OpenCV  4.9.0-dev
Open Source Computer Vision
No Matches
// This file is part of OpenCV project.
// It is subject to the license terms in the LICENSE file found in the top-level directory
// of this distribution and at
#include <iostream>
#include <iomanip>
using namespace cv;
using namespace std;
class Detector
enum Mode { Default, Daimler } m;
HOGDescriptor hog, hog_d;
Detector() : m(Default), hog(), hog_d(Size(48, 96), Size(16, 16), Size(8, 8), Size(8, 8), 9)
void toggleMode() { m = (m == Default ? Daimler : Default); }
string modeName() const { return (m == Default ? "Default" : "Daimler"); }
vector<Rect> detect(InputArray img)
// Run the detector with default parameters. to get a higher hit-rate
// (and more false alarms, respectively), decrease the hitThreshold and
// groupThreshold (set groupThreshold to 0 to turn off the grouping completely).
vector<Rect> found;
if (m == Default)
hog.detectMultiScale(img, found, 0, Size(8,8), Size(), 1.05, 2, false);
else if (m == Daimler)
hog_d.detectMultiScale(img, found, 0, Size(8,8), Size(), 1.05, 2, true);
return found;
void adjustRect(Rect & r) const
// The HOG detector returns slightly larger rectangles than the real objects,
// so we slightly shrink the rectangles to get a nicer output.
r.x += cvRound(r.width*0.1);
r.width = cvRound(r.width*0.8);
r.y += cvRound(r.height*0.07);
r.height = cvRound(r.height*0.8);
static const string keys = "{ help h | | print help message }"
"{ camera c | 0 | capture video from camera (device index starting from 0) }"
"{ video v | | use video as input }";
int main(int argc, char** argv)
CommandLineParser parser(argc, argv, keys);
parser.about("This sample demonstrates the use of the HoG descriptor.");
if (parser.has("help"))
return 0;
int camera = parser.get<int>("camera");
string file = parser.get<string>("video");
if (!parser.check())
return 1;
if (file.empty());
file = samples::findFileOrKeep(file);;
if (!cap.isOpened())
cout << "Can not open video stream: '" << (file.empty() ? "<camera>" : file) << "'" << endl;
return 2;
cout << "Press 'q' or <ESC> to quit." << endl;
cout << "Press <space> to toggle between Default and Daimler detector" << endl;
Detector detector;
Mat frame;
for (;;)
cap >> frame;
if (frame.empty())
cout << "Finished reading: empty frame" << endl;
vector<Rect> found = detector.detect(frame);
t = getTickCount() - t;
// show the window
ostringstream buf;
buf << "Mode: " << detector.modeName() << " ||| "
<< "FPS: " << fixed << setprecision(1) << (getTickFrequency() / (double)t);
putText(frame, buf.str(), Point(10, 30), FONT_HERSHEY_PLAIN, 2.0, Scalar(0, 0, 255), 2, LINE_AA);
for (vector<Rect>::iterator i = found.begin(); i != found.end(); ++i)
Rect &r = *i;
rectangle(frame,,, cv::Scalar(0, 255, 0), 2);
imshow("People detector", frame);
// interact with user
const char key = (char)waitKey(1);
if (key == 27 || key == 'q') // ESC
cout << "Exit requested" << endl;
else if (key == ' ')
return 0;
Designed for command line parsing.
Definition utility.hpp:820
n-dimensional dense array class
Definition mat.hpp:812
Template class for 2D rectangles.
Definition types.hpp:444
Point_< _Tp > tl() const
the top-left corner
_Tp x
x coordinate of the top-left corner
Definition types.hpp:480
_Tp y
y coordinate of the top-left corner
Definition types.hpp:481
_Tp width
width of the rectangle
Definition types.hpp:482
_Tp height
height of the rectangle
Definition types.hpp:483
Point_< _Tp > br() const
the bottom-right corner
Template class for specifying the size of an image or rectangle.
Definition types.hpp:335
Class for video capturing from video files, image sequences or cameras.
Definition videoio.hpp:731
virtual bool open(const String &filename, int apiPreference=CAP_ANY)
Opens a video file or a capturing device or an IP video stream for video capturing.
virtual bool isOpened() const
Returns true if video capturing has been initialized already.
This is the proxy class for passing read-only input arrays into OpenCV functions.
Definition mat.hpp:160
int64_t int64
Definition interface.h:61
int cvRound(double value)
Rounds floating-point number to the nearest integer.
Definition fast_math.hpp:200
double getTickFrequency()
Returns the number of ticks per second.
int64 getTickCount()
Returns the number of ticks.
void imshow(const String &winname, InputArray mat)
Displays an image in the specified window.
int waitKey(int delay=0)
Waits for a pressed key.
void rectangle(InputOutputArray img, Point pt1, Point pt2, const Scalar &color, int thickness=1, int lineType=LINE_8, int shift=0)
Draws a simple, thick, or filled up-right rectangle.
void putText(InputOutputArray img, const String &text, Point org, int fontFace, double fontScale, Scalar color, int thickness=1, int lineType=LINE_8, bool bottomLeftOrigin=false)
Draws a text string.
int main(int argc, char *argv[])
Definition highgui_qt.cpp:3
"black box" representation of the file storage associated with a file on disk.
Definition core.hpp:102
STL namespace.
Implementation of HOG (Histogram of Oriented Gradients) descriptor and object detector.
Definition objdetect.hpp:403
virtual void setSVMDetector(InputArray svmdetector)
Sets coefficients for the linear SVM classifier.
virtual void detectMultiScale(InputArray img, std::vector< Rect > &foundLocations, std::vector< double > &foundWeights, double hitThreshold=0, Size winStride=Size(), Size padding=Size(), double scale=1.05, double groupThreshold=2.0, bool useMeanshiftGrouping=false) const
Detects objects of different sizes in the input image. The detected objects are returned as a list of...