We present a comparative study of segmentation methods for high-power laser applications, focusing on two specific challenges: detection of microscopic surface damage on optical components and detection of radiochromic films for reconstructing high-dimensional particle phase space distributions. Both applications involve complex morphological variations and non-homogeneous contrast conditions, requiring robust and scalable analysis methods. We evaluate two conventional algorithms and two deep learning-based instance segmentation models, including YOLOv8n-seg and a Detectron2-based Mask R-CNN implementation. All models are evaluated on real datasets that reflect the experimental complexities. We focus particular attention to the accuracy of contour detection, using geometric evaluation metrics such as radial contour comparison, Hausdorff distance, Chamfer distance, as well as intersection-over-union, and analysing runtime performance. Our results indicate that the YOLOv8n-seg model outperforms the conventional surface damage segmentation method in accuracy, but with 12 times higher computational requirements. In contrast, for radiochromic films analysing YOLOv8n-seg achieves both higher accuracy and faster evaluation. In comparison to YOLOv8n-seg model, Detectron2-based Mask R-CNN implementation lags in both segmentation performance and runtime. These results highlight the potential of YOLOv8n-seg model in addressing specific data-related challenges in modern laser diagnostics and support their role in the development of next-generation automated analysis systems.
The European Space Agency (ESA), driven by its ambitions on planned lunar missions with the Argonaut lander, has a profound interest in reliable crater detection, since craters pose a risk to safe lunar landings. This task is usually addressed with automated crater detection algorithms (CDA) based on deep learning techniques. It is non-trivial due to the vast amount of craters of various sizes and shapes, as well as challenging conditions such as varying illumination and rugged terrain. Therefore, we propose a deep-learning CDA based on the OWLv2 model, which is built on a Vision Transformer, that has proven highly effective in various computer vision tasks. For fine-tuning, we utilize a manually labeled dataset fom the IMPACT project, that provides crater annotations on high-resolution Lunar Reconnaissance Orbiter Camera Calibrated Data Record images. We insert trainable parameters using a parameter-efficient fine-tuning strategy with Low-Rank Adaptation, and optimize a combined loss function consisting of Complete Intersection over Union (CIoU) for localization and a contrastive loss for classification. We achieve satisfactory visual results, along with a maximum recall of 94.0
Increasing product complexity, shorter development cycles and cross-domain integration demands pose significant challenges for modern race car engineering teams. In Formula Student teams, heterogeneous toolchains, manual data exchange, late system integration, and high personnel turnover hinder efficient collaborative development and lead to repeated knowledge loss. This paper presents an integrated digital-engineering framework combining graph-based design languages (GBDL), model-to-text transformations, natural-language interactions via Large Language Models (LLMs), and Git-based version control to address these issues. By formalizing design knowledge and storing it in a centralized design graph, the framework ensures digital consistency of data and models, supports automated vehicle design variant generation, and enables seamless cross-domain integration. Through case studies of three Formula Student teams, the methodology demonstrates quantifiable reductions in design iteration time, enabling the evaluation of more than 104 suspension variants within days instead of a few dozen manually created variants, while reducing hands-on engineering effort from minutes per variant to a largely unattended optimization process. The results indicate that the approach not only enhances efficiency and collaboration but also preserves design knowledge for long-term knowledge management and reuse. Looking forward, this methodology provides a scalable route toward further engineering automation, systematic variant-driven development, and early-stage design optimization supported by design languages and integrated downstream toolchains.
Timely, high-resolution maps of flood extent around settlements are essential for emergency response and damage assessment. We consider airborne RGB imagery for flood mapping as it can be collected rapidly at low cost. To produce flood maps, deep learning models for water segmentation are often used. CNN based and small vision transformer models are used. However, they need much data for adaptation to a change of scenery, i.e., another flooding event. Vision foundation models or large vision transformers are known to generalize across domains. Recently, foundation models for Earth observation became available. They are pretrained on satellite data, whose spatial resolution, viewing geometry, and radiometry differ from nadir RGB imagery. Thus, adaptation is required. We investigate how a satellite-pretrained Earth observation foundation model can be adapted to centimeter-scale floodwater mapping from RGB imagery. Specifically, we fine-tune a model we call Prithvi-2.0-UPN consisting of the Prithvi-EO-2.0-600M Vision Transformer combined with a UPerNet decoder for binary water segmentation on two RGB datasets (BlessemFlood21, NeuenahrFlood). In a first experiment we observe that Prithvi-2.0-UPN reaches state-of-the-art results on BlessemFlood21 and NeuenahrFlood, when trained on their datasets. In a second experiment we show that Prithvi-2.0-UPN performs better than state-of-the-art baseline models for transfer to a new flood event (trained on BlessemFlood21, tested on NeuenahrFlood) in a zero-shot setting. However, the performance indicates room for improvement. In this respect, we investigate in a third experiment how performance improves when further fine-tuning the models with small shares of NeuenahrFlood training data: Prithvi-2.0-UPN improves the fastest and reaches almost the performance level when fully trained on NeuenahrFlood, indicating transfer capabilities.
This work focuses on proposing a presentation attack detection (PAD) system for ID cards based on a meta-learning approach, such as Few-Shot Learning (FSL), to determine whether an image is bona fide, printed, or displayed on a screen with only a few samples (50). This approach involves a commercial PAD system trained in one country, such as Chile, that extends its capabilities to other countries with fewer available images, such as Nicaragua, Honduras, and El Salvador. We demonstrate that Prototypical Networks generalise effectively to new bona fide and attack with an average EER of 3,10% and BPCER20 of 2,80%. Our experiments validate FSL as a comprehensive solution for diverse presentation attack modalities in mobile production environments where acquiring large datasets is impractical1.
