alfa_80's profile - activity

The output of solvePnP() is a rotation vector and a translation vector.

My question: Is this rotation vector representing roll, pitch, yaw in (whatever X-Y-Z order or similar) fixed angle convention? I guess it is, but I want to have a confirmation on this.

Thanks in advance.

@StevenPuttemans: Thanks for the information. I've appended the code snippet in the question.

I am using solvePnP() to compute for attitude(roll, pitch & yaw). From solvePnP() I got the rotation vector and I use this to accordingly get roll, pitch and yaw. But the problem is when I rotate the camera 45deg, the measurement gives 25deg.

I think, it might be that I need to integrate the angle value(each roll, pitch & yaw ) over time..am I right, integrating it will resolve the issue?

Thanks in advance.

EDIT

The code snippet:

pose[3] = -rot_vec.at(0);

pose[4] = -rot_vec.at(1);

pose[5] = -rot_vec.at(2);

Note: pose[] is roll, pitch & yaw respectively & rot_vec is raw value of rotation vector obtained from solvePnP()

Did you get a solution already? Perhaps you can share how you have fixed it.

It's long ago, I hope still remember. Actually, you just need to define some parameters in the default.xml. There is an image list there that you can set.

But, I think the translation that outputted from solvePnP() is in pixel unit.

By looking at the output, I received something like "Translation: -224.111 -494.222 781.111", each for case in X, Y and Z. But, why is it too high if I would interpret in meters for example. If it's in mm, it makes a little bit sense. Also, why do you actually mean by "depends on the unit of the 3D points you us", I just define some 3D points that is nothing to do with actual unit of measurement?

I would like to know about how I can record(logic behind writing a video file) a video taking an input frame by frame. I know that I can use the functionality offered by VideoWriter class, but I am constrained from using that class because of some unavoidable reasons.

Thanks in advance.

I would like to ask about the solvePnP() output of rotation and translation vectors. What is the unit of of them, are they radian & meter respectively?

Thanks in advance.

What is OpenCV equivalent to zxing image data structure like:

zxing::Ref<zxing::BitMatrix>

Or how do I convert from grey image of OpenCV(cv::Mat) to zxing's. Anyone familiar with OpenCV & zxing might want to help.

Thanks in advance.

How do I proceed once I have a feature points to compute pose estimation. For example, I guess I can use solvePnP(), but where to pass the feature points to the method. Also, what to pass to the first and second parameters(imagePoint and objectPoint)?

Thanks in advance.

I am having a problem of visualizing keypoints(corners) generated from cv::goodFeaturesToTrack(). Is there something similar to cv::drawKeypoints that I can use. I've tried to use it but it didn't work.

Thanks in advance.

BTW, is it OK to use PNG images? or won't be compatible..I'm just curious..

It's now working out of the box taking into consideration your thoughts..thanks anyway.

With what you pointed out, I did it, but still getting the re-projection error about 4.44602, which is pretty high.

Is that really mandatory to set "The size of a square in some user defined metric system (pixel, millimeter)", in the XML config file? I leave it as 50, how to benefit from it?

Regarding "It seems that problem "2" and "3" will be solved if you manage problem number one.", why is it complained in the first place, not even trying to take the recorded video input.

Thanks for the answer, what do you mean by "Also be carefull about the condition of photographing, they should be the same, specially 'Focal Lengths' and 'Resolution'"? Do you mean while recording the video or image sequences, I should be using the same camera and with fixed lighting condition?

I have been spending some time to get my camera calibration working using OpenCV module as documented here. In particular, I have 3 questions regarding this issue:

1. When using camera input by setting certain value in XML configuration file, I got it working but after the calibration, I got a worse(than the original input) output remapped image. Are there any configuration that I am not aware of?

   Is the following configuration important, if so, should I measure in mm scale:

   <!-- The size of a square in some user defined metric system (pixel, millimeter)-->
   <Square_Size>50</Square_Size>
   

2. When using image list or recorded video stream, I didn't get any working? Is there any trick, perhaps? It didn't even detect the corners in my chessboard calibration target. When using image list, it runs the image sequences, however, without detecting corners and eventually I received the following error:

   OpenCV Error: Bad argument (Unknown array type) in cvarrToMat, file /tmp/buildd/ros-fuerte-opencv2-2.4.2-1precise-20130312-1306/modules/core/src/matrix.cpp, line 697 terminate called after throwing an instance of 'cv::Exception' what(): /tmp/buildd/ros-fuerte-opencv2-2.4.2-1precise-20130312-1306/modules/core/src/matrix.cpp:697: error: (-5) Unknown array type in function cvarrToMat

3. When using recorded video stream, I always get the following error:

   OpenCV Error: Parsing error (output.avi(0): Too long string or a last string w/o newline) in icvXMLSkipSpaces
   

Thanks in advance.