eduzhai > Applied Sciences > Engineering >

Algorithm Based on One Monocular Video Delivers Highly Valid and Reliable Gait Parameters

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 12 pages

Abstract: Despite its paramount importance for manifold use cases (e.g., in the healthcare industry, sports, rehabilitation and fitness assessment), sufficientlyvalid and reliable gait parameter measurement is still limited to high-techgait laboratories in large clinics. Here, we demonstrate the excellent validityand test-retest repeatability of a novel gait assessment system which is builtupon modern convolutional neuronal networks to extract three-dimensionalskeleton joints from monocular frontal-view videos of walking humans. Thevalidity study is based on a comparison to the GAITRite pressure-sensitivewalkway system. All measured gait parameters (gait speed, cadence, step lengthand step time) showed excellent concurrent validity for multiple walk trials atnormal and fast gait speeds. The test-retest-repeatability is on the same levelas the GAITRite system. In conclusion, we are convinced that our results canpave the way for cost, space and operationally effective gait analysis in broadmainstream applications. Most sensor-based systems are costly, must be operatedby extensively trained personnel (e.g., motion capture systems) or - even ifnot quite as costly - still possess considerable complexity (e.g. wearablesensors). In contrast, a video sufficient for the assessment method presentedhere can be obtained by anyone, without much training, via a smartphone camera.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...