Motion cue analysis for parkinsonian gait recognition

Abstract

This paper presents a computer-vision based marker-free method for gait-impairment detection in Patients with Parkinson's disease (PWP). The system is based upon the idea that a normal human body attains equilibrium during the gait by aligning the body posture with Axis-of-Gravity (AOG) using feet as the base of support. In contrast, PWP appear to be falling forward as they are less-able to align their body with AOG due to rigid muscular tone. A normal gait exhibits periodic stride-cycles with stride-angle around 45o between the legs, whereas PWP walk with shortened stride-angle with high variability between the stride-cycles. In order to analyze Parkinsonian-gait (PG), subjects were videotaped with several gait-cycles. The subject's body was segmented using a color-segmentation method to form a silhouette. The silhouette was skeletonized for motion cues extraction. The motion cues analyzed were stride-cycles (based on the cyclic leg motion of skeleton) and posture lean (based on the angle between leaned torso of skeleton and AOG). Cosine similarity between an imaginary perfect gait pattern and the subject gait patterns produced 100% recognition rate of PG for 4 normal-controls and 3 PWP. Results suggested that the method is a promising tool to be used for PG assessment in home-environment.

Keywords: Gait impairment; Gait video analysis; Image processing.; Parkinson’s disease.

Fig. (1)

A vision-based algorithm for Parkinsonian Gait recognition.

Fig. (2)

Silhouette isolation.

Fig. (3)

Human Model Proportions [9, 12].

Fig. (4)

Skeletonization.

Fig. (5)

Trigonometric evaluation to find the perfect stride angle θ_ps (based on Murray P. et al. [14]).

Fig. (6)

A comparison between the stride patterns of Normal Gait and PG is shown. Note that the time intervals t₁…t_n between the strides for n gait cycles are varying in PG. Moreover, the distances d₁…d_n between the cosines of θ_stride and θ_ps for n gait cycles are farther in PG as compared to the normal gait.

Fig. (7)

A comparison between the stride patterns of Normal Gait and PG is shown. Note that the time intervals t₁…t_n between the strides for n gait cycles are varying in PG. Moreover, the distances d₁…d_n between the cosines of θ_stride and θ_ps for n gait cycles are farther in PG as compared to the normal gait.

Fig. (8)

A comparison between the posture lean in a normal gait and PG is shown. Note that the posture pattern in PG shows high lean angle value per frame as compared to the normal gait.