I follow one topic to install yolo for c++ project (Include darknet Yolov3 for object detection), but I have one more question : I try to launch Yolov3 in my c++ project. I built the yolo_cpp_dll_no_gpu.sln (I don't have GPU), so I have darknet_no_gpu.exe
I would like to detect some objects on my frame from my webcam. I obtain my frame, but I don't know how to launch yolo detection in c++ project. Maybe it's similar to python commands, but I don't find the c++ syntax...
Can you help me please ?
edit: (I give more details)
I need to use YoloV3 for hand detection on a c++ project on visual studio 2019.
So I trained Yolov3 with python commands. I obtained my .weights file and the detection works when I launch this command on the cmd :
darknet_no_gpu detector demo data/obj.data cfg/yolov3-tiny.cfg yolov3-tiny_last.weights
Now, I would like to use this detection in VS project. I built yolo_cpp_dll_no_gpu.sln to obtain darknet_no_gpu.exe yolo cpp dll no gpu
In my project, I had the path of the include and library in the properties path in properties and the dependence dependence
So, my question is, what is the syntax to use yolo on my frame: `
VideoCapture cap(0); // open camera
if (!cap.isOpened())
return -1;
cap.set(CAP_PROP_FRAME_WIDTH, 320);
cap.set(CAP_PROP_FRAME_HEIGHT, 240);
for (;;) {
cap >> frame;
if (frame.empty())
break;
` because I can't use this one in VS
darknet_no_gpu detector demo data/obj.data cfg/yolov3-tiny.cfg yolov3-tiny_last.weights frame
edit 2: Hello, After some research with your help, I have 1 more problem... Here is my code:
#include <Windows.h>
#include <fstream>
#include <sstream>
#include <iostream>
#include <opencv2/dnn.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/highgui.hpp>
#include <opencv2/opencv.hpp>
using namespace cv;
using namespace dnn;
using namespace std;
// Initialize the parameters
float confThreshold = 0.5; // Confidence threshold
float nmsThreshold = 0.4; // Non-maximum suppression threshold
int inpWidth = 416; // Width of network's input image
int inpHeight = 416; // Height of network's input image
vector<string> classes;
// Remove the bounding boxes with low confidence using non-maxima suppression
void postprocess(Mat& frame, const vector<Mat>& out);
// Draw the predicted bounding box
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame);
// Get the names of the output layers
vector<String> getOutputsNames(const Net& net);
int main(int argc, char** argv)
{
// Load names of classes
string classesFile = "obj.names";
ifstream ifs(classesFile.c_str());
string line;
while (getline(ifs, line)) classes.push_back(line);
// Give the configuration and weight files for the model
String modelConfiguration = "yolov3-tiny.cfg";
String modelWeights = "yolov3-tiny_last.weights";
// Load the network
Net net = readNetFromDarknet(modelConfiguration, modelWeights);
net.setPreferableBackend(DNN_BACKEND_OPENCV);
net.setPreferableTarget(DNN_TARGET_CPU);
// Open a video file or an image file or a camera stream.
string outputFile;
//VideoCapture cap;
VideoWriter video;
Mat frame;
Mat blob, ex;
VideoCapture cap(0); // ouvre la camera par défaut
if (!cap.isOpened()) // check si succès
return -1;
for (;;) {
// get frame from the video
cap >> frame;
cvtColor(frame, ex, COLOR_BGR2YCrCb);
cout << frame.size << endl;
imshow("e", ex);
// Stop the program if reached end of video
if (frame.empty()) {
cout << "Done processing !!!" << endl;
cout << "Output file is stored as " << outputFile << endl;
waitKey(3000);
break;
}
// Create a 4D blob from a frame.
blobFromImage(frame, blob, 1 / 255.0, Size(inpWidth, inpHeight), Scalar(0, 0, 0), true, false);
//Sets the input to the network
net.setInput(blob);
// Runs the forward pass to get output of the output layers
vector<Mat> outs;
net.forward(outs, getOutputsNames(net));
// Remove the bounding boxes with low confidence
postprocess(frame, outs);
// Put efficiency information. The function getPerfProfile returns the overall time for inference(t) and the timings for each of the layers(in layersTimes)
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));
// Write the frame with the detection boxes
Mat detectedFrame;
frame.convertTo(detectedFrame, CV_8U);
imshow("f", frame);
Sleep(3000);
}
cap.release();
return 0;
}
// Remove the bounding boxes with low confidence using non-maxima suppression
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)
{
// Scan through all the bounding boxes output from the network and keep only the
// ones with high confidence scores. Assign the box's class label as the class
// with the highest score for the box.
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;
// Get the value and location of the maximum score
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));
}
}
}
// Perform non maximum suppression to eliminate redundant overlapping boxes with
// lower confidences
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);
}
}
// Draw the predicted bounding box
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame)
{
//Draw a rectangle displaying the bounding box
rectangle(frame, Point(left, top), Point(right, bottom), Scalar(255, 178, 50), 3);
//Get the label for the class name and its confidence
string label = format("%.2f", conf);
if (!classes.empty())
{
CV_Assert(classId < (int)classes.size());
label = classes[classId] + ":" + label;
}
//Display the label at the top of the bounding box
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);
}
// Get the names of the output layers
vector<String> getOutputsNames(const Net& net)
{
static vector<String> names;
if (names.empty())
{
//Get the indices of the output layers, i.e. the layers with unconnected outputs
vector<int> outLayers = net.getUnconnectedOutLayers();
//get the names of all the layers in the network
vector<String> layersNames = net.getLayerNames();
// Get the names of the output layers in names
names.resize(outLayers.size());
for (size_t i = 0; i < outLayers.size(); ++i)
names[i] = layersNames[outLayers[i] - 1];
}
return names;
}
So it would be working, but I obtain a gray windows with imshow. Like on the picture gray window
