Motion Capture Benchmark of Real Industrial Tasks and Traditional Crafts for Human Movement Analysis

Article Green & Sustainable Science & Technology

Introducing VTT-ConIot: A Realistic Dataset for Activity Recognition of Construction Workers Using IMU Devices

Satu-Marja Makela et al.

Summary: This article introduces a new publicly available dataset, VTT-ConIoT, for evaluating human activity recognition in professional construction settings. The dataset includes data from 13 users and 16 different activities, and also provides a benchmark baseline for human activity recognition. The representativity and usefulness of the dataset is demonstrated by comparing it with data collected in a real construction environment.

SUSTAINABILITY (2022)

添加到收藏夹

Article Chemistry, Analytical

The WGD-A Dataset of Assembly Line Working Gestures for Ergonomic Analysis and Work-Related Injuries Prevention

Christian Tamantini et al.

Summary: The study emphasizes the importance of human movement monitoring in preventing musculoskeletal disorders through the proposed WGD-Working Gesture Dataset. By analyzing kinematic data, quantitative indicators can be extracted to assess working tasks and detect factors that may contribute to the onset of musculoskeletal disorders. The results show that these indicators can be used to early detect incorrect gestures and postures, ultimately preventing work-related disorders.

SENSORS (2021)

添加到收藏夹

Article Multidisciplinary Sciences

MoVi: A large multi-purpose human motion and video dataset

Saeed Ghorbani et al.

Summary: The dataset contains 9 hours of optical motion capture data, 17 hours of video data, and 6.6 hours of inertial measurement units data, which can be used for research on human pose estimation, action recognition, motion modeling, gait analysis, and body shape reconstruction.

PLOS ONE (2021)

添加到收藏夹

Article Construction & Building Technology