Logistic Activity Recognition Challenge (LARa Version 01) – A Motion Capture and Inertial Measurement Dataset

Niemann, Friedrich; Reining, Christopher; Rueda, Fernando Moya; Altermann, Erik; Nair, Nilah Ravi; Steffens, Janine Anika; Fink, Gernot A.; Hompel, Michael ten

doi:10.5281/zenodo.3862782

Cited by 8 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The output layer has 19 units, corresponding to 19 movement attributes, and a sigmoid activation function. We did not perform any training of the network, but used the pre-trained network available at [ 17 ], which was trained on the LARa [ 8 ] dataset.…”

Section: Activity Recognition Methodologymentioning

confidence: 99%

“…The CAARL dataset is based on the set-up of the freely available logistics dataset LARa [ 8 , 17 ]. Both datasets were recorded in the same laboratory environment and contain the same scenarios.…”

Section: Related Workmentioning

confidence: 99%

“…In logistics, context-aware activity recognition is unexplored, which is also reflected in the existing datasets. Logistic datasets, such as [ 17 , 18 ], only contain sensor data of human movements. Specifically, it has not been investigated systematically which context data is most relevant in (intra-)logistics to increase HAR performance.…”

Section: The Caarl Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Context-Aware Human Activity Recognition in Industrial Processes

Niemann

Lüdtke

Bartelt

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Activity Recognition Methodologymentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%