Kalman filter dengan opencv

berikut ini implementasi kalman filter menggunakan open cv, selamat mencoba
-----------------------------------------------------------------------------------------------
hasilnya

-----------------------------------------------------------------------------------------------
#include "opencv2/video/tracking.hpp"
#include "opencv2/highgui/highgui.hpp"
#include <stdio.h>
using namespace cv;

static inline Point calcPoint(Point2f center, double R, double angle)
{
    return center + Point2f((float)cos(angle), (float)-sin(angle))*(float)R;
}

static void help()
{
   printf( "\nExamle of c calls to OpenCV's Kalman filter.\n"
"   Tracking of rotating point.\n"
"   Rotation speed is constant.\n"
"   Both state and measurements vectors are 1D (a point angle),\n"
"   Measurement is the real point angle + gaussian noise.\n"
"   The real and the estimated points are connected with yellow line segment,\n"
"   the real and the measured points are connected with red line segment.\n"
"   (if Kalman filter works correctly,\n"
"    the yellow segment should be shorter than the red one).\n"
            "\n"
"   Pressing any key (except ESC) will reset the tracking with a different speed.\n"
"   Pressing ESC will stop the program.\n"
            );
}

int main(int, char**)
{
    help();
    Mat img(500, 500, CV_8UC3);
    KalmanFilter KF(2, 1, 0);
    Mat state(2, 1, CV_32F); /* (phi, delta_phi) */
    Mat processNoise(2, 1, CV_32F);
    Mat measurement = Mat::zeros(1, 1, CV_32F);
    char code = (char)-1;

    for(;;)
    {
        randn( state, Scalar::all(0), Scalar::all(0.1) );
        KF.transitionMatrix = *(Mat_<float>(2, 2) << 1, 1, 0, 1);

        setIdentity(KF.measurementMatrix);
        setIdentity(KF.processNoiseCov, Scalar::all(1e-5));
        setIdentity(KF.measurementNoiseCov, Scalar::all(1e-1));
        setIdentity(KF.errorCovPost, Scalar::all(1));

        randn(KF.statePost, Scalar::all(0), Scalar::all(0.1));

        for(;;)
        {
            Point2f center(img.cols*0.5f, img.rows*0.5f);
            float R = img.cols/3.f;
            double stateAngle = state.at<float>(0);
            Point statePt = calcPoint(center, R, stateAngle);

            Mat prediction = KF.predict();
            double predictAngle = prediction.at<float>(0);
            Point predictPt = calcPoint(center, R, predictAngle);
 
            randn( measurement, Scalar::all(0), Scalar::all(KF.measurementNoiseCov.at<float>(0)));
 
            // generate measurement
            measurement += KF.measurementMatrix*state;

            double measAngle = measurement.at<float>(0);
            Point measPt = calcPoint(center, R, measAngle);

             // plot points
            #define drawCross( center, color, d )                                 \
            line( img, Point( center.x - d, center.y - d ),                \
                               Point( center.x + d, center.y + d ), color, 1, CV_AA, 0); \
            line( img, Point( center.x + d, center.y - d ),                \
                              Point( center.x - d, center.y + d ), color, 1, CV_AA, 0 )

            img = Scalar::all(0);
            drawCross( statePt, Scalar(255,255,255), 3 );
            drawCross( measPt, Scalar(0,0,255), 3 );
            drawCross( predictPt, Scalar(0,255,0), 3 );
            line( img, statePt, measPt, Scalar(0,0,255), 3, CV_AA, 0 );
            line( img, statePt, predictPt, Scalar(0,255,255), 3, CV_AA, 0 );

            if(theRNG().uniform(0,4) != 0)
                KF.correct(measurement);
 
            randn( processNoise, Scalar(0), Scalar::all(sqrt(KF.processNoiseCov.at<float>(0, 0))));
            state = KF.transitionMatrix*state + processNoise;
 
            imshow( "Kalman", img );
            code = (char)waitKey(100);
 
            if( code > 0 )
                break;
        }
         if( code == 27 || code == 'q' || code == 'Q' )
           break;
    }

   return 0;
}

Cluster Menggunakan metode K-means dengan opencv

kali ini mencoba melakukan cluster menggunakan metode k-means. cluster sendiri bertujuan untuk mengngelompokan dari suatu data yang memiliki kemiripan fitur antar setiap data, banyak implemntasi dari cluster ini yaitu pada Inteleggent transportationn system dll, berikut hasil dan source codenya....selamat mencoba (ika butuh penjelasan lebih lanjut silahkan hub via email).....
--------------------------------------------------------------------------------------------------
hasilnya (silahkan perbesar)

--------------------------------------------------------------------------------------------------
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/core/core.hpp"
#include <iostream>

using namespace cv;
using namespace std;

// static void help()
// {
//     cout << "\nThis program demonstrates kmeans clustering.\n"
//             "It generates an image with random points, then assigns a random number of cluster\n"
//             "centers and uses kmeans to move those cluster centers to their representitive location\n"
//             "Call\n"
//             "./kmeans\n" << endl;
// }

int main( int /*argc*/, char** /*argv*/ )
{
    const int MAX_CLUSTERS = 5;
    Scalar colorTab[] =
    {
        Scalar(0, 0, 255),
        Scalar(0,255,0),
        Scalar(255,100,100),
       

HSV, Gray, Biner, original

Kali ini mencoba image asli, di convert ke grey, diconvert ke biner, diconvert ke HSV....selamat mencoba

--------------------------------------------------------------------------------------------------------------------

#include <cv.h>

#include <highgui.h>

#include <cxcore.h>

using namespace std;

using namespace cv;

int main()

{

 IplImage *img = cvLoadImage("lenna.png");

 IplImage *hsv = cvCreateImage(cvGetSize(img), 8, 3);

 IplImage *gray = cvCreateImage(cvGetSize(img), IPL_DEPTH_8U, 1);

 IplImage *biner = cvCreateImage(cvGetSize(img), IPL_DEPTH_8U, 1);

 cvCvtColor(img, hsv, CV_RGB2HSV);

 cvCvtColor(img, gray, CV_RGB2GRAY);

 cvThreshold(gray, biner, 100, 255, CV_THRESH_BINARY);

 // print rgb values of first pixel

 int r = (int)img->imageData[0];

 int g = (int)img->imageData[1];

 int b = (int)img->imageData[2];