Towards Synthetic AI Training Data for Image Classification in Intralogistic Settings

Schoepflin, Daniel; Iyer, Karthik; Gomse, Martin; Schüppstuhl, Thorsten

doi:10.1007/978-3-030-74032-0_27

Cited by 7 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 17 ], this problem is addressed by using synthetic data. The successful use of synthetic training data for the domain of aircraft production and logistic scenarios is addressed by [ 18 , 19 ]. A variety of application scenarios for object identification of industrial components with a high degree of similarity using CNNs are shown in [ 2 , 4 , 20 , 21 , 22 , 23 , 24 ].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Comparative Study of Visual Identification Methods for Highly Similar Engine Tubes in Aircraft Maintenance, Repair and Overhaul

Prünte,

Schoepflin,

Schüppstuhl

2023

Sensors

Self Cite

View full text Add to dashboard Cite

Unique identification of machine parts is critical to production and maintenance, repair and overhaul (MRO) processes in the aerospace industry. Despite recent advances in automating these identification processes, many are still performed manually. This is time-consuming, labour-intensive and prone to error, particularly when dealing with visually similar objects that lack distinctive features or markings or when dealing with parts that lack readable identifiers due to factors such as dirt, wear and discolouration. Automation of these processes has the potential to alleviate these problems. However, due to the high visual similarity of components in the aerospace industry, commonly used object identifiers are not directly transferable to this domain. This work focuses on the challenging component spectrum engine tubes and aims to understand which identification method using only object-inherent properties can be applied to such problems. Therefore, this work investigates and proposes a comprehensive set of methods using 2D image or 3D point cloud data, incorporating digital image processing and deep learning approaches. Each of these methods is implemented to address the identification problem. A comprehensive benchmark problem is presented, consisting of a set of visually similar demonstrator tubes, which lack distinctive visual features or markers and pose a challenge to the different methods. We evaluate the performance of each algorithm to determine its potential applicability to the target domain and problem statement. Our results indicate a clear superiority of 3D approaches over 2D image analysis approaches, with PointNet and point cloud alignment achieving the best results in the benchmark.

show abstract

Section: Related Workmentioning

confidence: 99%

“…However, this requires prior training with a sufficiently large dataset that describes the target domain as completely as possible. To address the problem of unavailable training data, synthetic generation is a possible solution [ 18 , 19 ].…”

Section: Analysis Concept Creation and Data Preparationmentioning

confidence: 99%

A Comparative Study of Visual Identification Methods for Highly Similar Engine Tubes in Aircraft Maintenance, Repair and Overhaul

Prünte,

Schoepflin,

Schüppstuhl

2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Focusing on the ability to detect aircraft components in production supplying logistic operations with delivery units, [2,3] provide the capability to enable AI-based visual sensor applications with the help of synthetic training data. Such an approach can be incorporated into the design flow of this paper, however, is limited to components that can be differentiated through means of object detection and a top-view sensor configuration.…”

Section: Related Work and State Of The Artmentioning

confidence: 99%

Assessing Visual Identification Challenges for Unmarked and Similar Aircraft Components

Schoepflin

Gierecker

Schüppstuhl

2022

Lecture Notes in Mechanical Engineering

Self Cite

View full text Add to dashboard Cite

Highest demands for complete traceability and quality control of each component, require thorough identification of each produced, replaced, and (dis-)assembled aircraft component. As many production and MRO-processes for modern aircraft remain to be carried out manually, this poses a great challenge. Many small components either do not feature a Part Number or in MRO-processes their Part Number is occluded or not readable due to dirt and wear. Considering unmarked components with a high resemblance to one another and few characteristics, e.g. standard parts such as bushings and pipes, manual identification is an error-prone task. Avoiding errors through digitalized procedures has the potential to significantly reduce error rates and costs for a typical manual dual control. However, automated identification of components has to overcome the high classification complexity that originates in the manifold of aircraft components and is additionally increased by individualistic MRO modifications for specific aircraft. This work presents a methodological approach to reveal possible challenges for identification procedures and gives special focus to the assessment of similarities between components. Two similarity metrics are introduced that are calculated either through feature-based analysis or through 3D-shape similarity assessment. The methodology is demonstrated with two to this date unsolved Use-Cases that represent different challenges of visual identification systems for similar and unmarked components.

show abstract

“…Another essential gap in the l-app study has been the congruency between the information provided by l-apps and the actual experience felt by tourists. Indeed, 1-apps often use professional photographs and videos that are taken in ideal conditions, with perfect lighting and angles [ 22 ]. These images are carefully selected to showcase the best features of a particular attraction or destination.…”

Section: Introductionmentioning

confidence: 99%

Enhancing tourist loyalty through location-based service apps: Exploring the roles of digital literacy, perceived ease of use, perceived autonomy, virtual-content congruency, and tourist engagement

Xiong,

Zhang

2024

PLoS ONE

View full text Add to dashboard Cite

Advanced mobile functions and empowered smartphones have provided tourists with various location-based service apps that reshaped the business model of the tourism sector. Despite their importance to tourists, l-apps still have limitations, such as ignorance of tourist preferences and the mismatch between app introduction and tourist experience, therefore affecting tourist loyalty to destinations. Understanding tourist-oriented factors thus becomes critical for l-app designers and service providers. This study integrates the technology-acceptance model (TAM) into a unique context to examine the roles of digital literacy, perceived ease of use, perceived autonomy, virtual-content congruence, and tourist engagement on tourist loyalty. Our empirical test of a structural equation model based on a randomly recruited 319 customers found that tourists’ digital literacy influences their engagement and perceived ease of use, which mediates the relationship between digital literacy and engagement; tourists’ perceived autonomy influences their engagement. Moreover, we found the moderating role of information-experience congruency between digital literacy, perceived ease of use, and perceived autonomy and tourist engagement, thus contributing to the boundary conditions of the TAM model. Finally, tourist engagement contributes to tourist loyalty. The study contributes to the integration of the technology acceptance model with a tourist orientation. The findings also offer meaningful, practical implications and recommendations on l-app design to stakeholders of tourist destinations.

show abstract

Towards Synthetic AI Training Data for Image Classification in Intralogistic Settings

Cited by 7 publications

References 14 publications

A Comparative Study of Visual Identification Methods for Highly Similar Engine Tubes in Aircraft Maintenance, Repair and Overhaul

A Comparative Study of Visual Identification Methods for Highly Similar Engine Tubes in Aircraft Maintenance, Repair and Overhaul

Assessing Visual Identification Challenges for Unmarked and Similar Aircraft Components

Enhancing tourist loyalty through location-based service apps: Exploring the roles of digital literacy, perceived ease of use, perceived autonomy, virtual-content congruency, and tourist engagement

Contact Info

Product

Resources

About