A wearable, self-calibrating, wireless sensor network for body motion processing

Lim, Kwang Yong; Goh, Frederick; Dong, Wei; Nguyen, Khoa D.; Chen, I‐Ming; Yeo, Song Huat; Duh, Henry Been-Lirn; Kim, Chung Gon

doi:10.1109/robot.2008.4543338

Cited by 13 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One can extract the information of lifting frequency from workers' body motion data. To this end, previous studies have concentrated on using a variety of wearable or optical sensors to precisely track body motion and localize their joint points simultaneously (Lim et al, 2008;Atrsaei et al, 2018;Sun et al, 2019). For example, a reflective marker of an optical motion tracking system can be attached to the human body for tracking three-dimensional (3D) coordinates of the key body joints with high accuracy.…”

Section: Introductionmentioning

confidence: 99%

A computer vision-based lifting task recognition method

Jung

Wang

et al. 2022

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

Low-back musculoskeletal disorders (MSDs) are major cause of work-related injury among workers in manual material handling (MMH). Epidemiology studies show that excessive repetition is one of major risk factors of low-back MSDs. Thus, it is essential to monitor the frequency of lifting tasks for an ergonomics intervention. In the current field practice, safety practitioners need to manually observe workers to identify their lifting frequency, which is time consuming and labor intensive. In this study, we propose a method that can recognize lifting actions from videos using computer vision and deep neural networks. An open-source package OpenPose was first adopted to detect bony landmarks of human body in real time. Interpolation and scaling techniques were then applied to prevent missing points and offset different recording environments. Spatial and temporal kinematic features of human motion were then derived. These features were fed into long short-term memory networks for lifting action recognition. The results show that the F1-score of the lifting action recognition is 0.88. The proposed method has potential to monitor lifting frequency in an automated way and thus could lead to a more practical ergonomics intervention.

show abstract

Section: Introductionmentioning

confidence: 99%