I am a newbie in R, love it, but I am surprised by a complete lack of solid package to analyse motion capture data.
The simplest motion capture file is just a massive table with 'XYZ' coordinates for each point attached to a recorded subject, and for every frame captured. I know that I can find individual methods and functions in R to perform complex operations (like principal component analysis) or I can plot time series for all the points. But when I am looking for examples that could also educate me statistically about analysing human movement, and provide with nice toolbox for visual representation of data, R turns out to be a cold desert. On the other hand, MATLAB has Motion capture toolbox and MoCap Toolbox and especially the latter has quite good options for plotting and analysing the captures. But let's be honest - MATLAB has quite ugly visualisation engine comparing to R.
Some specific requests for R motion capture package would include:
Am I missing something here (in my Googling) or is there really no mocap packages out there for R? Have anyone tried playing with motion capture data in R? Can you give me some directions?
UPDATE, December 2019: It seems like the mocapr
package by Steen Harsted is a much more powerful tool than the one I built. Enjoy.
Have a look at my package, the mocap
package: https://github.com/gsimchoni/mocap
It is far from perfect but it's a start, currently tested only on CMU Graphics Lab Motion Capture Database ASF/AMC files.
And here is a blog post with some more details.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With