Marta Lagomarsino

Elena Merlo, Marta Lagomarsino, Edoardo Lamon et al.

This paper presents a new method to describe spatio-temporal relations between objects and hands, to recognize both interactions and activities within video demonstrations of manual tasks. The approach exploits Scene Graphs to extract key interaction features from image sequences while simultaneously encoding motion patterns and context. Additionally, the method introduces event-based automatic video segmentation and clustering, which allow for the grouping of similar events and detect if a monitored activity is executed correctly. The effectiveness of the approach was demonstrated in two multi-subject experiments, showing the ability to recognize and cluster hand-object and object-object interactions without prior knowledge of the activity, as well as matching the same activity performed by different subjects.

Marta Lagomarsino, Elena Merlo, Andrea Pupa et al.

Remarkable capabilities have been achieved by robotics and AI, mastering complex tasks and environments. Yet, humans often remain passive observers, fascinated but uncertain how to engage. Robots, in turn, cannot reach their full potential in human-populated environments without effectively modeling human states and intentions and adapting their behavior. To achieve a synergistic human-robot collaboration (HRC), a continuous information flow should be established: humans must intuitively communicate instructions, share expertise, and express needs. In parallel, robots must clearly convey their internal state and forthcoming actions to keep users informed, comfortable, and in control. This review identifies and connects key components enabling intuitive information exchange and skill transfer between humans and robots. We examine the full interaction pipeline: from the human-to-robot communication bridge translating multimodal inputs into robot-understandable representations, through adaptive planning and role allocation, to the control layer and feedback mechanisms to close the loop. Finally, we highlight trends and promising directions toward more adaptive, accessible HRC.

Olivia Nocentini, Marta Lagomarsino, Gokhan Solak et al.

Driver fatigue poses a significant challenge to railway safety, with traditional systems like the dead-man switch offering limited and basic alertness checks. This study presents an online behavior-based monitoring system utilizing a customised Directed-Graph Neural Network (DGNN) to classify train driver's states into three categories: alert, not alert, and pathological. To optimize input representations for the model, an ablation study was performed, comparing three feature configurations: skeletal-only, facial-only, and a combination of both. Experimental results show that combining facial and skeletal features yields the highest accuracy (80.88%) in the three-class model, outperforming models using only facial or skeletal features. Furthermore, this combination achieves over 99% accuracy in the binary alertness classification. Additionally, we introduced a novel dataset that, for the first time, incorporates simulated pathological conditions into train driver monitoring, broadening the scope for assessing risks related to fatigue and health. This work represents a step forward in enhancing railway safety through advanced online monitoring using vision-based technologies.

Qiyi Tong, Olivia Nocentini, Marta Lagomarsino et al.

Facial Landmark Detection (FLD) in thermal imagery is critical for applications in challenging lighting conditions, but it is hampered by the lack of rich visual cues. Conventional cross-modal solutions, like feature fusion or image translation from RGB data, are often computationally expensive or introduce structural artifacts, limiting their practical deployment. To address this, we propose Multi-Level Cross-Modal Knowledge Distillation (MLCM-KD), a novel framework that decouples high-fidelity RGB-to-thermal knowledge transfer from model compression to create both accurate and efficient thermal FLD models. A central challenge during knowledge transfer is the profound modality gap between RGB and thermal data, where traditional unidirectional distillation fails to enforce semantic consistency across disparate feature spaces. To overcome this, we introduce Dual-Injected Knowledge Distillation (DIKD), a bidirectional mechanism designed specifically for this task. DIKD establishes a connection between modalities: it not only guides the thermal student with rich RGB features but also validates the student's learned representations by feeding them back into the frozen teacher's prediction head. This closed-loop supervision forces the student to learn modality-invariant features that are semantically aligned with the teacher, ensuring a robust and profound knowledge transfer. Experiments show that our approach sets a new state-of-the-art on public thermal FLD benchmarks, notably outperforming previous methods while drastically reducing computational overhead.

Younggeol Cho, Elisa Motta, Olivia Nocentini et al.

Human pose estimation and action recognition have received attention due to their critical roles in healthcare monitoring, rehabilitation, and assistive technologies. In this study, we proposed a novel architecture named Transformer based Encoder Decoder Network (TED Net) designed for estimating human skeleton poses from WiFi Channel State Information (CSI). TED Net integrates convolutional encoders with transformer based attention mechanisms to capture spatiotemporal features from CSI signals. The estimated skeleton poses were used as input to a customized Directed Graph Neural Network (DGNN) for action recognition. We validated our model on two datasets: a publicly available multi modal dataset for assessing general pose estimation, and a newly collected dataset focused on fall related scenarios involving 20 participants. Experimental results demonstrated that TED Net outperformed existing approaches in pose estimation, and that the DGNN achieves reliable action classification using CSI based skeletons, with performance comparable to RGB based systems. Notably, TED Net maintains robust performance across both fall and non fall cases. These findings highlight the potential of CSI driven human skeleton estimation for effective action recognition, particularly in home environments such as elderly fall detection. In such settings, WiFi signals are often readily available, offering a privacy preserving alternative to vision based methods, which may raise concerns about continuous camera monitoring.

Marta Lagomarsino, Marta Lorenzini, Elena De Momi et al.

The ongoing trend towards Industry 4.0 has revolutionised ordinary workplaces, profoundly changing the role played by humans in the production chain. Research on ergonomics in industrial settings mainly focuses on reducing the operator's physical fatigue and discomfort to improve throughput and avoid safety hazards. However, as the production complexity increases, the cognitive resources demand and mental workload could compromise the operator's performance and the efficiency of the shop floor workplace. State-of-the-art methods in cognitive science work offline and/or involve bulky equipment hardly deployable in industrial settings. This paper presents a novel method for online assessment of cognitive load in manufacturing, primarily assembly, by detecting patterns in human motion directly from the input images of a stereo camera. Head pose estimation and skeleton tracking are exploited to investigate the workers' attention and assess hyperactivity and unforeseen movements. Pilot experiments suggest that our factor assessment tool provides significant insights into workers' mental workload, even confirmed by correlations with physiological and performance measurements. According to data gathered in this study, a vision-based cognitive load assessment has the potential to be integrated into the development of mechatronic systems for improving cognitive ergonomics in manufacturing.

Marta Lagomarsino, Vincent Groenhuis, Maura Casadio et al.

A biopsy is the only diagnostic procedure for accurate histological confirmation of breast cancer. When sonographic placement is not feasible, a Magnetic Resonance Imaging(MRI)-guided biopsy is often preferred. The lack of real-time imaging information and the deformations of the breast make it challenging to bring the needle precisely towards the tumour detected in pre-interventional Magnetic Resonance (MR) images. The current manual MRI-guided biopsy workflow is inaccurate and would benefit from a technique that allows real-time tracking and localisation of the tumour lesion during needle insertion. This paper proposes a robotic setup and software architecture to assist the radiologist in targeting MR-detected suspicious tumours. The approach benefits from image fusion of preoperative images with intraoperative optical tracking of markers attached to the patient's skin. A hand-mounted biopsy device has been constructed with an actuated needle base to drive the tip toward the desired direction. The steering commands may be provided both by user input and by computer guidance. The workflow is validated through phantom experiments. On average, the suspicious breast lesion is targeted with a radius down to 2.3 mm. The results suggest that robotic systems taking into account breast deformations have the potentials to tackle this clinical challenge.