_FRAME_HEIGHT))); }
static const string kWinName = "Deep learning object detection in OpenCV"; namedWindow(kWinName, WINDOW_NORMAL);
while (waitKey(1) < 0) { cap >> frame;
if (frame.empty()) { cout << "Done processing !!!" << endl; cout << "Output file is stored as " << outputFile << endl; waitKey(3000); break; } blobFromImage(frame, blob, 1/255.0, cv::Size(inpWidth, inpHeight), Scalar(0,0,0), true, false);
net.setInput(blob);
vector<Mat> outs; net.forward(outs, getOutputsNames(net));
postprocess(frame, outs);
vector<double> layersTimes; double freq = getTickFrequency() / 1000; double t = net.getPerfProfile(layersTimes) / freq; string label = format("Inference time for a frame : %.2f ms", t); putText(frame, label, Point(0, 15), FONT_HERSHEY_SIMPLEX, 0.5, Scalar(0, 0, 255));
Mat detectedFrame; frame.convertTo(detectedFrame, CV_8U); if (parser.has("image")) imwrite(outputFile, detectedFrame); else video.write(detectedFrame);
imshow(kWinName, frame); }
cap.release(); if (!parser.has("image")) video.release();
return 0; }
void postprocess(Mat& frame, const vector<Mat>& outs) { vector<int> classIds; vector<float> confidences; vector<Rect> boxes;
for (size_t i = 0; i < outs.size(); ++i) { float* data = (float*)outs[i].data; for (int j = 0; j < outs[i].rows; ++j, data += outs[i].cols) { Mat scores = outs[i].row(j).colRange(5, outs[i].cols); Point classIdPoint; double confidence; minMaxLoc(scores, 0, &confidence, 0, &classIdPoint); if (confidence > confThreshold) { int centerX = (int)(data[0] * frame.cols); int centerY = (int)(data[1] * frame.rows); int width = (int)(data[2] * frame.cols); int height = (int)(data[3] * frame.rows); int left = centerX - width / 2; int top = centerY - height / 2;
classIds.push_back(classIdPoint.x); confidences.push_back((float)confidence); boxes.push_back(Rect(left, top, width, height)); } } }
vector<int> indices; NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices); for (size_t i = 0; i < indices.size(); ++i) { int idx = indices[i]; Rect box = boxes[idx]; drawPred(classIds[idx], confidences[idx], box.x, box.y, box.x + box.width, box.y + box.height, frame); } }
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame) { rectangle(frame, Point(left, top), Point(right, bottom), Scalar(255, 178, 50), 3);
string label = format("%.2f", conf); if (!classes.empty()) { CV_Assert(classId < (int)classes.size()); label = classes[classId] + ":" + label; }
int baseLine; Size labelSize = getTextSize(label, FONT_HERSHEY_SIMPLEX, 0.5, 1, &baseLine); top = max(top, labelSize.height); rectangle(frame, Point(left, top - round(1.5*labelSize.height)), Point(left + round(1.5*labelSize.width), top + baseLine), Scalar(255, 255, 255), FILLED); putText(frame, label, Point(left, top), FONT_HERSHEY_SIMPLEX, 0.75, Scalar(0,0,0),1); }
vector<String> getOutputsNames(const Net& net) { static vector<String> names; if (names.empty()) { vector<int> outLayers = net.getUnconnectedOutLayers();
vector<String> layersNames = net.getLayerNames();
names.resize(outLayers.size()); for (size_t i = 0; i < outLayers.size(); ++i) names[i] = layersNames[outLayers[i] - 1]; } return names; }
|