Multi-Type Activity Recognition in Robot-Centric Scenarios
This addresses the need for autonomous robots to detect and recognize diverse activity types simultaneously, though it appears incremental by extending existing methods to a unified framework.
The paper tackles the problem of recognizing multiple types of activities (e.g., single actions, interactions) in robot-centric scenarios, proposing a unified descriptor called Relation History Image (RHI) and achieving systematic evaluation on a new dataset and public datasets with comparisons to baselines.
Activity recognition is very useful in scenarios where robots interact with, monitor or assist humans. In the past years many types of activities -- single actions, two persons interactions or ego-centric activities, to name a few -- have been analyzed. Whereas traditional methods treat such types of activities separately, an autonomous robot should be able to detect and recognize multiple types of activities to effectively fulfill its tasks. We propose a method that is intrinsically able to detect and recognize activities of different types that happen in sequence or concurrently. We present a new unified descriptor, called Relation History Image (RHI), which can be extracted from all the activity types we are interested in. We then formulate an optimization procedure to detect and recognize activities of different types. We apply our approach to a new dataset recorded from a robot-centric perspective and systematically evaluate its quality compared to multiple baselines. Finally, we show the efficacy of the RHI descriptor on publicly available datasets performing extensive comparisons.