Abstract
Optimizations in logistics require recognition and analysis of human activities. The potential of sensor-based human activity recognition (HAR) in logistics is not yet well explored. Despite a significant increase in HAR datasets in the past twenty years, no available dataset depicts activities in logistics. This contribution presents the first freely accessible logistics-dataset. In the ’Innovationlab Hybrid Services in Logistics’ at TU Dortmund University, two picking and one packing scenarios were recreated. Fourteen subjects were recorded individually when performing warehousing activities using Optical marker-based Motion Capture (OMoCap), inertial measurement units (IMUs), and an RGB camera. A total of 758 min of recordings were labeled by 12 annotators in 474 person-h. All the given data have been labeled and categorized into 8 activity classes and 19 binary coarse-semantic descriptions, also called attributes. The dataset is deployed for solving HAR using deep networks.
Highlights
Human activity recognition (HAR) assigns human action labels to signals of movements
Signals are time series that are obtained from video-frames, marked-based motion capturing systems (Mocap), or inertial measurements
This paper introduces a novel and large dataset for human activity recognition (HAR) in the context of logistics
Summary
Human activity recognition (HAR) assigns human action labels to signals of movements. One major reason for this is the lack of freely accessible and usable datasets that contain industrial work-processes This is because industrial environments such as factories and warehouses pose a challenge for data recording. This paper explains in detail the recording scenarios, sensors settings, and the annotation process It presents the performance of employing deep architectures for solving HAR on the provided dataset. The detailed annotation of these attributes leads to a total of 204 unique attribute representations for the 8 activity classes This high level of granularity is the prerequisite for evaluating different activity recognition approaches. The contribution answers the following research questions in the context of the first freely accessible logistics HAR dataset—Logistic Activity Recognition Challenge (LARa): 2. Based on the datasets’ descriptions, the guideline for creating the novel dataset in Section 3 is derived
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
