Gianluca Setti

Light Detection and Ranging (LiDAR) technology offers significant advantages for effective crowd management. This article presents LiDAR technology and highlights its primary advantages over other monitoring technologies, including enhanced privacy, performance in various weather conditions, and precise 3D mapping. We present a general taxonomy of four key tasks in crowd management: crowd detection, counting, tracking, and behavior classification, with illustrative examples of LiDAR applications for each task. We identify challenges and open research directions, including the scarcity of dedicated datasets, sensor fusion requirements, artificial intelligence integration, and processing needs for LiDAR point clouds. This article offers actionable insights for developing crowd management solutions tailored to public safety applications.

Rehabilitation aims to help patients with limited mobility regain their physical abilities through targeted movements, exercises, stimulation, and other therapeutic methods. Recent advances in technology have introduced sensor-based systems into rehabilitation and clinical practices, enabling real-time monitoring and providing accurate feedback on movement accuracy. Among these sensors, LiDAR has demonstrated strong potential, offering key advantages over conventional techniques such as camera-based systems, which raise privacy concerns, and wearable sensors, which can be uncomfortable and prone to errors. In this work, we review the applications of LiDAR in rehabilitation, post-injury care, and hospital environments, focusing on studies published between 2019 and 2025. Studies across several areas have been explored: 3D body scanning and gait analysis with standalone LiDAR, LiDAR mounted on robotic systems for rehabilitation, real-time monitoring and environment scanning for safe navigation, and activity and position recognition. We also analyze processing techniques, particularly learning-based approaches, and support the discussion with statistical analysis, highlighting trends, gaps, and future research opportunities. To the best of our knowledge, this is the first comprehensive survey dedicated to LiDAR for rehabilitation applications, providing an overview of current methods, AI-based processing techniques, and open challenges.

Industrial open radio access network (O-RAN) systems must support manufacturing workloads with dynamically varying communication and computation demands driven by production processes. Existing O-RAN orchestration mechanisms remain largely network-centric and fail to capture such process-induced variability. This letter proposes a decentralized process-informed reinforcement learning (RL) framework for joint radio and compute orchestration in industrial O-RAN. Distributed agents at radio units (RUs) adapt physical resource block (PRB) and compute allocations based on workload and latency requirements. Using a multi-agent dueling deep Q-network architecture, the approach improves latency fulfillment and reliability under nonstationary industrial traffic. Simulation results demonstrate consistent gains over network-centric multi-agent baselines.

Effective traffic monitoring is a cornerstone of intelligent transportation systems, enabling safer and more efficient urban mobility. Among emerging sensing modalities, Light Detection and Ranging (LiDAR) stands out as a robust technology capable of delivering high-resolution, 3D spatial information that can complement traditional traffic monitoring systems. However, despite its potential, publicly available LiDAR datasets dedicated to traffic monitoring remain scarce, with most existing datasets primarily designed for autonomous driving from the ego-vehicle perspective. In this work, we develop a comprehensive LiDAR-driven pipeline for urban traffic assessment, with a specific focus on road intersections, one of the most complex and safety-critical areas of urban networks involving vehicles and pedestrians. The proposed simulation-based framework, combining SUMO for traffic scenario generation and Blender for high-fidelity 3D reconstruction with LiDAR emulation, integrates perception and relational reasoning through two main components: (i) a LiDAR-based perception module for 3D object detection and segmentation, and (ii) a graph-construction module that encodes spatial, geometric, and semantic relations between road users and infrastructure. The resulting datasets offer rich annotations, making them suitable for advanced AI-driven analysis of road user interactions and behaviors. We validate our approach using state-of-the-art models for LiDAR perception and graph neural networks, demonstrating high detection and relation-learning accuracy under both clean and distorted point cloud conditions. The results confirm the effectiveness of the proposed pipeline and highlight LiDAR’s capability to provide a holistic and reliable understanding of complex traffic scenes, paving the way for future smart mobility and intelligent traffic management applications.

X-ray tomography is widely used across scientific and clinical domains, yet image degradation remains a major obstacle to reliable analysis, particularly under low-dose or data-scarce conditions. Existing restoration methods are typically designed for specific modalities and predefined degradation, limiting their generalizability. Here we show that image restoration can instead be formulated as learning realistic, nonparametric acquisition degradation processes directly from data. We introduce HorusEye, a self-supervised foundation model for X-ray tomography restoration that leverages interslice contrastive pretraining to jointly learn structural priors and degradation without paired supervision or predefined assumptions. Trained on over 100 million images, HorusEye generalizes across diverse modalities, restoration tasks and previously unseen imaging modalities, consistently outperforming task-specific approaches. Extensive evaluations demonstrate improved photon efficiency and recovery of high-frequency information. Clinical studies further demonstrate enhanced detectability of low-contrast anatomy and lesions, as well as improved performance on downstream tasks, highlighting HorusEye as a general postprocessing tool for X-ray tomography.

Accurate tree counting from satellite imagery remains a critical challenge for agricultural monitoring, climate analysis, and land-use management. While recent advances in deep learning, particularly large pre-trained Vision-Language Models (VLMs), have achieved remarkable results in general visual tasks, we show that they fail to reliably address tree counting in high-resolution satellite imagery. This highlights the need for specialized datasets to support the development and evaluation of models capable of solving this task, especially in plantation environments. To this end, we introduce a configurable synthetic image generator that produces realistic satellite imagery of olive plantations along with precise annotations in terms of the number and positions of trees, providing valuable resources for advancing tree counting research in agricultural settings. The generator simulates terrain textures, spatial distributions of trees, and tree shadows to approximate real-world conditions and exposes over 100 customizable parameters to control appearance and layout. It also includes a simulated Near-Infrared (NIR) layer to support vegetation-specific spectral analysis. We compare deep learning methods based on object detection or segmentation models trained on the generated data with pre-trained VLMs and an unsupervised computer vision baseline, and show that synthetic training achieves superior accuracy on a manually annotated real-world dataset, demonstrating effective sim-to-real performance transfer specifically in olive plantation imagery. In particular, SAM-ViT-Large achieves an average relative error of 4.82% on the real data, which is comparable to the performance of human labelers. The generator source code is publicly available, supporting further research in data-scarce agricultural monitoring with a focus on plantation analysis.

This study presents a novel method for recognizing magnetic tags based on far-field measurements using high-order projection techniques. Magnetic tags consisted of a 2× 2 array of neodymium permanent magnets, each treated as a dipole with a distinct magnetization state. The experimental measurements of the magnetic flux (Bz) were conducted using a Hall axial probe and xy translation stage. The proposed recognition algorithm employs two methods: Taylor series expansion and spectral continuation with regularization. The results demonstrate the ability of the algorithm to identify distinct magnetic tag signatures, particularly for intricate configurations. The spectral method with regularization is suitable for large continuation distances and can be adapted to very large distances using multistep scheduling.