A Bayesian blackboard framework for activity recognition by simultaneous inference of hierarchical group structure, recursive activity definitions, and activity boundaries.
For details, see the paper: Ernesto Brau, Colin R. Dawson, Alfredo
Carillo, David Sidi and Clayton T. Morrison. Bayesian Inference of
Recursive Sequences of Group Activities from
Tracks, In Proceedings of the
Thirtieth AAAI Conference on Artificial Intelligence (AAAI),
2016.
https://arxiv.org/abs/1604.06970
This project was created as part of the DARPA Mind's Eye program.
Depends on the IVILab bbb sampler:
svn+ssh://vision/home/svn/src/projects/bbb
https://code.google.com/archive/p/ua-b3/