Motion analysis is crucial for effective and timely rehabilitative interventions on people with motor disorders. Conventional marker-based (MB) gait analysis is highly time-consuming and calls for expensive equipment, dedicated facilities and personnel. Markerless (ML) systems may pave the way to less demanding gait monitoring, also in unsupervised environments (i.e., in telemedicine). However,scepticism on clinical usability of relevant outcome measures has hampered its use. ML is normally used to analyse treadmill walking, which is significantly different from the more physiological overground walking. This study aims to provide end-users with instructions on using a single-camera markerless system to obtain reliable motion data from overground walking, while clinicians will be instructed on the reliability of obtained quantities. The study compares kinematics obtained from ML systems to those concurrently obtained from marker-based systems, considering different stride counts and subject positioning within the capture volume. The findings suggest that five straight walking trials are sufficient for collecting reliable kinematics with ML systems. Precision on joint kinematics decreased at the boundary of the capture volume. Excellent correlation was found between ML and MB systems for hip and knee angles (0.92<R²<0.96), with slightly lower correlations observed for ankle plantar-dorsiflexion. The Bland-Altman analysis indicated the largest bias for hip flexion/extension ([0.2^∘,10.9^∘]) and the smallest for knee joint ([0.1^∘,0.8^∘]) when comparing MB-PiG and MB-JC approaches. For MB-JC vs. ML-JC comparison, the largest bias was for the ankle joint ([1.2^∘,11.8^∘]), while the smallest was for the hip joint ([0.2^∘,7.3^∘]). Single-camera markerless motion capture systems have great potential in assessing human joint kinematics during overground walking. Clinicians can confidently rely on estimated joint kinematics while walking, enabling personalized interventions and improving accessibility to remote evaluation and rehabilitation services, as long as: (i) the camera is positioned to capture someone walking back and forth at least five times with good visibility of the entire body silhouette; (ii) the walking path is at least 2 m long; and (iii) images captured at the boundaries of the camera image plane should be discarded.

The revolutionary technologies behind Industry 4.0 have opened a new era for manufacturing: connected and autonomous machines, collaborative robotics, and monitoring techniques are spreading to increase productivity and sustainability. From the workers’ perspective, they bring new safety threats but also opportunities to solve old ones, while concerns about workers’ privacy arise due to the increase of data sensed and transferred from the shop floor. This paper presents the results of a research project addressing the prediction of dangerous conditions through workplace monitoring with privacy guarantees. This work is driven by a realistic approach starting from the fact that it is entirely centered on a real 14-meter production line equipped with an extensive array of top-tier devices, including robotic arms, autonomous mobile robots, a reconfigurable moving belt, a multi-camera system, and a highly efficient data transport and computation infrastructure. This project shows safety and privacy achievements over six representative use cases such as man-on-the-ground, environmental events (e.g., fire incidents), workers’ errors that can lead to potential accidents, compliance of Personal Protective Equipment (PPE), and gatherings restrictions. The benefits of this study extend to stakeholders such as manufacturers and workers offering safety systems that can be deployed in industrial settings while addressing privacy concerns and providing compliance with regulations. The industrial laboratory at the heart of this study represents with realism a dynamic and interconnected Industry 4.0 and 5.0 environment.

Many modern programmable embedded devices contain CPUs and a GPU that share the same system memory on a single die. Such a unified memory architecture (UMA) allows programmers to implement different communication models between CPU and the integrated GPU (iGPU). Although the simpler model guarantees implicit synchronization at the cost of performance, the more advanced model allows, through the zero-copy paradigm, the explicit data copying between CPU and iGPU to be eliminated with the benefit of significantly improving performance and energy savings. On the other hand, the robot operating system (ROS) has become a de-facto reference standard for developing robotic applications. It allows for application re-use and the easy integration of software blocks in complex cyber-physical systems. Although ROS compliance is strongly required for SW portability and reuse, it can lead to performance loss and elude the benefits of the zero-copy communication. In this article we present efficient techniques to implement CPU–iGPU communication by guaranteeing compliance to the ROS standard. We show how key features of each communication model are maintained and the corresponding overhead involved by the ROS compliancy.