FAU Researchers Make Nice ‘Strides’ in Gait Analysis Know-how

Microsoft’s Azure Kinect depth digital camera captures 3D information, shade photographs and physique actions for movement monitoring.

A examine from the College of Engineering and Computer Science and the Sensing Institute (I-SENSE) at Florida Atlantic University reveals that foot-mounted wearable sensors and a 3D depth digital camera can precisely measure how folks stroll – even in busy medical environments – providing a strong and extra accessible different to conventional gait evaluation instruments.

Gait, the sample of how an individual walks, is an more and more essential marker of total well being, utilized in detecting fall threat, monitoring rehabilitation, and figuring out early indicators of neurodegenerative illnesses resembling Parkinson’s illness and Alzheimer’s illness. Although digital walkways just like the Zeno™ Walkway have lengthy been thought of the gold customary for gait evaluation, their excessive price, giant footprint and restricted portability prohibit widespread use – particularly exterior managed lab settings.

To overcome these boundaries, FAU researchers and collaborators performed the primary identified examine to concurrently consider three completely different sensing applied sciences: APDM wearable inertial measurement items (IMUs); Microsoft’s’ Azure Kinect depth digital camera; and the Zeno™ Walkway – beneath an identical, real-world medical circumstances. The depth-sensing digital camera captures 3D information, shade photographs, and physique actions to be used in AI, robotics and movement monitoring.

The examine findings, printed within the journal Sensors, reveal that foot-mounted IMUs and the Azure Kinect not solely match the accuracy of conventional instruments but additionally allow scalable, distant and cost-effective gait evaluation.

“This is the first time these three technologies have been directly compared side by side in the same clinical setting,” stated Behnaz Ghoraani, Ph.D., senior creator and an affiliate professor within the FAU Department of Electrical Engineering and Computer Science and the Department of Biomedical Engineering, and an I-SENSE fellow. “We wanted to answer a question the field has been asking for a long time: Can more accessible tools like wearables and markerless cameras reliably match the clinical standard for detailed gait analysis? The answer is yes – especially when it comes to foot-mounted sensors and the Azure Kinect.”

The examine recruited 20 adults aged 52 to 82, who accomplished each single-task and dual-task strolling trials – a technique usually used to imitate real-world strolling circumstances that require multitasking or divided consideration. Each participant’s gait was captured by the three methods on the similar time, because of a custom-built {hardware} platform the FAU researchers developed, which exactly synchronized all information sources to the millisecond.

Researchers evaluated 11 completely different gait markers, together with fundamental metrics like strolling velocity and step frequency, in addition to extra detailed indicators resembling stride time, assist phases and swing time. These markers had been analyzed utilizing statistical strategies to check every gadget’s measurements with these from the Zeno™ Walkway.

The outcomes had been clear: foot-mounted sensors confirmed near-perfect settlement with the walkway throughout practically all gait markers. The Azure Kinect additionally carried out impressively, sustaining robust accuracy even within the complicated, real-world clinic setting the place a number of folks, together with caregivers and employees, had been current within the digital camera’s discipline of view. In distinction, lumbar-mounted sensors, that are generally utilized in wearable gait research, demonstrated considerably decrease accuracy and consistency, notably for fine-grained gait cycle occasions.

Many research use lower-back sensors as a result of they’re simple to mount. However, information from this examine reveals that they usually fail to seize the main points clinicians care most about – particularly timing-based markers that may reveal early indicators of neurological issues. 

“By testing these tools in a realistic clinical environment with all the unpredictable visual noise that comes with it, we’ve made great strides toward validating them for everyday use,” stated Ghoraani. “This isn’t just a lab experiment. These technologies are ready to meet real-world demands.”

Importantly, the examine is the primary to benchmark the Azure Kinect towards an digital walkway for micro-temporal gait markers – filling a important hole within the literature and confirming the gadget’s potential medical worth.

“The implications of this research are far-reaching,” stated Stella Batalama, Ph.D., dean of the FAU College of Engineering and Computer Science. “As health care systems increasingly embrace telehealth and remote monitoring, scalable technologies like wearable foot sensors and depth cameras are emerging as powerful tools. They enable clinicians to track mobility, detect early signs of functional decline, and tailor interventions – without the need for costly, space-intensive equipment.”

Study co-authors are first creator Marjan Nassajpour and Mahmoud Seifallahi, each doctoral college students within the FAU College of Engineering and Computer Science; and Amie Rosenfeld, a bodily therapist researcher and assistant director of schooling; Magdalena I. Tolea, Ph.D., analysis assistant professor of neurology and affiliate director of analysis; and James E. Galvin, M.D., professor of neurology, chief, Division of Neurology, and director, Comprehensive Center for Brain Health, all with the University of Miami Miller School of Medicine.

This work was supported by a National Science Foundation grant awarded to Ghoraani and a National Institutes of Health grant awarded to Galvin.

(From left): Marjan Nassajpour; Behnaz Ghoraani, Ph.D.; Mahmoud Seifallahi (seated); and Mustafa Shuqair, Ph.D.

-FAU-