The babyPose dataset

Lucia Migliorelli; Sara Moccia; Rocco Pietrini; Virgilio Paolo Carnielli; Emanuele Frontoni

doi:10.1016/j.dib.2020.106329

The babyPose dataset

Data Brief. 2020 Sep 26:33:106329. doi: 10.1016/j.dib.2020.106329. eCollection 2020 Dec.

Authors

Lucia Migliorelli¹, Sara Moccia^{1

2}, Rocco Pietrini¹, Virgilio Paolo Carnielli³, Emanuele Frontoni¹

Affiliations

¹ Department of Information Engineering, Università Politecnica delle Marche, Ancona (Italy).
² Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa (Italy).
³ Department of Neonatology, University Hospital Ancona, Università Politecnica delle Marche, Ancona, Italy.

Abstract

The database here described contains data relevant to preterm infants' movement acquired in neonatal intensive care units (NICUs). The data consists of 16 depth videos recorded during the actual clinical practice. Each video consists of 1000 frames (i.e., 100s). The dataset was acquired at the NICU of the Salesi Hospital, Ancona (Italy). Each frame was annotated with the limb-joint location. Twelve joints were annotated, i.e., left and right shoul- der, elbow, wrist, hip, knee and ankle. The database is freely accessible at http://doi.org/10.5281/zenodo.3891404. This dataset represents a unique resource for artificial intelligence researchers that want to develop algorithms to provide healthcare professionals working in NICUs with decision support. Hence, the babyPose dataset is the first annotated dataset of depth images relevant to preterm infants' movement analysis.

Keywords: Artificial intelligence; Depth images; Neonatal intensive care units; Pose estimation; Preterm infants.