Sensor-based Pallet Activity Recognition in Logistics (SPARL Version 1) - A multi-modal Dataset

SPARL is a freely accessible data set for sensor-based activity recognition of pallets in logistics. The data set consists of 16 recordings. Three different sensors (MBIENTLAB MetaMotionS, MSR Electronics MSR 145, Kistler KiDaQ Module 5512A) were used simultaneously for all recordings. The recordings were accompanied by three cameras, of which two representative recordings are included anonymously in the data set. One scenario was executed rather slowly and the other faster in order to record different types of execution. The videos were annotated by one person in each frame. For this purpose, the annotation tool SARA was used, which can be found here: https://zenodo.org/records/8189341. The JSON schema used for annotation is also included in the SPARL dataset. The R code used our evaluation can be found in GitHub at https://github.com/bommert/ETFA24

If you have any questions about the dataset, please contact: sven.franke@tu-dortmund.de

If you use this dataset for research, please cite the following paper: “Smart pallets: Towards event detection using IMUs”, IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA), DOI: 10.1109/ETFA61755.2024.10710674.