Compensation Method for Missing and Misidentified Skeletons in Nursing Care Action Assessment by Improving Spatial Temporal Graph Convolutional Networks DOI Creative Commons
Xin Han, Norihiro Nishida, Minoru MORITA

и другие.

Bioengineering, Год журнала: 2024, Номер 11(2), С. 127 - 127

Опубликована: Янв. 29, 2024

With the increasing aging population, nursing care providers have been facing a substantial risk of work-related musculoskeletal disorders (WMSDs). Visual-based pose estimation methods, like OpenPose, are commonly used for ergonomic posture assessment. However, these methods face difficulty when identifying overlapping and interactive tasks, resulting in missing misidentified skeletons. To address this, we propose skeleton compensation method using improved spatial temporal graph convolutional networks (ST-GCN), which integrates kinematic chain action features to assess integrity compensate it. The results verified effectiveness our approach optimizing skeletal loss misidentification leading accuracy calculating both joint angles REBA scores. Moreover, comparative analysis against other demonstrated superior performance approach, achieving an 87.34% score. Collectively, might hold promising potential tasks.

Язык: Английский

Compensation Method for Missing and Misidentified Skeletons in Nursing Care Action Assessment by Improving Spatial Temporal Graph Convolutional Networks DOI Creative Commons
Xin Han, Norihiro Nishida, Minoru MORITA

и другие.

Bioengineering, Год журнала: 2024, Номер 11(2), С. 127 - 127

Опубликована: Янв. 29, 2024

With the increasing aging population, nursing care providers have been facing a substantial risk of work-related musculoskeletal disorders (WMSDs). Visual-based pose estimation methods, like OpenPose, are commonly used for ergonomic posture assessment. However, these methods face difficulty when identifying overlapping and interactive tasks, resulting in missing misidentified skeletons. To address this, we propose skeleton compensation method using improved spatial temporal graph convolutional networks (ST-GCN), which integrates kinematic chain action features to assess integrity compensate it. The results verified effectiveness our approach optimizing skeletal loss misidentification leading accuracy calculating both joint angles REBA scores. Moreover, comparative analysis against other demonstrated superior performance approach, achieving an 87.34% score. Collectively, might hold promising potential tasks.

Язык: Английский

Процитировано

7