| Autor: |
Niemann F; Chair of Materials Handling and Warehousing, TU Dortmund University, Joseph-von-Fraunhofer-Str. 2-4, 44227 Dortmund, Germany., Lüdtke S; Institute for Enterprise Systems, University of Mannheim, L15 1, 68131 Mannheim, Germany., Bartelt C; Institute for Enterprise Systems, University of Mannheim, L15 1, 68131 Mannheim, Germany., Ten Hompel M; Chair of Materials Handling and Warehousing, TU Dortmund University, Joseph-von-Fraunhofer-Str. 2-4, 44227 Dortmund, Germany. |
| Jazyk: |
angličtina |
| Zdroj: |
Sensors (Basel, Switzerland) [Sensors (Basel)] 2021 Dec 25; Vol. 22 (1). Date of Electronic Publication: 2021 Dec 25. |
| DOI: |
10.3390/s22010134 |
| Abstrakt: |
The automatic, sensor-based assessment of human activities is highly relevant for production and logistics, to optimise the economics and ergonomics of these processes. One challenge for accurate activity recognition in these domains is the context-dependence of activities: Similar movements can correspond to different activities, depending on, e.g., the object handled or the location of the subject. In this paper, we propose to explicitly make use of such context information in an activity recognition model. Our first contribution is a publicly available, semantically annotated motion capturing dataset of subjects performing order picking and packaging activities, where context information is recorded explicitly. The second contribution is an activity recognition model that integrates movement data and context information. We empirically show that by using context information, activity recognition performance increases substantially. Additionally, we analyse which of the pieces of context information is most relevant for activity recognition. The insights provided by this paper can help others to design appropriate sensor set-ups in real warehouses for time management. |
| Databáze: |
MEDLINE |
| Externí odkaz: |
|
|
Nepřihlášeným uživatelům se plný text nezobrazuje |
K zobrazení výsledku je třeba se přihlásit.
|
