As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
The integration of image processing and deep learning has become a crucial aspect of industrial development. However, its usage is still limited in the field of motion and time study. This paper introduces the development of a comprehensive holistic detection algorithm using Python and OpenCV to detect the poses of workers during operations. The detected poses from the video are transformed into variables to calculate process performance metrics such as cycle time, working speed, and compliance rating with standard operating procedures. The algorithm’s performance was tested and evaluated through a series of scenarios using attribute agreement analysis theory. The statistical results showed that the proposed algorithm can provide similar motion and time study analysis as that of human observations. Thus, the proposed algorithm could help reduce the time needed for process improvement projects and promote remote work. The algorithm can also be applied in job training and detecting risky work motions to prevent accidents and injuries to workers.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.