← All datasets

53+ hours of multimodal packaging work from 16 subjects: acceleration, gyro, quaternion, BVP, EDA, keypoints, LiDAR and depth. 20,129 annotated operations across 10 operation classes. Non-RGB is CC-BY-NC-SA; RGB is academic-use only.

Details

Subjects

n = 16

Protocol / load

Packaging operations (picking, box assembly, item insertion, scanning, labeling)

Equipment

4x IMU, 2x Empatica E4 (BVP/EDA), 2x depth camera, 1x LiDAR, barcode scanners

Formats

csv, json, mp4

License

CC-BY-NC-SA-4.0 (non-RGB); RGB under restrictive academic-only license

Keywords

logistics, packaging, activity-recognition, multimodal, non-commercial, iot

Added to catalog

2026-07-11

Cite

Cite the dataset as its authors request (check the source page for an official citation); this BibTeX is a convenience starting point.

@misc{openpack,
  author = {Yoshimura, N. and Morales, J. and Maekawa, T. and Hara, T.},
  title  = {{OpenPack: Packaging Work Recognition in IoT Logistics}},
  year   = {2024},
  url    = {https://open-pack.github.io/},
}