I have been trying to develop a simple feature tracking program. The user outlines an area on the screen with their mouse, and a mask is created for this area and passed to goodFeaturesToTrack. The features found by the function are then drawn on the screen (represented by blue circles).
Next I pass the feature vector returned by the function to calcOpticalFlowPyrLk and draw the resulting vector of points on the screen (represented by green circles). Although the program tracks the direction of flow correctly, for some reason the features output by the calcOpticalFlow funciton do not line up with the object's location on the screen.
I feel as though it is a small mistake in the logic I have used on my part, but I just can't seem to decompose it, and I would really appreciate some help from the you guys.
I have posted my code below, and I would like to greatly apologize for the global variables and messy structure. I am just testing at the moment, and plan to clean up and convert to an OOP format as soon as I get it running.
As well, here is a link to a YouTube video I have uploaded that demonstrates the behavior I am combating.
bool drawingBox = false;
bool destroyBox = false;
bool targetAcquired = false;
bool featuresFound = false;
CvRect box;
int boxCounter = 0;
cv::Point objectLocation;
cv::Mat prevFrame, nextFrame, prevFrame_1C, nextFrame_1C;
std::vector<cv::Point2f> originalFeatures, newFeatures, baseFeatures;
std::vector<uchar> opticalFlowFeatures;
std::vector<float> opticalFlowFeaturesError;
cv::TermCriteria opticalFlowTermination = cv::TermCriteria(CV_TERMCRIT_ITER | CV_TERMCRIT_EPS, 20, 0.3);
cv::Mat mask;
cv::Mat clearMask;
long currentFrame = 0;
void draw(cv::Mat image, CvRect rectangle)
{
if (drawingBox)
{
cv::rectangle(image, cv::Point(box.x, box.y), cv::Point(box.x + box.width, box.y + box.height), cv::Scalar(225, 238 , 81), 2);
CvRect rectangle2 = cvRect(box.x, box.y, box.width, box.height);
}
if (featuresFound)
{
for (int i = 0; i < originalFeatures.size(); i++)
{
cv::circle(image, baseFeatures[i], 4, cv::Scalar(255, 0, 0), 1, 8, 0);
cv::circle(image, newFeatures[i], 4, cv::Scalar(0, 255, 0),1, 8, 0);
cv::line(image, baseFeatures[i], newFeatures[i], cv::Scalar(255, 0, 0), 2, CV_AA);
}
}
}
void findFeatures(cv::Mat mask)
{
if (!featuresFound && targetAcquired)
{
cv::goodFeaturesToTrack(prevFrame_1C, baseFeatures, 200, 0.1, 0.1, mask);
originalFeatures= baseFeatures;
featuresFound = true;
std::cout << "Number of Corners Detected: " << originalFeatures.size() << std::endl;
for(int i = 0; i < originalFeatures.size(); i++)
{
std::cout << "Corner Location " << i << ": " << originalFeatures[i].x << "," << originalFeatures[i].y << std::endl;
}
}
}
void trackFeatures()
{
cv::calcOpticalFlowPyrLK(prevFrame_1C, nextFrame_1C, originalFeatures, newFeatures, opticalFlowFeatures, opticalFlowFeaturesError, cv::Size(30,30), 5, opticalFlowTermination);
originalFeatures = newFeatures;
}
void mouseCallback(int event, int x, int y, int flags, void *param)
{
cv::Mat frame;
frame = *((cv::Mat*)param);
switch(event)
{
case CV_EVENT_MOUSEMOVE:
{
if(drawingBox)
{
box.width = x-box.x;
box.height = y-box.y;
}
}
break;
case CV_EVENT_LBUTTONDOWN:
{
drawingBox = true;
box = cvRect (x, y, 0, 0);
targetAcquired = false;
cv::destroyWindow("Selection");
}
break;
case CV_EVENT_LBUTTONUP:
{
drawingBox = false;
featuresFound = false;
boxCounter++;
std::cout << "Box " << boxCounter << std::endl;
std::cout << "Box Coordinates: " << box.x << "," << box.y << std::endl;
std::cout << "Box Height: " << box.height << std::endl;
std::cout << "Box Width: " << box.width << std:: endl << std::endl;
if(box.width < 0)
{
box.x += box.width;
box.width *= -1;
}
if(box.height < 0)
{
box.y +=box.height;
box.height *= -1;
}
objectLocation.x = box.x;
objectLocation.y = box.y;
targetAcquired = true;
}
break;
case CV_EVENT_RBUTTONUP:
{
destroyBox = true;
}
break;
}
}
int main ()
{
const char *name = "Boundary Box";
cv::namedWindow(name);
cv::VideoCapture camera;
cv::Mat cameraFrame;
int cameraNumber = 0;
camera.open(cameraNumber);
camera >> cameraFrame;
cv::Mat mask = cv::Mat::zeros(cameraFrame.size(), CV_8UC1);
cv::Mat clearMask = cv::Mat::zeros(cameraFrame.size(), CV_8UC1);
if (!camera.isOpened())
{
std::cerr << "ERROR: Could not access the camera or video!" << std::endl;
}
cv::setMouseCallback(name, mouseCallback, &cameraFrame);
while(true)
{
if (destroyBox)
{
cv::destroyAllWindows();
break;
}
camera >> cameraFrame;
if (cameraFrame.empty())
{
std::cerr << "ERROR: Could not grab a camera frame." << std::endl;
exit(1);
}
camera.set(CV_CAP_PROP_POS_FRAMES, currentFrame);
camera >> prevFrame;
cv::cvtColor(prevFrame, prevFrame_1C, cv::COLOR_BGR2GRAY);
camera.set(CV_CAP_PROP_POS_FRAMES, currentFrame ++);
camera >> nextFrame;
cv::cvtColor(nextFrame, nextFrame_1C, cv::COLOR_BGR2GRAY);
if (targetAcquired)
{
cv::Mat roi (mask, cv::Rect(box.x, box.y, box.width, box.height));
roi = cv::Scalar(255, 255, 255);
findFeatures(mask);
clearMask.copyTo(mask);
trackFeatures();
}
draw(cameraFrame, box);
cv::imshow(name, cameraFrame);
cv::waitKey(20);
}
cv::destroyWindow(name);
return 0;
}
In my opinion you can't use camera.set(CV_CAP_PROP_POS_FRAMES, currentFrame) on a webcam, but I 'm not positive about that.
Instead I suggest you to save the previous frame in your prevFrame variable.
As an example I can suggest you this working code, I only change inside the while loop and I add comment before all my adds :
while(true)
{
if (destroyBox)
{
cv::destroyAllWindows();
break;
}
camera >> cameraFrame;
if (cameraFrame.empty())
{
std::cerr << "ERROR: Could not grab a camera frame." << std::endl;
exit(1);
}
// new lines
if(prevFrame.empty()){
prevFrame = cameraFrame;
continue;
}
// end new lines
//camera.set(CV_CAP_PROP_POS_FRAMES, currentFrame);
//camera >> prevFrame;
cv::cvtColor(prevFrame, prevFrame_1C, cv::COLOR_BGR2GRAY);
//camera.set(CV_CAP_PROP_POS_FRAMES, currentFrame ++);
//camera >> nextFrame;
// new line
nextFrame = cameraFrame;
cv::cvtColor(nextFrame, nextFrame_1C, cv::COLOR_BGR2GRAY);
if (targetAcquired)
{
cv::Mat roi (mask, cv::Rect(box.x, box.y, box.width, box.height));
roi = cv::Scalar(255, 255, 255);
findFeatures(mask);
clearMask.copyTo(mask);
trackFeatures();
}
draw(cameraFrame, box);
cv::imshow(name, cameraFrame);
cv::waitKey(20);
// old = new
// new line
prevFrame = cameraFrame.clone();
}
Related
I am working on a queue bypass detection project and i need to select a region of interest or the boundary. If a person crosses the boundary, we should get an alert. Please help me to select a region of interest in live video similar to the one in the image.
please see this image
After doing some research I found what you need on github
#include "opencv2/opencv.hpp"
#include <iostream>
using namespace cv;
using namespace std;
/*~~~~~~~~~~~~~~~~~~*/
char ky;
bool got_roi = false;
Point points_array[4];
Mat src, ROI_Img,backup,ROI_MASK;
Rect2d ROI_Select;
int width_roi = 0, height_roi = 0,min_x,min_y,max_x,max_y;
Rect ROI_RECT ;
vector< vector<Point> > co_ordinates;
/*~~~~~~~~~~~~~~~~~~*/
/*~~~~~~~~~~~~~~~~~~*/
//Callback for mousclick event, the x-y coordinate of mouse button-down
//are stored array of points [points_array].
void mouse_click(int event, int x, int y, int flags, void *param)
{
static int count=0;
switch (event)
{
case CV_EVENT_LBUTTONDOWN:
{
switch (count) // number of set Point
{
case 0:
cout << "Select top-right point" << endl;
break;
case 1:
cout << "Select bottom-right point" << endl;
break;
case 2:
cout << "Select bottom-left point" << endl << endl;
break;
default:
break;
}
if (!got_roi) // you are not select ROI yet!
{
points_array[count] = Point(x,y);
circle(src, points_array[count], 2, Scalar(0, 255, 0), 2); //show points on image
imshow("My_Win", src);
count++;
if (count == 4) // if select 4 point finished
{
cout << "ROI x & y points :" << endl;
cout << points_array[0] << endl;
cout << points_array[1] << endl;
cout << points_array[2] << endl;
cout << points_array[3] << endl;
cout << endl << "ROI Saved You can continue with double press any keys except 'c' " << endl <<"once press 'c' or 'C' to clear points and retry select ROI " << endl << endl;
ky = waitKey(0) & 0xFF;
if (ky == 99 || ky == 67) // c or C to clear
{
backup.copyTo(src);
points_array[0] = Point(0, 0);
points_array[1] = Point(0, 0);
points_array[2] = Point(0, 0);
points_array[3] = Point(0, 0);
imshow("My_Win", src);
count = 0;
cout << endl << endl << endl << "#--------------------- Clear Points! ------------------# " << endl << endl << endl ;
}
else // user accept points & dosn't want to clear them
{
min_x = std::min(points_array[0].x, points_array[3].x); //find rectangle for minimum ROI surround it!
max_x = std::max(points_array[1].x, points_array[2].x);
min_y = std::min(points_array[0].y, points_array[1].y);
max_y = std::max(points_array[3].y, points_array[2].y);
height_roi = max_y - min_y;
width_roi = max_x - min_x;
ROI_RECT = Rect(min_x, min_y, width_roi, height_roi);
got_roi = true;
co_ordinates.push_back(vector<Point>());
co_ordinates[0].push_back(points_array[0]);
co_ordinates[0].push_back(points_array[1]);
co_ordinates[0].push_back(points_array[2]);
co_ordinates[0].push_back(points_array[3]);
}
}
}
else { // if got_roi se true => select roi before
cout << endl << "You Select ROI Before " << endl << "if you want to clear point press 'c' or double press other keys to continue" << endl << endl;
}
break;
}
}
}
/*~~~~~~~~~~~~~~~~~~*/
int main()
{
// replace all "My_Win" with your window name
/*~~~~~~~~~~~~~~~~~~*/
namedWindow("My_Win", 1);
/*~~~~~~~~~~~~~~~~~~*/
VideoCapture input_video("Video_path");
// Set source imafe as [src]
/*~~~~~~~~~~~~~~~~~~*/
input_video >> src;
imshow("My_Win", src);
src.copyTo(backup);
setMouseCallback("My_Win", mouse_click, 0);
waitKey(0);
Mat mask(src.rows, src.cols, CV_8UC1, cv::Scalar(0));
drawContours(mask, co_ordinates, 0, Scalar(255), CV_FILLED, 8);
/*~~~~~~~~~~~~~~~~~~*/
while (1)
{
input_video >> src;
/*~~~~~~~~~~~~~~~~~~*/
//Need to copy Select ROI as MASK
src.copyTo(ROI_MASK, mask);
//Creat a rectangle around the Mask to reduce size of mask
ROI_Img = ROI_MASK(ROI_RECT);
/*~~~~~~~~~~~~~~~~~~*/
//Show Image
imshow("My_Win", ROI_Img);
// Do remaining processing here on capture roi for every frame
if(char (waitKey(1)& 0xFF) == 27) break;
}
}
I try to get the first frame of a movie. But it seems impossible with VideoCapture (opencv).
To make sure that I can not get the first video I made a with all the frames numbered. You can check that the saved video has the right numbering.
Whatever I do, I can not get the first frame back.
The code to check this:
reads a movie (6 frames)
writes the 6 frames with an index printed in per frame
reads the new created movie
shows the 2 images next to each other
How can I get the first frame of a movie?
Is this a bug or is something wrong in retrieving the frames in the code?
Please compile the code and run. Without arguments a small movie is generated. standard output comments on want happens. Or specify movie name as argument.
See also next question on the comparison of the 2 images ("Images are not the same after VideoWrite and videoRead OpenCv").
#include "opencv2/imgproc/imgproc.hpp"
#include "opencv2/imgcodecs.hpp"
#include "opencv2/highgui/highgui.hpp"
#include <stdlib.h>
#include <stdio.h>
#include <iostream>
using namespace cv;
using namespace std;
std::vector<Mat> ReadImages(string VideoName)
{
// read movie from disk
VideoCapture capture( VideoName);
cout << VideoName;
if (!capture.isOpened())
cout << "Could not open the output video for write: " << VideoName << endl;
int NumFrames = capture.get(CV_CAP_PROP_FRAME_COUNT);
std::vector<Mat> FramesRead(NumFrames);
// int NumFrames = capture.get(CV_CAP_PROP_FRAME_COUNT);
cout << endl;
for(int fr = 0; fr < NumFrames; ++fr){
// read frame in 3 different ways:
cout << "Position of pointer in Movie: " << capture.get(CAP_PROP_POS_FRAMES) << endl;
switch (3) {
case 1:
capture.grab();
capture.retrieve(FramesRead[fr]);// >> frame; // get frame
break;
case 2:
capture.set ( CV_CAP_PROP_POS_FRAMES , fr); // set position
capture.read(FramesRead[fr]); // get frame
break;
default:
capture >> FramesRead[fr]; // get frame
break;
}
// show read frame
imshow("Reader",FramesRead[fr]);
cout << "Frame read should indicate a '" << fr << "'" << " and " << fr+1 << " Faces" << endl;
cout << "if number in Image is not the same as written here: VideoReader does not retrieve first image! \n";
if(waitKey(-1)==1) break;
}
cout << "finished reading Movie\n";
return FramesRead;
}
string WriteImages(std::vector<Mat> frames, string VideoName)
{
// write movie to disk and put number in every image according to frame number
Size S = Size((int) frames[0].cols, // get input size
(int) frames[0].rows);
VideoWriter outputVideo;
// use a uncompressed codec sheme
string Codec = "raw ";//"tiff";//, "mp4v", "MJPG"};
// Open the output
String VideoName2 = VideoName + "_" + Codec + "_" + "Write.avi";
cout << VideoName2 << endl;
outputVideo.open( VideoName2, VideoWriter::fourcc(Codec[0],Codec[1],Codec[2],Codec[3]),1, S, false);
if (!outputVideo.isOpened())
{
cout << "Could not open the output video for write: " << VideoName << endl;
return "-1";
}
else
{
// write images and put frame number in images
for(int fr=0;fr < frames.size() ; ++fr) //Show the image captured in the window and repeat
{
imshow("writer",frames[fr]);
waitKey(1);
putText(frames[fr], to_string(fr), Point(200, 100), FONT_HERSHEY_SIMPLEX, 1, Scalar(255,255,255));
outputVideo << frames[fr].clone();
}
return VideoName2;
}
}
std::vector<Mat> Face_Color_Movie(int NumFrames)
{
// create a movie with colored faces
const int w = 450;
std::vector<Mat> Frames(NumFrames);
Mat tmp = Mat::zeros(w, w, CV_8UC3);
for(int i=0; i< NumFrames;i++)
tmp.copyTo(Frames[i]);
Scalar white = Scalar(0,0,255);
for(int fr=0;fr < NumFrames; fr++)
{
for( int i = 0; i < fr+1; i++ )
{
int dx = (i%2)*250 - 30;
int dy = (i/2)*150;
if (i == 0)
white = Scalar(0,0,255);
else if(i == 1)
white = Scalar(255,0,0);
else
white = Scalar(0,255,0);
const Scalar black = Scalar(0);
if( i == 0 )
{
for( int j = 0; j <= 10; j++ )
{
double angle = (j+5)*CV_PI/21;
line(Frames[fr], Point(cvRound(dx+100+j*10-80*cos(angle)),
cvRound(dy+100-90*sin(angle))),
Point(cvRound(dx+100+j*10-30*cos(angle)),
cvRound(dy+100-30*sin(angle))), white, 1, 8, 0);
}
}
// imshow("Faces", Frames[fr]);waitKey(1);
ellipse( Frames[fr], Point(dx+150, dy+100), Size(100,70), 0, 0, 360, white, -1, 8, 0 );
// imshow("Faces", Frames[fr]);waitKey(1);
ellipse( Frames[fr], Point(dx+115, dy+70), Size(30,20), 0, 0, 360, black, -1, 8, 0 );
ellipse( Frames[fr], Point(dx+185, dy+70), Size(30,20), 0, 0, 360, black, -1, 8, 0 );
ellipse( Frames[fr], Point(dx+115, dy+70), Size(15,15), 0, 0, 360, white, -1, 8, 0 );
ellipse( Frames[fr], Point(dx+185, dy+70), Size(15,15), 0, 0, 360, white, -1, 8, 0 );
ellipse( Frames[fr], Point(dx+115, dy+70), Size(5,5), 0, 0, 360, black, -1, 8, 0 );
ellipse( Frames[fr], Point(dx+185, dy+70), Size(5,5), 0, 0, 360, black, -1, 8, 0 );
ellipse( Frames[fr], Point(dx+150, dy+100), Size(10,5), 0, 0, 360, black, -1, 8, 0 );
ellipse( Frames[fr], Point(dx+150, dy+150), Size(40,10), 0, 0, 360, black, -1, 8, 0 );
ellipse( Frames[fr], Point(dx+27, dy+100), Size(20,35), 0, 0, 360, white, -1, 8, 0 );
ellipse( Frames[fr], Point(dx+273, dy+100), Size(20,35), 0, 0, 360, white, -1, 8, 0 );
}
imshow("Faces", Frames[fr]);
waitKey(1);
}
return Frames;
}
std::vector<Mat> Load_Movie(int NumFrames,string VideoName)
{
// reads NUMFRAMES from a specified movie from disk
VideoCapture capture(VideoName);
if (!capture.isOpened())
cout << "Could not open the output video for write: " << VideoName << endl;
int ex = static_cast<int>(capture.get(CV_CAP_PROP_FOURCC));
cout << "Codec: "<< ex << endl;
std::vector<Mat> Frames(NumFrames);
for(int fr = 0; fr < NumFrames; ++fr)
{
capture >> Frames[fr]; // get frame
imshow("test",Frames[fr]);
waitKey(30);
}
return Frames;
}
int main( int argc, char** argv )
{
int NumFrames = 6;
std::vector<Mat> Frames;
// create a movie
if (argc < 2)
// A movie with colored faces is generated
Frames = Face_Color_Movie(NumFrames);
// Frames = Face_Movie(NumFrames);
else{
// use an existing movie
string VideoName = "Megamind_bugy.avi"; // use your own movie here
VideoName = argv[1];
Frames = Load_Movie(NumFrames,VideoName);
}
//--------------------------------
// write the frames to disk
string VideoName2 = WriteImages(Frames, "Video_Faces.avi");
// read the frames from disk (again)
std::vector<Mat> FramesRead = ReadImages( VideoName2);
// show the frames and subtract to see if they are really the same?
for (int fr=0;fr <NumFrames; ++fr)
{
//-------------------------------
// first frame of read movie is missing!!!
// Original image; fr+1 because VideoReader skips the first frame!!!
imshow("Frame before writing to disk",Frames[fr]);
// Image read from disk (first frame missing)
imshow("Frame after reading from Disk",FramesRead[fr]);
cout << "-------------------------------\n";
cout << "Shows Frame before writing to disk and frames after reading from disk\n";
cout << "Image windows may lay on top of each other\n";
moveWindow("Frame after reading from Disk",505,46);
if(waitKey(-1)==1) break;
}
}
I am doing a project for which I need to detect the rear of a car using HOG features. Once I calculated the HOG features I trained the cvsvm using positive and negative samples. cvsvm is correctly classifying the new data. Here is my code that I used to train cvsvm.
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/ml/ml.hpp>
#include "opencv2/opencv.hpp"
#include "LinearSVM.h"
using namespace cv;
using namespace std;
int main(void)
{
LinearSVM *s = new LinearSVM;
vector<float> values, values1, values2, values3, values4;
FileStorage fs2("/home/ubuntu/Desktop/opencv-svm/vecSupport.yml", FileStorage::READ);
FileStorage fs3("/home/ubuntu/Desktop/opencv-svm/vecSupport1.yml", FileStorage::READ);
FileStorage fs4("/home/ubuntu/Desktop/opencv-svm/vecSupport2.yml", FileStorage::READ);
FileStorage fs5("/home/ubuntu/Desktop/opencv-svm/vecSupport3.yml", FileStorage::READ);
FileStorage fs6("/home/ubuntu/Desktop/opencv-svm/vecSupport4.yml", FileStorage::READ);
fs2["vector"]>>values;
fs3["vector"]>>values1;
fs4["vector"]>>values2;
fs5["vector"]>>values3;
fs6["vector"]>>values4;
//fill with data
values.insert(values.end(), values1.begin(), values1.end());
values.insert(values.end(), values2.begin(), values2.end());
fs2.release();
fs3.release();
fs4.release();
float arr[188496];
float car[2772];
float noncar[2772];
// move positive and negative to arr
std::copy(values.begin(), values.end(), arr);
std::copy(values3.begin(), values3.end(), car);
std::copy(values4.begin(), values4.end(), noncar);
float labels[68];
for (unsigned int s = 0; s < 68; s++)
{
if (s<34)
labels[s] = +1;
else
labels[s] = -1;
}
Mat labelsMat(68, 1, CV_32FC1, labels);
Mat trainingDataMat(68,2772, CV_32FC1, arr);
// Set up SVM's parameters
CvSVMParams params;
params.svm_type = CvSVM::C_SVC;
params.kernel_type = CvSVM::LINEAR;
params.term_crit = cvTermCriteria(CV_TERMCRIT_ITER, 100, 1e-6);
// Train the SVM
LinearSVM SVM;
SVM.train(trainingDataMat, labelsMat, Mat(), Mat(), params);
Mat matinput(1,2772,CV_32FC1,noncar);
//cout<<matinput;
float response = SVM.predict(matinput);
cout<<"Response : "<<response<<endl;
SVM.save("Classifier.xml");
vector<float>primal;
// LinearSVM s;
//s.getSupportVector(primal);
SVM.getSupportVector(primal);
FileStorage fs("/home/ubuntu/Desktop/opencv-svm/test.yml", FileStorage::WRITE);
fs << "dector" << primal;
fs.release();
}
// LinearSVM cpp file
#include "LinearSVM.h"
void LinearSVM::getSupportVector(std::vector<float>& support_vector) const {
int sv_count = get_support_vector_count();
const CvSVMDecisionFunc* df = decision_func;
const double* alphas = df[0].alpha;
double rho = df[0].rho;
int var_count = get_var_count();
support_vector.resize(var_count, 0);
for (unsigned int r = 0; r < (unsigned)sv_count; r++) {
float myalpha = alphas[r];
const float* v = get_support_vector(r);
for (int j = 0; j < var_count; j++,v++) {
support_vector[j] += (-myalpha) * (*v);
}
}
support_vector.push_back(rho);
}
// LinearSVM head file
#ifndef LINEAR_SVM_H_
#define LINEAR_SVM_H_
#include <opencv2/core/core.hpp>
#include <opencv2/ml/ml.hpp>
class LinearSVM: public CvSVM {
public:
void getSupportVector(std::vector<float>& support_vector) const;
};
#endif /* LINEAR_SVM_H_ */
After this step I got the vector file that I can fed into setsvmdetector method. Here is my code. I have used window size of 96 x 64 and scale of 1.11
#include <iostream>
#include <fstream>
#include <string>
#include <time.h>
#include <iostream>
#include <sstream>
#include <iomanip>
#include <stdexcept>
#include <stdexcept>
#include "opencv2/gpu/gpu.hpp"
#include "opencv2/highgui/highgui.hpp"
using namespace std;
using namespace cv;
bool help_showed = false;
class Args
{
public:
Args();
static Args read(int argc, char** argv);
string src;
bool src_is_video;
bool src_is_camera;
int camera_id;
bool write_video;
string dst_video;
double dst_video_fps;
bool make_gray;
bool resize_src;
int width, height;
double scale;
int nlevels;
int gr_threshold;
double hit_threshold;
bool hit_threshold_auto;
int win_width;
int win_stride_width, win_stride_height;
bool gamma_corr;
};
class App
{
public:
App(const Args& s);
void run();
void handleKey(char key);
void hogWorkBegin();
void hogWorkEnd();
string hogWorkFps() const;
void workBegin();
void workEnd();
string workFps() const;
string message() const;
private:
App operator=(App&);
Args args;
bool running;
bool use_gpu;
bool make_gray;
double scale;
int gr_threshold;
int nlevels;
double hit_threshold;
bool gamma_corr;
int64 hog_work_begin;
double hog_work_fps;
int64 work_begin;
double work_fps;
};
static void printHelp()
{
cout << "Histogram of Oriented Gradients descriptor and detector sample.\n"
<< "\nUsage: hog_gpu\n"
<< " (<image>|--video <vide>|--camera <camera_id>) # frames source\n"
<< " [--make_gray <true/false>] # convert image to gray one or not\n"
<< " [--resize_src <true/false>] # do resize of the source image or not\n"
<< " [--width <int>] # resized image width\n"
<< " [--height <int>] # resized image height\n"
<< " [--hit_threshold <double>] # classifying plane distance threshold (0.0 usually)\n"
<< " [--scale <double>] # HOG window scale factor\n"
<< " [--nlevels <int>] # max number of HOG window scales\n"
<< " [--win_width <int>] # width of the window (48 or 64)\n"
<< " [--win_stride_width <int>] # distance by OX axis between neighbour wins\n"
<< " [--win_stride_height <int>] # distance by OY axis between neighbour wins\n"
<< " [--gr_threshold <int>] # merging similar rects constant\n"
<< " [--gamma_correct <int>] # do gamma correction or not\n"
<< " [--write_video <bool>] # write video or not\n"
<< " [--dst_video <path>] # output video path\n"
<< " [--dst_video_fps <double>] # output video fps\n";
help_showed = true;
}
int main(int argc, char** argv)
{
try
{
if (argc < 2)
printHelp();
Args args = Args::read(argc, argv);
if (help_showed)
return -1;
App app(args);
app.run();
}
catch (const Exception& e) { return cout << "error: " << e.what() << endl, 1; }
catch (const exception& e) { return cout << "error: " << e.what() << endl, 1; }
catch(...) { return cout << "unknown exception" << endl, 1; }
return 0;
}
Args::Args()
{
src_is_video = false;
src_is_camera = false;
camera_id = 0;
write_video = false;
dst_video_fps = 24.;
make_gray = false;
resize_src = false;
width = 640;
height = 480;
scale = 1.11;
nlevels = 13;
gr_threshold = 1;
hit_threshold = 1.4;
hit_threshold_auto = true;
win_width = 64;
win_stride_width = 8;
win_stride_height = 8;
gamma_corr = true;
}
Args Args::read(int argc, char** argv)
{
Args args;
for (int i = 1; i < argc; i++)
{
if (string(argv[i]) == "--make_gray") args.make_gray = (string(argv[++i]) == "true");
else if (string(argv[i]) == "--resize_src") args.resize_src = (string(argv[++i]) == "true");
else if (string(argv[i]) == "--width") args.width = atoi(argv[++i]);
else if (string(argv[i]) == "--height") args.height = atoi(argv[++i]);
else if (string(argv[i]) == "--hit_threshold")
{
args.hit_threshold = atof(argv[++i]);
args.hit_threshold_auto = false;
}
else if (string(argv[i]) == "--scale") args.scale = atof(argv[++i]);
else if (string(argv[i]) == "--nlevels") args.nlevels = atoi(argv[++i]);
else if (string(argv[i]) == "--win_width") args.win_width = atoi(argv[++i]);
else if (string(argv[i]) == "--win_stride_width") args.win_stride_width = atoi(argv[++i]);
else if (string(argv[i]) == "--win_stride_height") args.win_stride_height = atoi(argv[++i]);
else if (string(argv[i]) == "--gr_threshold") args.gr_threshold = atoi(argv[++i]);
else if (string(argv[i]) == "--gamma_correct") args.gamma_corr = (string(argv[++i]) == "true");
else if (string(argv[i]) == "--write_video") args.write_video = (string(argv[++i]) == "true");
else if (string(argv[i]) == "--dst_video") args.dst_video = argv[++i];
else if (string(argv[i]) == "--dst_video_fps") args.dst_video_fps = atof(argv[++i]);
else if (string(argv[i]) == "--help") printHelp();
else if (string(argv[i]) == "--video") { args.src = argv[++i]; args.src_is_video = true; }
else if (string(argv[i]) == "--camera") { args.camera_id = atoi(argv[++i]); args.src_is_camera = true; }
else if (args.src.empty()) args.src = argv[i];
else throw runtime_error((string("unknown key: ") + argv[i]));
}
return args;
}
App::App(const Args& s)
{
cv::gpu::printShortCudaDeviceInfo(cv::gpu::getDevice());
args = s;
cout << "\nControls:\n"
<< "\tESC - exit\n"
<< "\tm - change mode GPU <-> CPU\n"
<< "\tg - convert image to gray or not\n"
<< "\t1/q - increase/decrease HOG scale\n"
<< "\t2/w - increase/decrease levels count\n"
<< "\t3/e - increase/decrease HOG group threshold\n"
<< "\t4/r - increase/decrease hit threshold\n"
<< endl;
use_gpu = true;
make_gray = args.make_gray;
scale = args.scale;
gr_threshold = args.gr_threshold;
nlevels = args.nlevels;
if (args.hit_threshold_auto)
args.hit_threshold = args.win_width == 48 ? 1.4 : 0.;
hit_threshold = args.hit_threshold;
gamma_corr = args.gamma_corr;
/*
if (args.win_width != 64 && args.win_width != 48)
args.win_width = 64;*/
cout << "Scale: " << scale << endl;
if (args.resize_src)
cout << "Resized source: (" << args.width << ", " << args.height << ")\n";
cout << "Group threshold: " << gr_threshold << endl;
cout << "Levels number: " << nlevels << endl;
cout << "Win width: " << args.win_width << endl;
cout << "Win stride: (" << args.win_stride_width << ", " << args.win_stride_height << ")\n";
cout << "Hit threshold: " << hit_threshold << endl;
cout << "Gamma correction: " << gamma_corr << endl;
cout << endl;
}
void App::run()
{
FileStorage fs("/home/ubuntu/Desktop/implemenatation/vecSupport.yml", FileStorage::READ);
vector<float> detector;
int frameCount;
fs["vector"] >> detector;
for (unsigned int i=0; i<detector.size(); i++)
{
std::cout << std::fixed << std::setprecision(10) << detector[i] << std::endl;
}
fs.release();
running = true;
cv::VideoWriter video_writer;
Size win_size(96,64); //(64, 128) or (48, 96)
Size win_stride(args.win_stride_width, args.win_stride_height);
// Create HOG descriptors and detectors here
/*
vector<float> detector;
if (win_size == Size(64, 128))
detector = cv::gpu::HOGDescriptor::getPeopleDetector64x128();
else
detector = cv::gpu::HOGDescriptor::getPeopleDetector48x96();*/
cv::gpu::HOGDescriptor gpu_hog(win_size, Size(16, 16), Size(8, 8), Size(8, 8), 9,
cv::gpu::HOGDescriptor::DEFAULT_WIN_SIGMA, 0.2, gamma_corr,
cv::gpu::HOGDescriptor::DEFAULT_NLEVELS);
cv::HOGDescriptor cpu_hog(win_size, Size(16, 16), Size(8, 8), Size(8, 8), 9, 1, -1,
HOGDescriptor::L2Hys, 0.2, gamma_corr, cv::HOGDescriptor::DEFAULT_NLEVELS);
gpu_hog.setSVMDetector(detector);
cpu_hog.setSVMDetector(detector);
while (running)
{
VideoCapture vc;
Mat frame;
if (args.src_is_video)
{
vc.open(args.src.c_str());
if (!vc.isOpened())
throw runtime_error(string("can't open video file: " + args.src));
vc >> frame;
}
else if (args.src_is_camera)
{
vc.open(args.camera_id);
if (!vc.isOpened())
{
stringstream msg;
msg << "can't open camera: " << args.camera_id;
throw runtime_error(msg.str());
}
vc >> frame;
}
else
{
frame = imread(args.src);
if (frame.empty())
throw runtime_error(string("can't open image file: " + args.src));
}
Mat img_aux, img, img_to_show;
gpu::GpuMat gpu_img;
// Iterate over all frames
while (running && !frame.empty())
{
workBegin();
// Change format of the image
if (make_gray) cvtColor(frame, img_aux, CV_BGR2GRAY);
else if (use_gpu) cvtColor(frame, img_aux, CV_BGR2BGRA);
else frame.copyTo(img_aux);
// Resize image
if (args.resize_src) resize(img_aux, img, Size(args.width, args.height));
else img = img_aux;
img_to_show = img;
gpu_hog.nlevels = nlevels;
cpu_hog.nlevels = nlevels;
vector<Rect> found;
// Perform HOG classification
hogWorkBegin();
if (use_gpu)
{
gpu_img.upload(img);
gpu_hog.detectMultiScale(gpu_img, found, hit_threshold, win_stride,
Size(0, 0), scale, gr_threshold);
}
else cpu_hog.detectMultiScale(img, found, hit_threshold, win_stride,
Size(0, 0), scale, gr_threshold);
hogWorkEnd();
// Draw positive classified windows
for (size_t i = 0; i < found.size(); i++)
{
Rect r = found[i];
rectangle(img_to_show, r.tl(), r.br(), CV_RGB(0, 255, 0), 3);
}
if (use_gpu)
putText(img_to_show, "Mode: GPU", Point(5, 25), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
else
putText(img_to_show, "Mode: CPU", Point(5, 25), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
putText(img_to_show, "FPS (HOG only): " + hogWorkFps(), Point(5, 65), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
putText(img_to_show, "FPS (total): " + workFps(), Point(5, 105), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
imshow("opencv_gpu_hog", img_to_show);
if (args.src_is_video || args.src_is_camera) vc >> frame;
workEnd();
if (args.write_video)
{
if (!video_writer.isOpened())
{
video_writer.open(args.dst_video, CV_FOURCC('x','v','i','d'), args.dst_video_fps,
img_to_show.size(), true);
if (!video_writer.isOpened())
throw std::runtime_error("can't create video writer");
}
if (make_gray) cvtColor(img_to_show, img, CV_GRAY2BGR);
else cvtColor(img_to_show, img, CV_BGRA2BGR);
video_writer << img;
}
handleKey((char)waitKey(3));
}
}
}
void App::handleKey(char key)
{
switch (key)
{
case 27:
running = false;
break;
case 'm':
case 'M':
use_gpu = !use_gpu;
cout << "Switched to " << (use_gpu ? "CUDA" : "CPU") << " mode\n";
break;
case 'g':
case 'G':
make_gray = !make_gray;
cout << "Convert image to gray: " << (make_gray ? "YES" : "NO") << endl;
break;
case '1':
scale *= 1.11;
cout << "Scale: " << scale << endl;
break;
case 'q':
case 'Q':
scale /= 1.11;
cout << "Scale: " << scale << endl;
break;
case '2':
nlevels++;
cout << "Levels number: " << nlevels << endl;
break;
case 'w':
case 'W':
nlevels = max(nlevels - 1, 1);
cout << "Levels number: " << nlevels << endl;
break;
case '3':
gr_threshold++;
cout << "Group threshold: " << gr_threshold << endl;
break;
case 'e':
case 'E':
gr_threshold = max(0, gr_threshold - 1);
cout << "Group threshold: " << gr_threshold << endl;
break;
case '4':
hit_threshold+=0.25;
cout << "Hit threshold: " << hit_threshold << endl;
break;
case 'r':
case 'R':
hit_threshold = max(0.0, hit_threshold - 0.25);
cout << "Hit threshold: " << hit_threshold << endl;
break;
case 'c':
case 'C':
gamma_corr = !gamma_corr;
cout << "Gamma correction: " << gamma_corr << endl;
break;
}
}
inline void App::hogWorkBegin() { hog_work_begin = getTickCount(); }
inline void App::hogWorkEnd()
{
int64 delta = getTickCount() - hog_work_begin;
double freq = getTickFrequency();
hog_work_fps = freq / delta;
}
inline string App::hogWorkFps() const
{
stringstream ss;
ss << hog_work_fps;
return ss.str();
}
inline void App::workBegin() { work_begin = getTickCount(); }
inline void App::workEnd()
{
int64 delta = getTickCount() - work_begin;
double freq = getTickFrequency();
work_fps = freq / delta;
}
inline string App::workFps() const
{
stringstream ss;
ss << work_fps;
return ss.str();
}
Problem:
I am not able to detect anything. Can someone look at my work and can let me know what I am doing wrong. Any suggestions would be valuable. Thank you. From last four weeks I am doing these steps over and over again.
P.S: You can find yaml files here and test images along with the annotations here
First of all, partition your data for cross-validation as suggested already. Second thing is that it is a good idea to use RBF kernel rather than Linear kernel. I highly doubt that a linear kernel can learn complex objects. A brief explanation is given here. Finally, experiment with the parameters. To do that, you need to check the limits of the parameter space, it's been a while since I haven't used SVMs therefore I cannot provide any details but a grid search with 20% cross-validation is a good start.
I have some code to draw a line between two points on an image which are selected by mouse, and then to display a histogram.
However, when I press q as required by code I get an error saying R6010 abort() has been called and saying VC++ run time error.
Please advise me how I can find this error.
#include <vector>
#include "opencv2/highgui/highgui.hpp"
#include <opencv\cv.h>
#include <iostream>
#include<conio.h>
using namespace cv;
using namespace std;
struct Data_point
{
int x;
unsigned short int y;
};
int PlotMeNow(unsigned short int *values, unsigned int nSamples)
{
std::vector<Data_point> graph(nSamples);
for (unsigned int i = 0; i < nSamples; i++)
{
graph[i].x = i;
graph[i].y = values[i];
}
cv::Size imageSize(5000, 500); // your window size
cv::Mat image(imageSize, CV_8UC1);
if (image.empty()) //check whether the image is valid or not
{
std::cout << "Error : Image cannot be created..!!" << std::endl;
system("pause"); //wait for a key press
return 0;
}
else
{
std::cout << "Good job : Image created successfully..!!" << std::endl;
}
// tru to do some ofesseting so the graph do not hide on x or y axis
Data_point dataOffset;
dataOffset.x = 20;
// we have to mirror the y axis!
dataOffset.y = 5000;
for (unsigned int i = 0; i<nSamples; ++i)
{
graph[i].x = (graph[i].x + dataOffset.x) * 3;
graph[i].y = (graph[i].y + dataOffset.y) / 200;
}
// draw the samples
for (unsigned int i = 0; i<nSamples - 1; ++i)
{
cv::Point2f p1;
p1.x = graph[i].x;
p1.y = graph[i].y;
cv::Point2f p2;
p2.x = graph[i + 1].x;
p2.y = graph[i + 1].y;
cv::line(image, p1, p2, 'r', 1, 4, 0);
}
cv::namedWindow("MyWindow1", CV_WINDOW_AUTOSIZE); //create a window with the name "MyWindow"
cv::imshow("MyWindow1", image); //display the image which is stored in the 'img' in the "MyWindow" window
while (true)
{
char c = cv::waitKey(10);
if (c == 'q')
break;
}
destroyWindow("MyWindow1");
destroyWindow("MyWindow"); //destroy the window with the name, "MyWindow"
return 0;
}
void IterateLine(const Mat& image, vector<ushort>& linePixels, Point p2, Point p1, int* count1)
{
LineIterator it(image, p2, p1, 8);
for (int i = 0; i < it.count; i++, it++)
{
linePixels.push_back(image.at<ushort>(it.pos())); //doubt
}
*count1 = it.count;
}
//working line with mouse
void onMouse(int evt, int x, int y, int flags, void* param)
{
if (evt == CV_EVENT_LBUTTONDOWN)
{
std::vector<cv::Point>* ptPtr = (std::vector<cv::Point>*)param;
ptPtr->push_back(cv::Point(x, y));
}
}
void drawline(Mat image, std::vector<Point>& points)
{
cv::namedWindow("Output Window");
cv::setMouseCallback("Output Window", onMouse, (void*)&points);
int X1 = 0, Y1 = 0, X2 = 0, Y2 = 0;
while (1)
{
cv::imshow("Output Window", image);
if (points.size() > 1) //we have 2 points
{
for (auto it = points.begin(); it != points.end(); ++it)
{
}
break;
}
waitKey(10);
}
//just for testing that we are getting pixel values
X1 = points[0].x;
X2 = points[1].x;
Y1 = points[0].y;
Y2 = points[1].y;
// Draw a line
line(image, Point(X1, Y1), Point(X2, Y2), 'r', 2, 8);
cv::imshow("Output Window", image);
//exit image window
while (true)
{
char c = cv::waitKey(10);
if (c == 'q')
break;
}
destroyWindow("Output Window");
}
void show_histogram_image(Mat img1)
{
int sbins = 65536;
int histSize[] = { sbins };
float sranges[] = { 0, 65536 };
const float* ranges[] = { sranges };
cv::MatND hist;
int channels[] = { 0 };
cv::calcHist(&img1, 1, channels, cv::Mat(), // do not use mask
hist, 1, histSize, ranges,
true, // the histogram is uniform
false);
double maxVal = 0;
minMaxLoc(hist, 0, &maxVal, 0, 0);
int xscale = 10;
int yscale = 10;
cv::Mat hist_image;
hist_image = cv::Mat::zeros(65536, sbins*xscale, CV_16UC1);
for int s = 0; s < sbins; s++)
{
float binVal = hist.at<float>(s, 0);
int intensity = cvRound(binVal * 65535 / maxVal);
rectangle(hist_image, cv::Point(s*xscale, hist_image.rows),
cv::Point((s + 1)*xscale - 1, hist_image.rows - intensity),
cv::Scalar::all(65535), 1);
}
imshow("Histogram", hist_image);
waitKey(0);
}
int main()
{
vector<Point> points1;
vector<ushort>linePixels;
Mat img = cvLoadImage("desert.jpg");
if (img.empty()) //check whether the image is valid or not
{
cout << "Error : Image cannot be read..!!" << endl;
system("pause"); //wait for a key press
return -1;
}
//Draw the line
drawline(img, points1);
//now check the collected points
Mat img1 = cvLoadImage("desert.jpg");
if (img1.empty()) //check whether the image is valid or not
{
cout << "Error : Image cannot be read..!!" << endl;
system("pause"); //wait for a key press
return -1;
}
int *t = new int;
IterateLine( img1, linePixels, points1[1], points1[0], t );
PlotMeNow(&linePixels[0], t[0]);
show_histogram_image(img);
delete t;
_getch();
return 0;
}
This is one of the bad smells in your code:
void IterateLine(const Mat& image, vector<ushort>& linePixels, Point p2, Point p1, int* count1)
{
...
linePixels.push_back(image.at<ushort>(it.pos())); //doubt
Now image is a CV_8UC3 image (from Mat img1 = cvLoadImage("desert.jpg");, but you are accessing here like it is CV_16UC1, so what gets put in linePixels is garbage. This will almost certainly cause PlotMeNow() to draw outside its image and corrupt something, which is probably why your code is crashing.
Sine it is very unclear what your code is trying to do, I can't suggest what you should have here instead.
I have just managed to do this, you only have to put "-1" to your loop limit:
for (unsigned int i = 0; i < nSamples-1; i++)
{
graph[i].x = i;
graph[i].y = values[i];
}
Ok, so I've decided that using a histogram of oriented gradients is a better method for image fingerprinting vs. creating a histogram of sobel derivatives. I think I finally have it mostly figured out but when I test my code I get the following:
OpenCV Error: Assertion failed ((winSize.width - blockSize.width) % blockStride.width == 0 && (winSize.height - blockSize.height) % blockStride.height == 0).
As of now I'm just trying to figure out how to compute the HOG correctly and see the results; but not visually, I just want some very basic output to see if the HOG was created. Then I'll figure out how to use it in image comparison.
Here is my sample code:
using namespace cv;
using namespace std;
int main(int argc, const char * argv[])
{
// Initialize string variables.
string thePath, img, hogSaveFile;
thePath = "/Users/Mikie/Documents/Xcode/images/";
img = thePath + "HDimage.jpg";
hogSaveFile = thePath + "HDimage.yml";
// Create mats.
Mat src;
// Load image as grayscale.
src = imread(img, CV_LOAD_IMAGE_GRAYSCALE);
// Verify source loaded.
if(src.empty()){
cout << "No image data. \n ";
return -1;
}else{
cout << "Image loaded. \n" << "Size: " << src.cols << " X " << src.rows << "." << "\n";
}
// Initialize float variables.
float imgWidth, imgHeight, newWidth, newHeight;
imgWidth = src.cols;
imgHeight = src.rows;
newWidth = 320;
newHeight = (imgHeight/imgWidth)*newWidth;
Mat dst = Mat::zeros(newHeight, newWidth, CV_8UC3);
resize(src, dst, Size(newWidth, newHeight), CV_INTER_LINEAR);
// Was resize successful?
if (dst.rows < src.rows && dst.cols < src.cols) {
cout << "Resize successful. \n" << "New size: " << dst.cols << " X " << dst.rows << "." << "\n";
} else {
cout << "Resize failed. \n";
return -1;
}
vector<float>theHOG(Mat dst);{
if (dst.empty()) {
cout << "Image lost. \n";
} else {
cout << "Setting up HOG. \n";
}
imshow("Image", dst);
bool gammaC = true;
int nlevels = HOGDescriptor::DEFAULT_NLEVELS;
Size winS(newWidth, newHeight);
// int block_size = 16;
// int block_stride= 8;
// int cell_size = 8;
int gbins = 9;
vector<float> descriptorsValues;
vector<Point> locations;
HOGDescriptor hog(Size(320, 412), Size(16, 16), Size(8, 8), Size(8, 8), gbins, -1, HOGDescriptor::L2Hys, 0.2, gammaC, nlevels);
hog.compute(dst, descriptorsValues, Size(0,0), Size(0,0), locations);
printf("descriptorsValues.size() = %ld \n", descriptorsValues.size()); //prints 960
for (int i = 0; i <descriptorsValues.size(); i++) {
cout << descriptorsValues[i] << endl;
}
}
cvWaitKey(0);
return 0;
}
As you can see, I messed around with different variables to define the sizes but to no avail so, I commented them out and tried manually setting them. Still nothing. What am I doing wrong? Any help will be greatly appreciated.
Thank you!
You are initializing the HOGDescriptor incorrectly.
The assertion states that each of the first three input parameters must satisfy the constraint:
(winSize - blockSize) % blockStride == 0
in both height and width dimensions.
The problem is that winSize.height does not satisfy this constraint, considering the other parameters you initialize hog with:
(412 - 16) % 8 = 4 //Problem!!
Probably the simplest fix is to increase your window dimensions from cv::Size(320,412) to something divisible by 8, perhaps cv::Size(320,416), but the specific size will depend on your specific requirements. Just pay attention to what the assertion is saying!