Web-based Clinician Guide to Record Compatible Video of Standardized Drinking Task Kinematics for Computer Vision...

Area of Science:

• Rehabilitation Science
• Biomedical Engineering
• Computer Vision

Background:

• Upper limb assessment is crucial for rehabilitation outcomes.
• Kinematic analysis of the drinking task is a validated measure for conditions like stroke and musculoskeletal disease.
• Current motion capture methods present technical challenges hindering widespread adoption in research and clinical practice.

Purpose of the Study:

• To present a web-based application (app) for standardized video capture of the drinking task.
• To demonstrate the integration of this video capture with a computer vision pipeline for kinematic metric extraction.
• To reduce technical barriers and improve access to upper limb kinematic data in rehabilitation.

Main Methods:

• Development of a web-based application guiding clinicians through a standardized drinking task protocol.
• Utilizing off-the-shelf stereo cameras and personal computers for video acquisition.
• Employing a custom-built computer vision pipeline to process video data and extract kinematic metrics.

Main Results:

• The developed app facilitates standardized video capture of the drinking task.
• The video capture is compatible with a computer vision pipeline for kinematic analysis.
• The approach significantly reduces the technical complexity associated with traditional motion capture.

Conclusions:

• The presented tool enhances accessibility to standardized upper limb kinematic metrics.
• This advancement is expected to accelerate research and improve clinical care for rehabilitation populations with upper limb impairments.
• Ongoing validation and usability studies will further support the clinical translation of this technology.