Search options (Page 30 of 137)

Hola, quieres decir iPad?
No sé pero mejor escribe en el foro en español en un nuevo hilo.

Hi,
Thanks for reporting about this.

The distortion model is the one from OpenCV.
http://docs.opencv.org/doc/tutorials/ca … ation.html

Kinovea solves for the three coefficients k1, k2, k3 (radial distortion). And the others (p1, p2, tangential distortion, and fx, fy, cx, cy intrinsic parameters).

When you run the calibration the coefficients found will be written in the log and should be available in the camera calibration dialog.

I imagine there are two places where this process could fail, either in the initial calibration, or when applying it.

You may be right that only one view is sufficient. I think the idea with multiple views was to have data in all parts of the image, as if you have only one view there might be corners with no data if the pattern filmed is at an angle. I'm not sure why it would fail with multiple views though, it worked in the past. I'll have to retry it.

It should also be possible to automatically find the corners in the image and avoid the whole process of manually placing them.

You can also tweak the coefficients manually to find a good fit. In this case usually only k1 and k2 are used.

You can change the width of the lines, you need to edit the tool file though. I admit it's a bit thick.
Go to the program files and find \DrawingTools\Custom\openpose_body25.xml
In the section <Segments>...</Segments> find & replace width="4" by width="1" or something.

Unfortunately I can't really integrate OpenPose directly into Kinovea as it's only available for "academic or non-profit organization noncommercial research use" (per their license), which is incompatilbe with open source software.

And last time I looked the other projects doing posture estimation were also restricted to research purpose only for some reason.

Some more info about OpenPose in the documentation: https://www.kinovea.org/help/en/annotat … _data.html

Yes tracking is only done on the final video.

Hi,
Yes, this should work out of the box. Each instance has its own preferences file. When you click on the menu Options > Workspace > Save as default workspace, it saves the workspace directly in that instance's preferences files. So if you do that on your second instance, it will save it for your second instance only. Each instance will now have its own startup workspace.

If you want to experiment and backup your original workspace, you can go to Help > Open log folder to open the directory where the preferences are saved. You should see a "Preferences.xml" which is the master one, and "Preferences.2.xml" for your second instance (or another name if you start the instance with the name flag). You can copy the "Preferences.xml" somewhere else to back it up and then experiment with saving default workspace in various instances.

Another way with more control is to save the workspaces in external files instead of directly in the preferences, by using the menu "Export workspace". In this case you can create shortcuts in Windows for each instance and have them use a specific name and workspace file. This way it it's more explicit and doesn't rely on the sequence of launch.

Ciao,
Quando la versione 0.9.5 è stata publicata la traduzione al'italiano era troppo incompleta (in particolare il menu principale ed il player). È per questo che l'opzione non era disponibile nell'interfaccia. Diverse persone hanno lavorato a completare la traduzione e sara disponibile nella prossima versione.
(Scusatemi per le errore di lingua, ovviamente non è stato io a fare la tradduzione dell'interfaccia :-)).

Hi, it's only implemented for videos at the moment, not for single image files.