On the reliability of single-camera markerless systems for overground gait monitoring.

BACKGROUND AND OBJECTIVE: 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. METHODS: 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. RESULTS: 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

Preserving Data Privacy and Accuracy of Human Pose Estimation Software Based on CNN s for Remote Gait Analysis.

In the last years there have been significant improvements in the accuracy of real-time 3D skeletal data estimation software. These applications based on convolutional neural networks (CNNs) can playa key role in a variety of clinical scenarios, from gait analysis to medical diagnosis. One of the main challenges is to apply such intelligent video analytic at a distance, which requires the system to satisfy, beside accuracy, also data privacy. To satisfy privacy by default and by design, the software has to run on "edge" computing devices, by which the sensitive information (i.e., the video stream) is elaborated close to the camera while only the process results can be stored or sent over the communication network. In this paper we address such a challenge by evaluating the accuracy of the state-of-the-art software for human pose estimation when run "at the edge". We show how the most accurate platforms for pose estimation based on complex and deep neural networks can become inaccurate due to subs amp ling of the input video frames when run on the resource constrained edge devices. In contrast, we show that, starting from less accurate and "lighter" CNNs and enhancing the pose estimation software with filters and interpolation primitives, the platform achieves better real-time performance and higher accuracy with a deviation below the error tolerance of a marker-based motion capture system.

Enabling Gait Analysis in the Telemedicine Practice through Portable and Accurate 3D Human Pose Estimation.

Human pose estimation (HPE) through deep learning-based software applications is a trend topic for markerless motion analysis. Thanks to the accuracy of the state-of-the-art technology, HPE could enable gait analysis in the telemedicine practice. On the other hand, delivering such a service at a distance requires the system to satisfy multiple and different constraints like accuracy, portability, real-time, and privacy compliance at the same time. Existing solutions either guarantee accuracy and real-time (e.g., the widespread OpenPose software on well-equipped computing platforms) or portability and data privacy (e.g., light convolutional neural networks on mobile phones). We propose a portable and low-cost platform that implements real-time and accurate 3D HPE through an embedded software on a low-power off-the-shelf computing device that guarantees privacy by default and by design. We present an extended evaluation of both accuracy and performance of the proposed solution conducted with a marker-based motion capture system (i.e., Vicon) as ground truth. The results show that the platform achieves real-time performance and high-accuracy with a deviation below the error tolerance when compared to the marker-based motion capture system (e.g., less than an error of 5∘ on the estimated knee flexion difference on the entire gait cycle and correlation 0.91<ρ<0.99). We provide a proof-of-concept study, showing that such portable technology, considering the limited discrepancies with respect to the marker-based motion capture system and its working tolerance, could be used for gait analysis at a distance without leading to different clinical interpretation.