9 results
Now showing1 - 9 of 9
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Tuning domain randomization for 3D-rendered synthetic training data for defect detection in aircraft engine borescope inspectionVisual surface defect detection in complex industrial inspection scenarios remains predominantly manual. Deep learning–based vision systems promise to automate this task but require large quantities of representative, annotated defect images, which are often unavailable due to the rarity and diversity of relevant defects. We address this challenge with a modular synthetic data generation pipeline leveraging physically based 3D rendering, which enables systematic domain randomization throughout the entire rendering chain. The pipeline comprises dedicated modules for scene composition, geometry-based defect generation, procedural material modeling, rendering, and automatic pixel-wise annotation, allowing users to expose and tune key parameters such as defect size, position, and penetration depth, object materials, camera poses, and lighting. We first provide a structured analysis of all process steps that influence image appearance in defect synthesis and then instantiate the pipeline for a case study on aircraft engine borescope inspection, targeting missing-material defects on high-pressure compressor blades. Using a two-stage experimental design, we employ a Plackett–Burman screening over 22 candidate factors followed by a one-factor-at-a-time optimization of the most influential parameters. Our results show that the material model, defect positioning, defect size, and penetration depth randomization dominate detection performance. Training an object detector solely on synthetic images generated with the optimized configuration yields a maximum of 0.89 mAP@0.5IoU on a real-world borescope validation set, with performance saturating at ∼500 rendered training images. These findings demonstrate that carefully structured domain randomization in a physically based rendering pipeline can provide practically useful synthetic training data for industrial defect detection.Publicationtype: Journal Article9 13 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , An edge Is all you need: Cracking the code for generating synthetic datasets for robust crack detection modelsGenerating synthetic datasets for training crack detection models remains a challenge due to the variability of crack appearances and the need for pixel-level annotations. As a promising alternative to manual labeling, synthetic data generation using Perlin Noise has gained attention. However, the relationship between Perlin Noise parameters and the physical characteristics of cracks is not well-established, leading to potential dataset bias and suboptimal model performance. This paper presents a novel approach that maps Perlin Noise generated crack parameters to crack characteristics such as width, length, curvature, and bifurcations, enabling the generation of diverse and realistic crack patterns. We employ a broad domain randomization technique by projecting the generated cracks onto randomly selected background images from the ImageNet database to reduce dataset bias and enhance model robustness. Using the Partitioning Around Medoids (PAM) algorithm, we create six distinct datasets capturing a comprehensive range of crack parameter variations. We demonstrate the effectiveness of our approach by fine-tuning the state-of-the-art SegFormer 5b model on our synthetic datasets and benchmarking its performance on the Crack500 dataset. Through linear regression analysis, we can identify the key crack parameters that influence model performance. Our results show that synthetic cracks have to be long, wide, straight, and should have few bifurcations to maximize evaluation metrics such as Intersection over Union (IoU), precision, recall, and F1.Publicationtype: Conference Paper27 13 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Transparent reporting of AI in systematic literature reviews: development of the PRISMA-trAIce checklist(JMIR Publications, 2025-12-10); ; ; ; Background: Systematic literature reviews (SLRs) build the foundation for evidence synthesis, but they are exceptionally demanding in terms of time and resources. While recent advances in artificial intelligence (AI), particularly large language models, offer the potential to accelerate this process, their use introduces challenges to transparency and reproducibility. Reporting guidelines such as the PRISMA-AI (Preferred Reporting Items for Systematic Reviews and Meta-Analyses–Artifi-cial Intelligence Extension) primarily focus on AI as a subject of research, not as a tool in the review process itself. Objective: To address the gap in reporting standards, this study aimed to develop and propose a discipline-agnostic checklist extension to the PRISMA 2020 statement. The goal was to ensure transparent reporting when AI is used as a methodological tool in evidence synthesis, fostering trust in the next generation of SLRs. Methods: The proposed checklist, named PRISMA-trAIce (PRISMA–Transparent Reporting of Artificial Intelligence in Comprehensive Evidence Synthesis), was developed through a systematic process. We conducted a literature search to identify established, consensus-based AI reporting guidelines (eg, CONSORT-AI [Consolidated Standards of Reporting Trials–Arti-ficial Intelligence] and TRIPOD-AI [Transparent Reporting of a Multivariable Prediction Model of Individual Prognosis or Diagnosis–Artificial Intelligence]). Relevant items from these frameworks were extracted, analyzed, and thematically synthesized to form a modular checklist that integrated with the PRISMA 2020 structure. Results: The primary result of this work is the PRISMA-trAIce checklist, a comprehensive set of reporting items designed to document the use of AI in SLRs. The checklist covers the entire structure of an SLR, from title and abstract to methods and discussion, and includes specific items for identifying AI tools, describing human-AI interaction, reporting performance evaluation, and discussing limitations. Conclusions: PRISMA-trAIce establishes an important framework to improve the transparency and methodological integrity of AI-assisted systematic reviews, enhancing the trust required for the responsible application of AI-assisted systematic reviews in evidence synthesis. We present this work as a foundational proposal, explicitly inviting the scientific community to join an open science process of consensus building. Through this collaborative refinement, we aim to evolve PRISMA-trAIce into a formally endorsed guideline, thereby ensuring the collective validation and scientific rigor of future AI-driven research.Publicationtype: Journal Article25 23 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Introducing a tool for synthetic defect image data generation: enhancing industrial surface inspectionVisual surface defect detection in complex scenarios remains a manual endeavor in industrial inspection. Stateof- the-art machine learning approaches promise to automate this task through machine vision; however, they require substantial, suitable training data to be effectively trained. For industrial products, such data are often unavailable for several reasons, including the rarity of certain defects or their manifestations. This paper introduces a tool to generate synthetic data for training machine vision systems using rendering techniques. Our tool allows for targeted manipulation of process parameters throughout the rendering chain, including scene composition involving object, camera, and lighting, defect generation, placement, and material generation. This enables an exploration of the impacts along the rendering pipeline and facilitates selecting an appropriate data set for specific inspection tasks. We demonstrate our tool’s effectiveness by applying models trained on our synthetic data to a real-world inspection task.Publicationtype: Conference Paper77 75 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Analyzing the effects of different 3D-model acquisition methods for synthetic AI training data generation and the domain gap(Springer, 2024); ; 80 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Industrial segment anything - A case study in aircraft manufacturing, intralogistics, maintenance, repair, and overhaul(2023-07-24); ; ; ; Deploying deep learning-based applications in specialized domains like the aircraft production industry typically suffers from the training data availability problem. Only a few datasets represent non-everyday objects, situations, and tasks. Recent advantages in research around Vision Foundation Models (VFM) opened a new area of tasks and models with high generalization capabilities in non-semantic and semantic predictions. As recently demonstrated by the Segment Anything Project, exploiting VFM's zero-shot capabilities is a promising direction in tackling the boundaries spanned by data, context, and sensor variety. Although, investigating its application within specific domains is subject to ongoing research. This paper contributes here by surveying applications of the SAM in aircraft production-specific use cases. We include manufacturing, intralogistics, as well as maintenance, repair, and overhaul processes, also representing a variety of other neighboring industrial domains. Besides presenting the various use cases, we further discuss the injection of domain knowledge.Publicationtype: Preprint147 68 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Adapting synthetic training data in deep learning-based visual surface inspection to improve transferability of simulations to real-world environments(The International Society for Optical Engineering, 2023); ; ; Learning models from synthetic image data rendered from 3D models and applying them to real-world applications can reduce costs and improve performance when using deep learning for image processing in automated visual inspection tasks. However, sufficient generalisation from synthetic to real-world data is challenging, because synthetic samples only approximate the inherent structure of real-world images and lack image properties present in real-world data, a phenomenon called domain gap. In this work, we propose to combine synthetic generation approaches with CycleGAN, a style transfer method based on Generative Adversarial Networks (GANs). CycleGAN learns the inherent structure from real-world samples and adapts the synthetic data accordingly. We investigate how synthetic data can be adapted for a use case of visual inspection of automotive cast iron parts, and show that supervised deep object detectors trained on the adapted data can successfully generalise to real-world data and outperform object detectors trained on synthetic data alone. This demonstrates that generative domain adaptation helps to leverage synthetic data in deep learning-assisted inspection systems for automated visual inspection tasks.Publicationtype: Conference Paper32 30 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Generation of synthetic AI training data for robotic grasp-candidate identification and evaluation in intralogistics bin-picking scenariosRobotic bin picking remains a main challenge for the wide enablement of industrial robotic tasks. While AI-enabled picking approaches are encouraging they repeatedly face the problem of data availability. The scope of this paper is to present a method that combines analytical grasp research with the field of synthetic data creation to generate individual training data for use-cases in intralogistics transportation scenarios. Special attention is given to systematic grasp finding for new objects and unknown geometries in transportation bins and to match the generated data to a real two-finger parallel gripper. The presented approach includes a grasping simulation in Pybullet to investigate the general tangibility of objects under uncertainty and combines these findings with a previously reported virtual scene generator in Blender, which generates AI-images of fully packed transport boxes, including depth maps and necessary annotations. This paper, therefore, contributes a synthesizing and cross-topic approach that combines different facets of bin-picking research such as geometric analysis, determination of tangibility of objects, grasping under uncertainty, finding grasps in dynamic and restricted bin-environments, and automation of synthetic data generation. The approach is utilized to generate synthetic grasp training data and to train a grasp-generating convolutional neural network (GG-CNN) and demonstrated on real-world objects.Publicationtype: Conference PaperScopus© Citations 1 84 122 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Synthetic training data generation for visual object identification on load carriersWith visual AI processes relying on individual and context accurate training data, the existing common object datasets and randomization based synthetic data pipelines can only hardly be transferred or applied on specific and narrow industrial tasks. To enable visual AI applications for intralogistics processes, such as supervision or localization of objects, a domain-knowledge driven implementation for generation of context accurate synthetic training data is introduced. With this consideration of process and domain requirements in the data generation pipeline itself, a data-generator for object identification on load carriers is contributed.Publicationtype: Journal ArticleScopus© Citations 18 163 328