sustAGE User Postures & Actions Monitoring dataset

The sustAGE User Postures & Actions Monitoring dataset contains videos, data related to occurrences of ergonomic (body straining) postures as well as heart rate measurements of line workers during work activities in a realistic manufacturing environment. The time-synchronized data streams were captured during assembly tasks performed by real line workers in a realistic car door assembly production line in the premises of Stellantis --- Centro Ricerche FIAT (CRF)/SPW Research \& Innovation department in Melfi, Italy in the context of the sustAGE project.

The dataset can be used by methods that target the following research tasks: a) vision-based detection of worker’s ergonomically unhealthy (body straining) postures during assembly tasks according to the MURI risk analysis tool, b) vision-based recognition of human assembly actions, c) multi-modal analysis and forecasting of worker heart rate and physical fatigue based on heart rate measurements and the detection (annotated occurrences) of body straining postures during work activities. Each video shows a single line worker that performs a series of car door assembly activities, noted as a task cycle execution, for a specific workstation of the production line. A set of twelve task cycle executions performed by three different workers were captured using static StereoLabs ZED or ZED2 sensors. Each task cycle execution has a mean duration of 4 minutes. Moreover, time-synchronised data for the occurrences of body straining postures and worker heart rate are available for 8 work sessions. Each work session was recorded during morning or afternoon time of the work shift and regards 3 to 5 consecutive task cycle executions performed by the same line worker. Heart rate data was captured using a Garmin Vivoactive 3 smartwatch. Time annotations are available for the samples collected during the work sessions based on the Unix time (Epoch time) format.

Annotation data are available for twelve task cycle executions and contain the semantic labels and temporal boundaries of each assembly action and for the ergonomic risk scores of body straining postures performed by the line worker during each task cycle execution. Data was provided by experts in manufacturing and ergonomics based on the MURI risk analysis tool.

Documentation of this dataset can be found in [1].

If you use the dataset in your research work, you are kindly asked to cite [1] in your publications.

[1] Papoutsakis K, Papadopoulos G, Maniadakis M, Papadopoulos T, Lourakis M, Pateraki M, Varlamis I. Detection of Physical Strain and Fatigue in Industrial Environments Using Visual and Non-Visual Low-Cost Sensors. MDPI Technologies. 2022; 10(2):42. https://doi.org/10.3390/technologies10020042