← All datasets

vtt-coniot Open

VTT-ConIoT: Activity Recognition of Construction Workers with IMUs

Makela S.-M., Lamsa A., Keranen J.S., Liikka J., Ronkainen J., Peltola J., Haikio J., Bordallo Lopez M.

VTT Technical Research Centre of Finland / University of Oulu · 2021 · Finland

Realistic human activity recognition dataset for professional construction work: 13 subjects performing 16 recommended or non-recommended work activities with 10-DOF IMUs at three body positions, plus video-derived pose keypoints. Designed with construction-industry stakeholders and validated against real site conditions (doi:10.3390/su14010220).

IMUVideoAssemblyWalkingReaching
View source ↗DOI: 10.5281/zenodo.4683703

Details

Subjects
n = 13
Protocol / load
16 simulated construction-work activities (installation, painting, drilling, cleaning, climbing, walking) designed with building-industry stakeholders
Equipment
10-DOF wearable IMUs (accelerometer, gyroscope, magnetometer, barometer) at three body locations; body pose keypoints extracted from complementary video
Formats
csv
License
CC-BY-4.0
Keywords
construction, activity-recognition, har, wearable-sensors
Added to catalog
2026-08-25

Cite

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

@misc{vtt-coniot,
  author = {Makela, S.-M. and Lamsa, A. and Keranen, J.S. and Liikka, J. and Ronkainen, J. and Peltola, J. and Haikio, J. and Bordallo Lopez, M.},
  title  = {{VTT-ConIoT: Activity Recognition of Construction Workers with IMUs}},
  year   = {2021},
  doi    = {10.5281/zenodo.4683703},
  url    = {https://doi.org/10.5281/zenodo.4683703},
}