Logistic Activity Recognition Challenge (LARa Version 02) – A Motion Capture and Inertial Measurement Dataset

<strong>LARa</strong><strong> Version 02</strong> is a freely accessible logistics-dataset for human activity recognition. In the ’Innovationlab Hybrid Services in Logistics’ at TU Dortmund University, two picking and one packing scenarios with 16 subjects were recorded using an optical marker-based Motion Capturing system (OMoCap), Inertial Measurement Units (IMUs), and an RGB camera. Each subject was recorded for one hour (960 minutes in total). All the given data have been labeled and categorised into eight activity classes and 19 binary coarse-semantic descriptions, also called attributes. In total, the dataset contains 221 unique attribute representations. You can find the latest version of the annotation tool here: https://github.com/wilfer9008/Annotation_Tool_LARa <strong>Upgrade:</strong> Subject 15 and 16 added OMoCap raw data added (c3d, csv) Second IMU set added (MotionMiners Sensors) OMoCap data: file names from subject 01 to subject 06 corrected OMoCap data: additional annotated data added OMoCap and IMU data (Mbientlab and MotionMiners Sensors): Annotation errors corrected OMoCap Networks added (all for Window Size of 200 frames (1sec.)) tCNN_classes tCNN-IMU_classes tCNN_attrib tCNN-IMU_attrib Mbientlab Networks added (all for Window Size of 100 frames (1sec.)) tCNN_classes tCNN-IMU_classes tCNN_attrib tCNN-IMU_attrib Protocol extended (now README file) List of unique attribute representations added (csv) <strong>If you use this dataset for research, please cite the following paper: “LARa: Creating a Dataset for Human Activity Recognition in Logistics Using Semantic Attributes</strong><strong>”, Sensors 2020, DOI: 10.3390/s20154083.</strong> <strong>If you use the Mbientlab Networks, please cite the following paper: “From Human Pose to On-Body Devices for Human-Activity Recognition”, 25th International Conference on Pattern Recognition (ICPR), 2021, DOI: </strong><strong>10.1109/ICPR48806.2021.9412283</strong><strong>.</strong> If you have any questions about the dataset, please contact <strong>[e-mail].</strong>