#include <fstream>
#include <sstream>
#include "common.hpp"
std::string keys =
"{ help h | | Print help message. }"
"{ @alias | | An alias name of model to extract preprocessing parameters from models.yml file. }"
"{ zoo | models.yml | An optional path to file with preprocessing parameters }"
"{ device | 0 | camera device number. }"
"{ input i | | Path to input image or video file. Skip this argument to capture frames from a camera. }"
"{ framework f | | Optional name of an origin framework of the model. Detect it automatically if it does not set. }"
"{ classes | | Optional path to a text file with names of classes to label detected objects. }"
"{ thr | .5 | Confidence threshold. }"
"{ nms | .4 | Non-maximum suppression threshold. }"
"{ backend | 0 | Choose one of computation backends: "
"0: automatically (by default), "
"1: Halide language (http://halide-lang.org/), "
"2: Intel's Deep Learning Inference Engine (https://software.intel.com/openvino-toolkit), "
"3: OpenCV implementation }"
"{ target | 0 | Choose one of target computation devices: "
"0: CPU target (by default), "
"1: OpenCL, "
"2: OpenCL fp16 (half-float precision), "
"3: VPU }";
using namespace dnn;
float confThreshold, nmsThreshold;
std::vector<std::string> classes;
void drawPred(
int classId,
float conf,
int left,
int top,
int right,
int bottom,
Mat& frame);
void callback(int pos, void* userdata);
std::vector<String> getOutputsNames(const Net& net);
int main(int argc, char** argv)
{
const std::string modelName = parser.get<
String>(
"@alias");
const std::string zooFile = parser.get<
String>(
"zoo");
keys += genPreprocArguments(modelName, zooFile);
parser.about("Use this script to run object detection deep learning networks using OpenCV.");
if (argc == 1 || parser.has("help"))
{
parser.printMessage();
return 0;
}
confThreshold = parser.get<float>("thr");
nmsThreshold = parser.get<float>("nms");
float scale = parser.get<float>("scale");
bool swapRB = parser.get<bool>("rgb");
int inpWidth = parser.get<int>("width");
int inpHeight = parser.get<int>("height");
if (parser.has("classes"))
{
std::string file = parser.get<
String>(
"classes");
std::ifstream ifs(file.c_str());
if (!ifs.is_open())
while (std::getline(ifs, line))
{
classes.push_back(line);
}
}
Net net =
readNet(modelPath, configPath, parser.get<
String>(
"framework"));
net.setPreferableBackend(parser.get<int>("backend"));
net.setPreferableTarget(parser.get<int>("target"));
std::vector<String> outNames = net.getUnconnectedOutLayersNames();
static const std::string kWinName = "Deep learning object detection in OpenCV";
int initialConf = (int)(confThreshold * 100);
createTrackbar(
"Confidence threshold, %", kWinName, &initialConf, 99, callback);
if (parser.has("input"))
else
cap.
open(parser.get<
int>(
"device"));
{
cap >> frame;
if (frame.empty())
{
break;
}
Size inpSize(inpWidth > 0 ? inpWidth : frame.cols,
inpHeight > 0 ? inpHeight : frame.rows);
net.setInput(blob);
if (net.getLayer(0)->outputNameToIndex("im_info") != -1)
{
resize(frame, frame, inpSize);
Mat imInfo = (
Mat_<float>(1, 3) << inpSize.height, inpSize.width, 1.6f);
net.setInput(imInfo, "im_info");
}
std::vector<Mat> outs;
net.forward(outs, outNames);
std::vector<double> layersTimes;
double t = net.getPerfProfile(layersTimes) / freq;
std::string label = format("Inference time: %.2f ms", t);
}
return 0;
}
{
static std::vector<int> outLayers = net.getUnconnectedOutLayers();
static std::string outLayerType = net.getLayer(outLayers[0])->type;
std::vector<int> classIds;
std::vector<float> confidences;
std::vector<Rect> boxes;
if (net.getLayer(0)->outputNameToIndex("im_info") != -1)
{
float* data = (float*)outs[0].data;
for (size_t i = 0; i < outs[0].total(); i += 7)
{
float confidence = data[i + 2];
if (confidence > confThreshold)
{
int left = (int)data[i + 3];
int top = (int)data[i + 4];
int right = (int)data[i + 5];
int bottom = (int)data[i + 6];
int width = right - left + 1;
int height = bottom - top + 1;
classIds.push_back((int)(data[i + 1]) - 1);
boxes.push_back(
Rect(left, top, width, height));
confidences.push_back(confidence);
}
}
}
else if (outLayerType == "DetectionOutput")
{
float* data = (float*)outs[0].data;
for (size_t i = 0; i < outs[0].total(); i += 7)
{
float confidence = data[i + 2];
if (confidence > confThreshold)
{
int left = (int)(data[i + 3] * frame.
cols);
int top = (int)(data[i + 4] * frame.
rows);
int right = (int)(data[i + 5] * frame.
cols);
int bottom = (int)(data[i + 6] * frame.
rows);
int width = right - left + 1;
int height = bottom - top + 1;
classIds.push_back((int)(data[i + 1]) - 1);
boxes.push_back(
Rect(left, top, width, height));
confidences.push_back(confidence);
}
}
}
else if (outLayerType == "Region")
{
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);
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));
}
}
}
}
else
std::vector<int> indices;
NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices);
for (size_t i = 0; i < indices.size(); ++i)
{
int idx = indices[i];
drawPred(classIds[idx], confidences[idx], box.
x, box.
y,
}
}
void drawPred(
int classId,
float conf,
int left,
int top,
int right,
int bottom,
Mat& frame)
{
std::string label = format("%.2f", conf);
if (!classes.empty())
{
label = classes[classId] + ": " + label;
}
int baseLine;
}
void callback(int pos, void*)
{
confThreshold = pos * 0.01f;
}