dberga's profile - activity

Histogram backprojection on other spaces I have been trying the histogram backprojection with the image convolved with s

If I build a platform that would detect different pattern markers using findCirclesGrid in a monochrome image, how would I know which rotation does every circle grid (marker) has?

And if I detect that marker with multiple cameras and I do the 3D reconstruction, how would I know the marker's X rotation, Y rotation and Z rotation if I have the intrinsic and extrinsic parameters for each camera?

I tried with the WAY2 and works, nevermind folks (I forgot an instantiation, now seems to be fixed)

If I'm using a class with functions to instanciate the SimpleBlobDetector params I get the error so that the params is protected. I tried 2 ways for the usage of SimpleBlobDetector but both fail.

WAY 1

class Foo{

 public:    
Foo();     
virtual ~Foo();

private:   
 cv::SimpleBlobDetector * detector;   
 }



Foo::~Foo(){ 
}

Foo::Foo(){
    detector = new cv::SimpleBlobDetector();
    detector->create("SimpleBlobDetector");

    detector->params.minThreshold = 40;
    detector->params.maxThreshold = 60;
    detector->params.thresholdStep = 5;
    detector->params.minArea = 10;
    detector->params.minConvexity = .4f;
    detector->params.minInertiaRatio = .1f;
    detector->params.maxArea = 8000;
    detector->params.maxConvexity = 2;
    detector->params.filterByColor = false;
    detector->params.filterByCircularity = false;
}

WAY 2

class Foo{

 public:    
Foo();     
virtual ~Foo();

private:   
 cv::SimpleBlobDetector detector;   
 cv::SimpleBlobDetector::Params dparams;
 }



Foo::~Foo(){ 
}

Foo::Foo(){

    dparams.minThreshold = 40;
    dparams.maxThreshold = 60;
    dparams.thresholdStep = 5;
    dparams.minArea = 10;
    dparams.minConvexity = .4f;
    dparams.minInertiaRatio = .1f;
    dparams.maxArea = 8000;
    dparams.maxConvexity = 2;
    dparams.filterByColor = false;
    dparams.filterByCircularity = false;
    detector = cv::SimpleBlobDetector( dparams);
    detector->create("SimpleBlobDetector");


}

How can I use SimpleBlobDetector in an object-based way? (considering the params as an attribute)

SOLUTION: adjust de flags parameter

I'm dealing with two cameras and I played CalibrateCamera, it returned me correct distCoeffs, CameraMatrix, tvecs and rvecs values for each camera. The results seemed to be correct

Then I realised that for dealing with 3D triangulation of points I would need stereoCalibrate instead, so I tried it and it doesn't work, it returns zero values for each Output parameter. I verified previously that ImagePoints for each camera were correct but see the results:

Why? Because I see the stereoCalibrate returned 0 values for each Output parameter. How can I solve that? Should I use an alternative of using stereoCalibrate?

PD: I'm using the default extra flags or criteria parameters. I'm using version 2.4.6 with mingw with the following documentation http://docs.opencv.org/2.4.6/modules/calib3d/doc/camera_calibration_and_3d_reconstruction.html#stereocalibrate

As well is known, the VideoCapture recognises the device id as the cameras are connected. For example, if I have a webcam and two cameras, the devices would be 1,2 and 3 (maybe). But what I wanna know how to get unique identificators per camera. I mean, if I connect the cameras in another way in the future, the device id would be changed as 1,3 and 2. But I don't want that, I want the devices to have unique serial identificators for saving captured data and stuff from the concrete camera.

So, how can I get the "serial id" or "unique id" for each camera?

Thanks in advance