With generic data structure and dynamic properties, various motion capture format can be loaded.
From data filtering to joint kinetics computation, various published processing methods are available.
Events detection, cycles normalization, and other tools might help you to explain your research hypotheses.
Designed to be simple to use but efficient and powerful, this library can be embedded in your existing workflow.
Because different implementation technic for the same algorithm can affect largely outcomes.
OpenMA wants to be simple to use, easily integrable in your existing workflow, and fast to execute.
All implemented algorithms are tested on different reference datasets to ensure results accuracy and quality.
Because teamwork is the best way to generate better results, OpenMA wants to facilitate exchange between teams.
Captured data can come from different acquisition systems, but at the end, the processing pipeline stays the same.
Started in 2009, reshaped in 2015, the project continues to evolve to improve movement analysis knowledge!
Python 2 & 3
Need more details? The documentation is a good start.
Having questions not answered? The support page might help you to find answers.
Found a bug? Want to contribute to the project? Go on GitHub.