Computer Vision Methods for Parkinsonian Gait Analysis: A Review on Patents
Taha Khan, Peter Grenholm and Dag Nyholm
Affiliation: Academy of Industry and Society, Computer Engineering, Dalarna University, SE- 781 88 Borlänge, Sweden.
Keywords: Gait Impairment, Parkinson’s disease, Gait Video Analysis, and Image Processing.
Gait disturbance is an important symptom of Parkinson’s disease (PD). This paper presents a review of patents
reported in the area of computerized gait disorder analysis. The feasibility of marker-less vision based systems has been
examined for ‘at-home’ self-evaluation of gait taking into account the physical restrictions of patients arising due to PD. A
three tier review methodology has been utilized to synthesize gait applications to investigate PD related gait features and
to explore methods for gait classification based on symptom severities. A comparison between invasive and non-invasive
methods for gait analysis revealed that marker-free approach can provide resource efficient, convenient and accurate gait
measurements through the use of image processing methods. Image segmentation of human silhouette is the major challenge
in the marker-free systems which can possibly be comprehended through the use of Microsoft Kinect application
and motion estimation algorithms. Our synthesis further suggests that biorhythmic features in gait patterns have potential
to discriminate gait anomalies based on the clinical scales.
Rights & PermissionsPrintExport