Evaluating digital work instructions with augmented reality versus paper-based documents for manual, object-specific repair tasks in a case study with experienced workers

Eversberg, Leon; Lambrecht, Jens

doi:10.1007/s00170-023-11313-4

Cited by 6 publications

(2 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We collected 1300 images in 1080P quality from two Microsoft Azure Kinect cameras on an industrial workbench from our previous work [ 49 ] over several days. The images were collected from two different camera angles.…”

Section: Methodsmentioning

confidence: 99%

Combining Synthetic Images and Deep Active Learning: Data-Efficient Training of an Industrial Object Detection Model

Eversberg,

Lambrecht

2024

J. Imaging

Self Cite

View full text Add to dashboard Cite

Generating synthetic data is a promising solution to the challenge of limited training data for industrial deep learning applications. However, training on synthetic data and testing on real-world data creates a sim-to-real domain gap. Research has shown that the combination of synthetic and real images leads to better results than those that are generated using only one source of data. In this work, the generation of synthetic training images via physics-based rendering is combined with deep active learning for an industrial object detection task to iteratively improve model performance over time. Our experimental results show that synthetic images improve model performance, especially at the beginning of the model’s life cycle with limited training data. Furthermore, our implemented hybrid query strategy selects diverse and informative new training images in each active learning cycle, which outperforms random sampling. In conclusion, this work presents a workflow to train and iteratively improve object detection models with a small number of real-world images, leading to data-efficient and cost-effective computer vision models.

show abstract

Section: Methodsmentioning

confidence: 99%

Combining Synthetic Images and Deep Active Learning: Data-Efficient Training of an Industrial Object Detection Model

Eversberg,

Lambrecht

2024

J. Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…The current trend is to move away from paper manuals [8]. Digitized manuals lead to better overall results and a reduction in errors [9].…”

Section: Introductionmentioning

confidence: 99%

Methodology for Rationalization of Pre-Production Processes Using Virtual Reality Based Manufacturing Instructions

Novikov,

Hořejší,

Kubr

et al. 2023

Machines

View full text Add to dashboard Cite

This article deals with the rationalization of manufacturing processes within the product life cycle with emphasis on the pre-production phase of production. A new methodology for evaluating the applicability of modern visualization tools in manufacturing processes is presented. This methodology includes a modified Z-score for categorizing manufacturing processes and has been validated by the successful implementation of 10 real projects. Ultimately, the methodology provides a practical decision-making aid for manufacturing companies in deploying such Computer Aided Instruction tools. For the pre-production phase of products and their development, the possibilities of using modern visualization tools to support CAD instructions and assembly instructions are being explored. These modern visualization tools are video tutorials, augmented reality tutorials and virtual reality tutorials. This paper explores the use of these tools for rationalization of pre-production processes. A methodology was designed to select the most appropriate tool for rationalizing process execution in preparation for production. The functionality of the methodology was verified by applying the methodology in industrial practice and subsequent implementation of the recommended solutions. The methodology was validated by testing key combinations that can arise based on the methodology directly in the operations of manufacturing companies. A total of 10 implementations in real production processes were tailored to this study and carried out over 2 years and the functionality of the methodology was confirmed (that consisted also of a new software development). It was found that there is a dependency between the visualization tools chosen to create the instructions in the context of organizational production preparation and the nature of the production processes.

show abstract

Object Detection for Human–Robot Interaction and Worker Assistance Systems

Tavakoli,

Suh,

Walunj

et al. 2023

Artificial Intelligence in Manufacturing

View full text Add to dashboard Cite

The primary goal of this research is to describe the scenarios, challenges, and complexities associated with object detection in industrial environments and to provide clues on how to tackle them. While object detection in production lines offers significant advantages, it also poses notable difficulties. This chapter delves into the common scenarios and specific challenges encountered in industrial object detection and proposes targeted solutions for various use cases. For example, synthetic data play a pivotal role in overcoming labeling challenges, particularly when it comes to small objects. By harnessing synthetic data, we can efficiently track and debug object detection results, ensuring faster identification and resolution of many data labeling issues. Synthetic data facilitate effective tracking and debugging of object detection results, streamlining the overall workflow. Furthermore, we explore the application of object detection in head-worn devices, utilizing the human point of view (POV) as a valuable perspective. This approach not only enhances human assistance systems but also enhances safety in specific use cases. Through this research endeavor, our aim is to contribute to the advancement of the whole process of object detection methods in complex industrial environments.

show abstract

Evaluating digital work instructions with augmented reality versus paper-based documents for manual, object-specific repair tasks in a case study with experienced workers

Cited by 6 publications

References 44 publications

Combining Synthetic Images and Deep Active Learning: Data-Efficient Training of an Industrial Object Detection Model

Combining Synthetic Images and Deep Active Learning: Data-Efficient Training of an Industrial Object Detection Model

Methodology for Rationalization of Pre-Production Processes Using Virtual Reality Based Manufacturing Instructions

Object Detection for Human–Robot Interaction and Worker Assistance Systems

Contact Info

Product

Resources

About