activity
20242026
most citedLEVIO: Lightweight Embedded Visual Inertial Odometry for Resource-Constrained Devices

1 citations · 1 across the 2 of their papers we have counts for

collaborators

17 papers

cs.RO2026

Fly, Track, Land: Infrastructure-less Magnetic Localization for Heterogeneous UAV-UGV Teaming

Valerio Brunacci, Davide Plozza, Alessio De Angelis +2

Persistent air ground robot teams require nano UAVs that can leave a mobile UGV, perform short scouting or inspection tasks, and reliably return to a compact landing interface. Thi…

cs.CV20261 cited

LEVIO: Lightweight Embedded Visual Inertial Odometry for Resource-Constrained Devices

Jonas Kühne, Christian Vogt, Michele Magno +1

Accurate, infrastructure-less sensor systems for motion tracking are essential for mobile robotics and augmented reality (AR) applications. The most popular state-of-the-art visual…

eess.SP2025

A Non-Invasive Path to Animal Welfare: Contactless Vital Signs and Activity Monitoring of In-Vivo Rodents Using a mm-Wave FMCW Radar

Tommaso Polonelli, Manuel Glahn, Stefano Kron +3

Monitoring physiological and behavioral parameters of laboratory rodents is fundamental for biomedical research, yet conventional techniques often rely on invasive sensors or frequ…

cs.HC2025

Evaluating Electric Charge Variation Sensors for Camera-free Eye Tracking on Smart Glasses

Alan Magdaleno, Pietro Bonazzi, Tommaso Polonelli +1

Contactless Electrooculography (EOC) using electric charge variation (QVar) sensing has recently emerged as a promising eye-tracking technique for wearable devices. QVar enables lo…

cs.CV2025

Efficient and Accurate Downfacing Visual Inertial Odometry

Jonas Kühne, Christian Vogt, Michele Magno +1

Visual Inertial Odometry (VIO) is a widely used computer vision method that determines an agent's movement through a camera and an IMU sensor. This paper presents an efficient and…

cs.LG2025

EdgeCodec: Onboard Lightweight High Fidelity Neural Compressor with Residual Vector Quantization

Benjamin Hodo, Tommaso Polonelli, Amirhossein Moallemi +2

We present EdgeCodec, an end-to-end neural compressor for barometric data collected from wind turbine blades. EdgeCodec leverages a heavily asymmetric autoencoder architecture, tra…