Activity Recognition in Assembly Tasks by Bayesian Filtering in Multi-Hypergraphs
This work addresses activity recognition in manual work processes, which is an incremental improvement for industrial automation and monitoring.
The paper tackles the challenge of sensor-based human activity recognition in assembly tasks, where combinatorial explosion in system states makes Bayesian filtering difficult, by proposing an efficient Bayesian filtering model using multi-hypergraphs and graph rewriting rules, and demonstrates its applicability on a real dataset.
We study sensor-based human activity recognition in manual work processes like assembly tasks. In such processes, the system states often have a rich structure, involving object properties and relations. Thus, estimating the hidden system state from sensor observations by recursive Bayesian filtering can be very challenging, due to the combinatorial explosion in the number of system states. To alleviate this problem, we propose an efficient Bayesian filtering model for such processes. In our approach, system states are represented by multi-hypergraphs, and the system dynamics is modeled by graph rewriting rules. We show a preliminary concept that allows to represent distributions over multi-hypergraphs more compactly than by full enumeration, and present an inference algorithm that works directly on this compact representation. We demonstrate the applicability of the algorithm on a real dataset.