Abstract
The analysis of human gait is an important tool in medicine and rehabilitation to evaluate the effects and the progression of neurological diseases resulting in neuromotor disorders. In these fields, the gold standard techniques adopted to perform gait analysis rely on motion capture systems and markers. However, these systems present drawbacks: they are expensive, time consuming and they can affect the naturalness of the motion. For these reasons, in the last few years, considerable effort has been spent to study and implement markerless systems based on videography for gait analysis. Unfortunately, only few studies quantitatively compare the differences between markerless and marker-based systems in 3D settings. This work presented a new RGB video-based markerless system leveraging computer vision and deep learning to perform 3D gait analysis. These results were compared with those obtained by a marker-based motion capture system. To this end, we acquired simultaneously with the two systems a multimodal dataset of 16 people repeatedly walking in an indoor environment. With the two methods we obtained similar spatio-temporal parameters. The joint angles were comparable, except for a slight underestimation of the maximum flexion for ankle and knee angles. Taking together these results highlighted the possibility to adopt markerless technique for gait analysis.
Highlights
Gait analysis is a fundamental tool in medicine and rehabilitation [1]
We tested the following null hypothesis: “There are no statistically significant differences between the gait angles obtained with our markerless approach and the gait angles obtained with the gold standard marker-based system”
The PCKh for these keypoints is comparable to the one of the others, and to the results presented in other works
Summary
Gait analysis is a fundamental tool in medicine and rehabilitation [1]. It helps expert physicians to characterize and monitor motion patterns after orthopedic injuries and in people with neurological diseases, e.g., stroke, spinal cord injury, multiple sclerosis, or Parkinson [2]. Recent advances on markerless pose estimation algorithms, based on computer vision and deep neural networks, are opening the possibility of adopting efficient methods for extracting motion information starting from common redgreen-blue (RGB) video data [10] This leads to the question of whether deep learning-based approaches can be adopted to analyze human motion in different domains and, if they can be adopted to perform accurate gait analysis for clinical applications [8].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
