arXiv subjects

Peer Stelldinger

Publications and source records attributed to Peer Stelldinger.

8 recordsLinked to original sources

arXiv2026

Pointwise Metrics Mislead: An Evaluation Protocol for Multimodal Inverse Problems

Evaluation in scientific reconstruction is dominated by pointwise metrics - RMSE, MAE, per-event resolution - under the implicit assumption that lower error means better reconstruction. We show that this assumption fails structurally for inverse problems with multimodal posteriors. By the law of total variance, point estimators trained to minimize MSE or MAE produce a marginal spectrum strictly narrower than the truth whenever the posterior has nonzero width. The resulting bias is independent of architecture, training, and dataset size, and it compresses precisely the spectral features - tails, modes, shapes - that downstream scientific measurements rely on. We propose a three-part evaluation protocol where each step targets a failure mode the others miss: per-event distributional accuracy via CRPS, population-level marginal accuracy via a spectrum-fidelity diagnostic, and uncertainty trustworthiness via coverage-based calibration. On a synthetic benchmark with an analytic posterior and on a realistic many-to-one inverse problem from particle physics, model rankings reverse between pointwise and distributional metrics, and calibration further separates architectures indistinguishable under CRPS. The evaluation protocol, not the model, determines the scientific conclusion.

cs.LG↗

arXiv2025

Diffusion-Based Synthetic Brightfield Microscopy Images for Enhanced Single Cell Detection

Accurate single cell detection in brightfield microscopy is crucial for biological research, yet data scarcity and annotation bottlenecks limit the progress of deep learning methods. We investigate the use of unconditional models to generate synthetic brightfield microscopy images and evaluate their impact on object detection performance. A U-Net based diffusion model was trained and used to create datasets with varying ratios of synthetic and real images. Experiments with YOLOv8, YOLOv9 and RT-DETR reveal that training with synthetic data can achieve improved detection accuracies (at minimal costs). A human expert survey demonstrates the high realism of generated images, with experts not capable to distinguish them from real microscopy images (accuracy 50%). Our findings suggest that diffusion-based synthetic data generation is a promising avenue for augmenting real datasets in microscopy image analysis, reducing the reliance on extensive manual annotation and potentially improving the robustness of cell detection models.

cs.CV↗

arXiv2025

Conceptual Evaluation of Deep Visual Stereo Odometry for the MARWIN Radiation Monitoring Robot in Accelerator Tunnels

The MARWIN robot operates at the European XFEL to perform autonomous radiation monitoring in long, monotonous accelerator tunnels where conventional localization approaches struggle. Its current navigation concept combines lidar-based edge detection, wheel/lidar odometry with periodic QR-code referencing, and fuzzy control of wall distance, rotation, and longitudinal position. While robust in predefined sections, this design lacks flexibility for unknown geometries and obstacles. This paper explores deep visual stereo odometry (DVSO) with 3D-geometric constraints as a focused alternative. DVSO is purely vision-based, leveraging stereo disparity, optical flow, and self-supervised learning to jointly estimate depth and ego-motion without labeled data. For global consistency, DVSO can subsequently be fused with absolute references (e.g., landmarks) or other sensors. We provide a conceptual evaluation for accelerator tunnel environments, using the European XFEL as a case study. Expected benefits include reduced scale drift via stereo, low-cost sensing, and scalable data collection, while challenges remain in low-texture surfaces, lighting variability, computational load, and robustness under radiation. The paper defines a research agenda toward enabling MARWIN to navigate more autonomously in constrained, safety-critical infrastructures.

cs.CV↗

arXiv2025

PuzzlePoles: Cylindrical Fiducial Markers Based on the PuzzleBoard Pattern

Reliable perception of the environment is a key enabler for autonomous systems, where calibration and localization tasks often rely on robust visual markers. We introduce the PuzzlePole, a new type of fiducial markers derived from the recently proposed PuzzleBoard calibration pattern. The PuzzlePole is a cylindrical marker, enabling reliable recognition and pose estimation from 360{\deg} viewing direction. By leveraging the unique combinatorial structure of the PuzzleBoard pattern, PuzzlePoles provide a high accuracy in localization and orientation while being robust to occlusions. The design offers flexibility for deployment in diverse autonomous systems scenarios, ranging from robot navigation and SLAM to tangible interfaces.

cs.CV↗

arXiv2025

Enhancing ECG Classification Robustness with Lightweight Unsupervised Anomaly Detection Filters

Continuous electrocardiogram (ECG) monitoring via wearable devices is vital for early cardiovascular disease detection. However, deploying deep learning models on resource-constrained microcontrollers faces reliability challenges, particularly from Out-of-Distribution (OOD) pathologies and noise. Standard classifiers often yield high-confidence errors on such data. Existing OOD detection methods either neglect computational constraints or address noise and unseen classes separately. This paper investigates Unsupervised Anomaly Detection (UAD) as a lightweight, upstream filtering mechanism. We perform a Neural Architecture Search (NAS) on six UAD approaches, including Deep Support Vector Data Description (Deep SVDD), input reconstruction with (Variational-)Autoencoders (AE/VAE), Masked Anomaly Detection (MAD), Normalizing Flows (NFs) and Denoising Diffusion Probabilistic Models (DDPM) under strict hardware constraints ($\leq$512k parameters), suitable for microcontrollers. Evaluating on the PTB-XL and BUT QDB datasets, we demonstrate that a NAS-optimized Deep SVDD offers the superior Pareto efficiency between detection performance and model size. In a simulated deployment, this lightweight filter improves the accuracy of a diagnostic classifier by up to 21.0 percentage points, demonstrating that optimized UAD filters can safeguard ECG analysis on wearables.

cs.LG↗

arXiv2025

On-Device Inference versus Wireless Streaming: Energy-Efficient Multi-Modal Deep Learning for Wearable Cardiovascular Patches

Wearable cardiovascular sensor patches promise continuous, unobtrusive monitoring, but their tight energy, memory, and compute budgets make it unclear whether physiological signals should be analyzed on the device or streamed to the cloud for processing. We study this inference-versus-transmission trade-off for a resource-constrained patch that records synchronized electrocardiogram (ECG) and phonocardiogram (PCG) signals. We propose an end-to-end, multi-modal convolutional neural network (CNN) with early fusion that classifies the two modalities directly on the device, without hand-crafted features. Trained and validated on the PhysioNet/Computing in Cardiology Challenge 2016 dataset, the floating-point model attains an accuracy of 0.975, which is competitive with the best reported results. At the same time, it reduces the parameter count and computational cost by approximately three orders of magnitude. We deploy an 8-bit integer version of the model on a microcontroller with an integrated neural processing unit (NPU) and measure its inference energy. We also benchmark the energy required for Bluetooth Low Energy (BLE) communication on a representative evaluation kit across a range of payload sizes. NPU inference consumes approximately one-seventh of the energy required for CPU inference. For realistic per-second payloads, local inference is also several times more energy efficient than continuous raw-data streaming. These results show that on-device intelligence, rather than constant transmission, is the more energy-efficient basis for always-on wearable cardiovascular monitoring at the edge.

cs.LG↗

arXiv2024

PuzzleBoard: A New Camera Calibration Pattern with Position Encoding

Accurate camera calibration is a well-known and widely used task in computer vision that has been researched for decades. However, the standard approach based on checkerboard calibration patterns has some drawbacks that limit its applicability. For example, the calibration pattern must be completely visible without any occlusions. Alternative solutions such as ChArUco boards allow partial occlusions, but require a higher camera resolution due to the fine details of the position encoding. We present a new calibration pattern that combines the advantages of checkerboard calibration patterns with a lightweight position coding that can be decoded at very low resolutions. The decoding algorithm includes error correction and is computationally efficient. The whole approach is backward compatible to both checkerboard calibration patterns and several checkerboard calibration algorithms. Furthermore, the method can be used not only for camera calibration but also for camera pose estimation and marker-based object localization tasks.

cs.CV↗

arXiv2024

On de Bruijn Rings and Families of Almost Perfect Maps

De Bruijn tori, or perfect maps, are two-dimensional periodic arrays of letters from a finite alphabet, where each possible pattern of shape (m,n) appears exactly once in a single period. While the existence of certain de Bruijn tori, such as square tori with odd m=n element {3,5,7} and even alphabet sizes, remains unresolved, sub-perfect maps are often sufficient in applications like positional coding. These maps capture a large number of patterns, with each appearing at most once. While previous methods for generating such sub-perfect maps cover only a fraction of the possible patterns, we present a construction method for generating almost perfect maps for arbitrary pattern shapes and arbitrary non-prime alphabet sizes, including the above mentioned square tori with odd m=n element {3,5,7} as long that the alphabet size is non-prime. This is achieved through the introduction of de Bruijn rings, a minimal-height sub-perfect map and a formalization of the concept of families of almost perfect maps. The generated sub-perfect maps are easily decodable which makes them perfectly suitable for positional coding applications.

cs.DM↗