Ergonomic Analysis supported by Virtual Reality: a Systematic Literature Review

Silva, Adailton Gonçalves da; Winkler, Ingrid; Pinto, Ubiratan de Melo

doi:10.1109/svr51698.2020.00074

Cited by 9 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This systematic review followed the PRISMA guidelines [8] and the method described in [9] was used, which encompasses seven steps: Planning, Scoping, Searching, Assessing, Synthetizing, Analyzing, and Writing.…”

Section: Methodsmentioning

confidence: 99%

Virtual Reality and Digital Human Modeling for the Physical Ergonomic Analysis in Product Development in Industry: A Systematic Review

Silva¹,

Mendes²,

Winkler³

2021

Preprint

View full text Add to dashboard Cite

The efficacy of the product development process is measured by the ability to launch a project with product and production process specifications that could guarantee that the manufacturing can produce it with the least impact. If a problem is detected late, they bring consequences beyond the high cost of the solution, if related to physical ergonomics, which will influence the well-being of operators, productivity, and quality. Virtual Reality (VR) and Digital Human Modeling (DHM) are ones of the enabling technologies of Industry 4.0 and has already been applied on a large scale in industries such as automotive, construction, and aeronautics. However, even though the huge applications, these technologies are not yet applied by these industries for the analysis of physical ergonomics during product development phases. This study aims to characterize the state of the art and technology about the application of Virtual Reality and Digital Human Modeling for the physical ergonomics analysis in the during product development phases in the industry through a systematic review of the literature and patents. In patent documents recovery, we used Derwent Innovation database. The research is based on searching the selected terms in the title, summary, and claims of the documents through a search strategy containing IPC code and keywords. In articles recovery, we searched ScienceDirect, Springer, and IEEExplore databases for scientific publications. The search resulted in 311 patents documents and 16 articles in the scientific database. This study analyzed the patents to map out the technological progress in this area, where we found in the charts and data an increasing number of publications per year and a spread application with a considerable number of new technologies presented in these recent patents. The literature review indicated that Virtual Reality technology complements the Digital Human Modeling during physical ergonomics analysis for manufacturing process already designed. The majority of research on the use of VR and DHM technologies for physical ergonomics analysis focus on the automotive industry and the ergonomic assessment of workstations and current processes. Further research is needed to investigate how Virtual Reality and Digital Human Modeling might assist in the understanding of physical ergonomics in certain tasks throughout the product development process, such as the simulation of worker posture or effort when assembling parts.

show abstract

Section: Methodsmentioning

confidence: 99%

Virtual Reality and Digital Human Modeling for the Physical Ergonomic Analysis in Product Development in Industry: A Systematic Review

Silva¹,

Mendes²,

Winkler³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The accurate classification of human postures is key for a wide range of applications in different fields, from ergonomics to physical rehabilitation or sports. This process may require subjective and costly interpretation in terms of time and human resources and usually involves visual analysis of images or videos [1,2], digital human modelling [3], or the incorporation of virtual reality to analyze various postures in a controlled digital environment in real time [4]. In this context, the use of computer vision techniques to automate the detection and classification of postures is being widely used, often in combination with different types of "non-visual" sensors to improve the detection accuracy (e.g., motion sensors, gyroscopes, accelerometers, depth sensors, and pressure sensors).…”

Section: Introductionmentioning

confidence: 99%

Exploring the Use of Contrastive Language-Image Pre-Training for Human Posture Classification: Insights from Yoga Pose Analysis

Dobrzycki,

Bernardos,

Bergesio

et al. 2023

Mathematics

View full text Add to dashboard Cite

Accurate human posture classification in images and videos is crucial for automated applications across various fields, including work safety, physical rehabilitation, sports training, or daily assisted living. Recently, multimodal learning methods, such as Contrastive Language-Image Pretraining (CLIP), have advanced significantly in jointly understanding images and text. This study aims to assess the effectiveness of CLIP in classifying human postures, focusing on its application in yoga. Despite the initial limitations of the zero-shot approach, applying transfer learning on 15,301 images (real and synthetic) with 82 classes has shown promising results. The article describes the full procedure for fine-tuning, including the choice for image description syntax, models and hyperparameters adjustment. The fine-tuned CLIP model, tested on 3826 images, achieves an accuracy of over 85%, surpassing the current state-of-the-art of previous works on the same dataset by approximately 6%, its training time being 3.5 times lower than what is needed to fine-tune a YOLOv8-based model. For more application-oriented scenarios, with smaller datasets of six postures each, containing 1301 and 401 training images, the fine-tuned models attain an accuracy of 98.8% and 99.1%, respectively. Furthermore, our experiments indicate that training with as few as 20 images per pose can yield around 90% accuracy in a six-class dataset. This study demonstrates that this multimodal technique can be effectively used for yoga pose classification, and possibly for human posture classification, in general. Additionally, CLIP inference time (around 7 ms) supports that the model can be integrated into automated systems for posture evaluation, e.g., for developing a real-time personal yoga assistant for performance assessment.

show abstract

“…Virtual reality tools use computer modeling and simulation technologies that have been widely used for more than half a century in education, health, entertainment, culture, sports, engineering, the armed forces, and other sectors, but have only recently become a practical tool for the manufacturing industry [4]. While these considerations have so far focused on the human-in-the-loop scenario, i.e., mainly on ergonomics and user experience [5], the focus is now broadening to include hardware-in-the-loop.…”

Section: Introductionmentioning

confidence: 99%

Product Tests in Virtual Reality: Lessons Learned during Collision Avoidance Development for Drones

Settgast

Kostarakos

Eggeling

et al. 2022

Designs

View full text Add to dashboard Cite

Virtual reality (VR) and real-world simulations have become an important tool for product development, product design, and product tests. Product tests in VR have many advantages, such as reproducibility and shortened development time. In this paper, we investigate the virtual testing of a collision avoidance system for drones in terms of economic benefits. Our results show that virtual tests had both positive and negative effects on the development, with the positive aspects clearly predominating. In summary, the tests in VR shorten the development time and reduce risks and therefore costs. Furthermore, they offer possibilities not available in real-world tests. Nevertheless, real-world tests are still important.

show abstract

Ergonomic Analysis supported by Virtual Reality: a Systematic Literature Review

Cited by 9 publications

References 11 publications

Virtual Reality and Digital Human Modeling for the Physical Ergonomic Analysis in Product Development in Industry: A Systematic Review

Virtual Reality and Digital Human Modeling for the Physical Ergonomic Analysis in Product Development in Industry: A Systematic Review

Exploring the Use of Contrastive Language-Image Pre-Training for Human Posture Classification: Insights from Yoga Pose Analysis

Product Tests in Virtual Reality: Lessons Learned during Collision Avoidance Development for Drones

Contact Info

Product

Resources

About