can you provide the session id so we can reproduce?

Thanks,
scott

Try again with the hrnet pose model. As of yesterday it is now the default, so just try collecting again. Make sure at least 2 cameras can see every body part.

For upper body kinematics, Id recommend using the hrnet pose model and the musculoskeletal model with ISB shoulder. These can be selected in Advanced Settings on the neutral pose page. This may solve the first two issues. Generally when the kinematics are inaccurate, it can be helpful to download th...

Hi Arafat, Yes, you can try running the neutral pose when seated, the scaled model will likely not be great since we assume standing-like hip-knee-ankle angles, but it should process. If it processes, you can then proceed with the collection and reprocess the data locally after the fact (https://git...

Hi Merve, you can maximize the plot or change the plotting code here if you like. https://github.com/stanfordnmbl/opencap ... D.py#L1844

Hi Denni, First off, I recommend using the HRNet pose estimation model (can select in Advanced Settings at bottom of page for static pose). This should help. The participant needs to stand straight and still for the calibration to go through, ideally ~3m from cameras. We have used the tool successfu...

updated it. Thanks!

here's a setup that worked well for us with 3 cameras. https://app.opencap.ai/session/6cb1cdf9 ... cc86bd5449

It depends how much occlusion there is. At least 2 cameras need to see every marker at all times. I recommend using the HRNet pose estimation model as well.

Hi Dani,

I wasn't able to replicate this error. Make sure you've pulled the latest version of the opencap-core code from github. If that doesn't solve it, could you provide me the list of session ids that I can use to reproduce the error?

Thanks,
Scott

Hi Tom, Thanks for your questions. A quick comment on volleyball - if you aren't already, I recommend recording at 120 or 240 Hz due to motion blur. We've found this helps with stop jumps. Re. kinetics. It should work to simulate a stop jump, but it will likely require iteration on the problem formu...