aless.mosca's profile - activity

Hello everybody, I'm new in OpenCV and in computer vision. I'm working with robots and I would like to make you a question. If I have an object (on the table for example), and I start turning around, or just moving along a straight path, in order to the get several images of that object from different point of view, and, knowing the relative rotations and translations (extracted from the robot, since the camera is mounted on) of each image respect to the previous one, is possible to estimate the distance of that object from the last point of view ? which kind of algorithm i should use ?

Thanks for the answer and for the help

yes, i know but since the are using almost the some function. Could you answer me as it was a opencv problem? Thanks

Hello, I'm working on the stereoCamera. what I've done is almost here (following the example)

CvInvoke.StereoCalibrate(corners_object_Points, corners_points_Left, corners_points_Right, cameraMatrix_left, distCoeff_left, cameraMatrix_right, distCoeff_right, left.Size, ext_param.RotationVector.RotationMatrix, ext_param.TranslationVector, essential, fundamental, Emgu.CV.CvEnum.CalibType.FixPrincipalPoint, new MCvTermCriteria(30, 0.01));

CvInvoke.StereoRectify(cameraMatrix_left, distCoeff_left, cameraMatrix_right, distCoeff_right, left.Size, ext_param.RotationVector.RotationMatrix, ext_param.TranslationVector, R1, R2, P1, P2, Q, StereoRectifyType.Default, 0, left.Size, ref rect_left, ref rect_right);

I would like to show the two images rectified in order to see if the process of calibration and rectification it was good or not. Is there some who can help me?

coould you suggest me any kind of post processing, please? Thanks

thanks for answering me. Since I'm using emgucv, the function cvInvoke.StereoCalibrate is a void function.

Hello all, I'm approaching to the ComputerVision and to OpenCV in these months. What I'm doing is create a stereo camera in order to obtain informations about an object (a cilindere more or less, with 4 cm of diameter and 8 cm height ) which should be manipulated by a robot. So through the depth map I would like to obtain the 3D position of the object. But first to do this, I would like to obtain a decent real time depth map. What I did is following the example contained in to the examples folder of Emgucv(i'm doing it in C#). there are few questions that I would to propose you:

• How can I be sure that the calibration process was good or not
• For computing the depth map I use the Semi Global Block Matching approach (StereoSGBM method), should I make some pre and/or post filtering to improve the quality of my depth map.

Below, a picture of my actual depth map

Thanks in advance