The robot operating system (ROS) standard has been extended with different communication mechanisms to address real-time and scalability requirements. On the other hand, containerization and orchestration platforms like Docker and Kubernetes are increasingly being adopted to strengthen platform-independent development and automatic software deployment. In this paper, we quantitatively analyze the impact of topology, containerization, and edge-cloud distribution of ROS nodes on the efficiency of the ROS2 communication protocols. We then present a framework that automatically binds the most efficient ROS protocol for each node-to-node communication by considering the architectural characteristics of both software and edge-cloud computing platforms. The framework is available at https://github.com/PARCO-LAB/ros4k.

In the context of smart environments, crafting remote monitoring systems that are efficient, cost-effective, user-friendly, and respectful of privacy is crucial for many scenarios. Recognizing and tracing individuals via markerless motion capture systems in multi-person settings poses challenges due to obstructions, varying light conditions, and intricate interactions among subjects. In contrast, methods based on data gathered by Inertial Measurement Units (IMUs) located in wearables grapple with other issues, including the precision of the sensors and their optimal placement on the body. We claim that more accurate results can be achieved by mixing Human Pose Estimation (HPE) techniques with information collected by wearables. To do that, we introduce a real-time platform that fuses HPE and IMU data to track and identify people. It exploits a matching model that consists of two synergistic components: the first employs a geometric approach, correlating orientation, acceleration, and velocity readings from the input sources. The second utilizes a Convolutional Neural Network (CNN) to yield a correlation coefficient for each HPE and IMU data pair. The proposed platform achieves promising results in identification and tracking, with an accuracy rate of 96.9%.

There is an increasing interest in exploiting human pose estimation (HPE) software in human-machine interaction systems. Nevertheless, adopting such a computer vision application in real industrial scenarios is challenging. To overcome occlusion limitations, it requires multiple cameras, which in turn require multiple, distributed, and synchronized HPE software nodes running on resource-constrained edge devices. We address this challenge by presenting a real-time distributed 3D HPE platform, which consists of a set of 3D HPE software nodes on edge devices (i.e., one per camera) to redundantly extrapolate the human pose from different points of view. A centralized aggregator collects the pose information through a shared communication network and merges them, in real time, through a pipeline of filtering, clustering and association algorithms. It addresses network communication issues (e.g., delay and bandwidth variability) through a two-levels synchronization, and supports both single and multi-person pose estimation. We present the evaluation results with a real case of study (i.e., HPE for human-machine interaction in an intelligent manufacturing line), in which the platform accuracy and scalability are compared with state-of-the-art approaches and with a marker-based infra-red motion capture system.

Deep learning (DL) for intelligent video analytics is increasingly pervasive in various application domains, ranging from Healthcare to Industry 5.0. A significant trend involves deploying DL models on edge devices with limited resources. Techniques, such as pruning, quantization, and early exit, have demonstrated the feasibility of real-time inference at the edge by compressing and optimizing deep neural networks (DNNs). However, adapting pretrained models to new and dynamic scenarios remains a significant challenge. While solutions like domain adaptation, active learning (AL), and teacher-student knowledge distillation (KD) contribute to addressing this challenge, they often rely on cloud or well-equipped computing platforms for fine tuning. In this study, we propose a framework for domain-adaptive online AL of DNN models tailored for intelligent video analytics on resource-constrained devices. Our framework employs a KD approach where both teacher and student models are deployed on the edge device. To determine when to retrain the student DNN model without ground-truth or cloud-based teacher inference, our model utilizes singular value decomposition of input data. It implements the identification of key data frames and efficient retraining of the student through the teacher execution at the edge, aiming to prevent model overfitting. We evaluate the framework through two case studies: 1) human pose estimation and 2) car object detection, both implemented on an NVIDIA Jetson NX device.

Health telematics is a major improvement on patient lives and has shown to be a key practice to deliver healthcare services, overcoming geographical, temporal, and even organizational barriers. One of the main challenges is to perform gait analysis at a distance through camera-based platforms, which requires the system to satisfy, beside accuracy and real-time, also portability and privacy compliance at the same time. We address this challenge by proposing a portable and low-cost platform that implements real-time and accurate 3D human pose estimation through an embedded software on a low-power off-the-shelf computing device that guarantees privacy by default and by design. We evaluated both accuracy and performance of the proposed solution through an infra-red marker-based motion capture system as ground truth to understand if and how such a portable technology can be used for gait analysis at a distance without leading to different clinical interpretations.