Abstract
Traditional observational posture evaluation methods stress on sampling approach for continuous evaluation of dynamic postures in any activity. Hence, the quality of results from such evaluations is under debate. This article proposes a Video Image-based Posture Assessment (VIPA) method as a highly capable one for assessing an activity requiring dynamic postures of workers. This article explains the various steps of VIPA and its application for (i) the extraction and classification of postures into different categories based on the instructed posture classes from 10 videos of soil loosening activity having 48,715 postures and (ii) the use of OWAS to evaluate the postures. VIPA relies on traditional posture evaluation methods. The results indicate that VIPA could identify precarious postures 30% of the activity duration; these results were found to be accurate and reliable because there is no sampling method involved. The capability of VIPA method is proven through the activity studied.
Acknowledgements
We would like to express our sincere gratitude to Dr. Meena J. Panikker (Associate Professor in English, P. A. First Grade College, Mangalore, Karnataka, India) for her valuable and constructive suggestions in the edition of the English language. Her willingness to give her time generously for the discussions has been much appreciated.
Authors’ contributions
Kiran Mohan: Data Collection, Data Analysis, Coding, Manuscript Preparation; Dr. V. Madhusudanan Pillai: Data Collection, Data Analysis, Manuscript Preparation, Research Design/Guidance; Pujara Dhaval Jayendrakumar: Data Collection, Coding; Dr. Praveen Sankaran: Research Design/Guidance; Dr. Arun C.: Research Design/Guidance.
Availability of data and material
All the data related to the manuscript and other finding of this study are available from the corresponding author upon request.
Code availability
All the codes related to this study are available from the corresponding author upon request.
Consent to participate
All research participants have given their permission to be part of this study.
Consent for publication
Personal details of participants are not included in the manuscript. All research participants have given their permission to publish the collected data.
Disclosure statement
No potential conflict of interest was reported by the authors.
Ethics approval
Relevant approval has been taken from the competent authority.
Additional information
Funding
Notes on contributors
Kiran Mohan
Kiran Mohan is a research scholar in Mechanical Engineering Department at National Institute of Technology Calicut, Kerala. He has done his post-graduation in Industrial Engineering and Management from National Institute of Technology Calicut in 2013. He completed his graduation in Mechanical Engineering from Calicut University in 2010.
V. Madhusudanan Pillai
V. Madhusudanan Pillai is currently a professor in the Department of Mechanical Engineering, National Institute of Technology Calicut, India. He received B.Tech. in Mechanical Engineering from the University of Kerala in 1988. His M.Tech. in Industrial Engineering (1991) and PhD in Industrial Engineering (2005) are from University of Calicut, India. He has more than 140 publications in peer reviewed journals, conferences and book chapters. His current research interest focuses on application of modern tools in ergonomics, and machine learning and block chain technology applications in supply chain management.
Pujara Dhaval Jayendrakumar
Dhaval Jayendrakumar Pujara received the degree of B.E. from Gujarat Technological University, Gujarat, in 2010. He completed his M.Tech. in Industrial Engineering and Management from the Mechanical Engineering Department, National Institute of Technology Calicut, Kerala.
Praveen Sankaran
Praveen Sankaran is an assistant professor in the Department of Electronics and Communication Engineering at National Institute of Technology Calicut (NITC), Kerala. Prior to joining NITC, he was a post-doctoral researcher in the Computational Intelligence and Machine Vision Laboratory (ODU Vision Lab) at Old Dominion University. He was also an adjunct faculty in the Electrical and Computer Engineering (ECE) Department at Old Dominion University. He received his Bachelor of Technology in Applied Electronics and Instrumentation Engineering from University of Calicut, in 2002 and Master of Science in Electrical Engineering from Old Dominion University, Norfolk, Virginia in 2005. He earned his Ph.D. in Electrical and Computer Engineering from Old Dominion University, Norfolk, Virginia in 2009. His current research focuses on nonlinear feature extraction methods for data classification.
Arun Chandramohan
Arun Chandramohan is currently a professor at National Institute of Construction Management and Research Goa campus. He received B.Tech. in Civil Engineering from University of Calicut, India in 1999. He received M.Tech. in Construction Engineering & Management) from College of Engineering, Guindy, India in 2001 and PhD in Construction Engineering in 2004 from College of Engineering, Guindy, India.