arXiv subjects

Francesco Dell'Olio

Publications and source records attributed to Francesco Dell'Olio.

3 recordsLinked to original sources

arXiv2026

Improving Faint Object Detection for Space Situational Awareness with Variational Autoencoders

We present a deep-learning pipeline for enhancing the detection of faint moving objects in optical space situational awareness (SSA) imagery through automated star removal and background reconstruction. Detecting low signal-to-noise ratio (SNR) objects remains extremely challenging in optical observations, particularly in the cislunar (X-GEO) environment, where structured sky backgrounds, dense stellar fields, and scattered moonlight significantly degrade the performance of classical detection algorithms. To address this problem, the proposed pipeline combines a lightweight segmentation network (Tiny-U-Net) to generate stellar masks with a partial-convolution variational autoencoder (astro-VAE), designed to learn the statistical distribution of astronomical backgrounds and perform context-aware inpainting of masked regions. The reconstructed background maps can then be used as a preprocessing step to suppress fixed sources and background inhomogeneities prior to detection. As a proof of concept, the approach is integrated with a shift-and-stack scheme and evaluated on real ground-based telescope observations targeting the X-GEO region. Results demonstrate that the method reconstructs star-free backgrounds with high fidelity, while preserving moving targets and significantly enhancing detectability, thereby providing an effective data-driven preprocessing strategy for faint moving-object detection in optical SSA scenarios.

cs.CV↗

arXiv2026

A magneto-mechanical gyroscope with spintronic readout

Gyroscopes are essential elements in navigation, consumer electronics, robotics, and aerospace applications. Most micro electro-mechanical systems (MEMS) implementations rely on capacitive sensing mechanisms, which limit the dimensional scaling to the micrometer scale. In this work, we introduce a MEMS-like two-degree-of-freedom (2-DOF) gyroscope that exploits the rectification functionality of magnetic tunnel junctions (MTJs) as its readout mechanism and as the transducer of the mechanical dynamics. Experimentally characterized MTJs have been used to calibrate and perform an experiment-informed design of the magneto-mechanical model combining micromagnetic theory with 2-DOF mechanical equations. We demonstrated that the output is linear with angular rate, and that the proposed device is able to extract the angular rate in dynamic cases exploiting a homodyne demodulation approach. The results open a path towards a compact, complementary metal-oxide semiconductor (CMOS)-compatible readout pathway that relaxes reliance on tight capacitive gaps and motivates multi-physics designs of the device.

cond-mat.mes-hall↗

arXiv2025

Efficient FPGA-accelerated Convolutional Neural Networks for Cloud Detection on CubeSats

We present the implementation of four FPGA-accelerated convolutional neural network (CNN) models for onboard cloud detection in resource-constrained CubeSat missions, leveraging Xilinx's Vitis AI (VAI) framework and Deep Learning Processing Unit (DPU), a programmable engine with pre-implemented, parameterizable IP cores optimized for deep neural networks, on a Zynq UltraScale+ MPSoC. This study explores both pixel-wise (Pixel-Net and Patch-Net) and image-wise (U-Net and Scene-Net) models to benchmark trade-offs in accuracy, latency, and model complexity. Applying channel pruning, we achieved substantial reductions in model parameters (up to 98.6%) and floating-point operations (up to 90.7%) with minimal accuracy loss. Furthermore, the VAI tool was used to quantize the models to 8-bit precision, ensuring optimized hardware performance with negligible impact on accuracy. All models retained high accuracy post-FPGA integration, with a cumulative maximum accuracy drop of only 0.6% after quantization and pruning. The image-wise Scene-Net and U-Net models demonstrated strong real-time inference capabilities, achieving frame rates per second of 57.14 and 37.45, respectively, with power consumption of around 2.5 W, surpassing state-of-the-art onboard cloud detection solutions. Our approach underscores the potential of DPU-based hardware accelerators to expand the processing capabilities of small satellites, enabling efficient and flexible onboard CNN-based applications.

eess.SP↗