User's profile - activity

I build in new directory and it works

Yes, I update my question

@pklab It doesn't work too :((( I was able to capture 640x480 at Linux with libv4l2cam library, but at Windows it doesn't work

@pklab Thank you for detailed explanaition and answer. But as I mentioned I try with 10 FPS even with 5, it says "unable grab from some Cam." because capR.read(imgR) gives false

I streoCalibrate Minoru 3d camera with OpenCV 3.1 and libcamm and I get the following error:

OpenCV Error: One of arguments' values is out of range (The specified aspect ratio (= cameraMatrix[0][0] / cameraMatrix[1][1]) is incorrect) in cvCalibrateCamera2, file /media/DATA1/libs/opencv 3.1/opencv/sources/modules/calib3d/src/calibration.cpp, line 1450 terminate called after throwing an instance of 'cv::Exception' what(): /media/DATA1/libs/opencv 3.1/opencv/sources/modules/calib3d/src/calibration.cpp:1450: error: (-211) The specified aspect ratio (= cameraMatrix[0][0] / cameraMatrix[1][1]) is incorrect in function cvCalibrateCamera2

Though the same code works fine when I do calibration in windows with OpenCV 2.3 with already captured images or standart VideoCapture

Camera supports 640x480 resolution, but at that resolution only one of the cameras works. I. e. capL.read(imgR) gives true and capR.read(imgR) gives false

But it works only for 320x240 resolution. Is it way to work for 640x480?

Thank you very much, it works :)) My problem was, that I didn't specified CV_CAP_DSHOW flag

use Minoru 3D stereocamera and want to capture images from left and right camera at the same time with OpenCV. I use Windows 7 64 bit

I have tried all solutions that I found in web, trying it with minoru drivers from CD and without.I try at 640x480 resolution with fps 15, even 5. I tried with standart OpenCV VideoCapture and also with videoInput library. But no one gives the expected result.

How can I run 2 Minoru cameras simultaneously?

@Eduardo: I do exactly what you say: if( point[2] < 10) this if means that

I can't get normal depth map from disparity. Here is my code:

#include "opencv2/core/core.hpp"
#include "opencv2/calib3d/calib3d.hpp"
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include "opencv2/contrib/contrib.hpp"
#include <cstdio>
#include <iostream>
#include <fstream>

using namespace cv;
using namespace std;

ofstream out("points.txt");

int main()
{
    Mat img1, img2;
    img1 = imread("images/im7rect.bmp");
    img2 = imread("images/im8rect.bmp");

    //resize(img1, img1, Size(320, 280));
    //resize(img2, img2, Size(320, 280));

    Mat g1,g2, disp, disp8;
    cvtColor(img1, g1, CV_BGR2GRAY);
    cvtColor(img2, g2, CV_BGR2GRAY);

    int sadSize = 3;
    StereoSGBM sbm;
    sbm.SADWindowSize = sadSize;
    sbm.numberOfDisparities = 144;//144; 128
    sbm.preFilterCap = 10; //63
    sbm.minDisparity = 0; //-39; 0
    sbm.uniquenessRatio = 10;
    sbm.speckleWindowSize = 100;
    sbm.speckleRange = 32;
    sbm.disp12MaxDiff = 1;
    sbm.fullDP = true;
    sbm.P1 = sadSize*sadSize*4;
    sbm.P2 = sadSize*sadSize*32;
    sbm(g1, g2, disp);

    normalize(disp, disp8, 0, 255, CV_MINMAX, CV_8U);

    Mat dispSGBMscale; 
    disp.convertTo(dispSGBMscale,CV_32F, 1./16); 

    imshow("image", img1);

    imshow("disparity", disp8);

    Mat Q;
    FileStorage fs("Q.txt", FileStorage::READ);
    fs["Q"] >> Q;
    fs.release();

    Mat points, points1;
    //reprojectImageTo3D(disp, points, Q, true);
    reprojectImageTo3D(disp, points, Q, false, CV_32F);
    imshow("points", points);

    ofstream point_cloud_file;
    point_cloud_file.open ("point_cloud.xyz");
    for(int i = 0; i < points.rows; i++) {
        for(int j = 0; j < points.cols; j++) {
            Vec3f point = points.at<Vec3f>(i,j);
            if(point[2] < 10) {
                point_cloud_file << point[0] << " " << point[1] << " " << point[2]
                    << " " << static_cast<unsigned>(img1.at<uchar>(i,j)) << " " << static_cast<unsigned>(img1.at<uchar>(i,j)) << " " << static_cast<unsigned>(img1.at<uchar>(i,j)) << endl;
            }
        }
    }
    point_cloud_file.close(); 

    waitKey(0);

    return 0;
}

My images are:

Disparity map:

I get smth like this point cloud:

Q is equal: [ 1., 0., 0., -3.2883545303344727e+02, 0., 1., 0., -2.3697290992736816e+02, 0., 0., 0., 5.4497170185417110e+02, 0., 0., -1.4446083962336606e-02, 0. ]

I tried many other things. I tried with different images, but no one is able to get normal depth map.

What am I doing wrong? Should I do with reprojectImageTo3D or use other approach instead of it? What is the best way to vizualize depth map? (I tried point_cloud library) Or could you provide me the working example with dataset and calibration info, that I could run it and get depth map. Or how can I get depth_map from middlebury stereo database (http://vision.middlebury.edu/stereo/d...), I think there isn't enough calibration info.