Monitoring of Gait Parameters in Post-Stroke Individuals: A Feasibility Study Using RGB-D Sensors

Abstract

Stroke is one of the most significant causes of permanent functional impairment and severe motor disability. Hemiplegia or hemiparesis are common consequences of the acute event, which negatively impacts daily life and requires continuous rehabilitation treatments to favor partial or complete recovery and, consequently, to regain autonomy, independence, and safety in daily activities. Gait impairments are frequent in stroke survivors. The accurate assessment of gait anomalies is therefore crucial and a major focus of neurorehabilitation programs to prevent falls or injuries. This study aims to estimate, using a single RGB-D sensor, gait patterns and parameters on a short walkway. This solution may be suitable for monitoring the improvement or worsening of gait disorders, including in domestic and unsupervised scenarios. For this purpose, some of the most relevant spatiotemporal parameters, estimated by the proposed solution on a cohort of post-stroke individuals, were compared with those estimated by a gold standard system for a simultaneous instrumented 3D gait analysis. Preliminary results indicate good agreement, accuracy, and correlation between the gait parameters estimated by the two systems. This suggests that the proposed solution may be employed as an intermediate tool for gait analysis in environments where gold standard systems are impractical, such as home and ecological settings in real-life contexts.

Computation of Gait Parameters in Post Stroke and Parkinson’s Disease: A Comparative Study Using RGB-D Sensors and Optoelectronic Systems

“…For each joint, the relative 3D position to the origin of the sensor reference system is available and returned for the 3D reconstruction of the body movements. In our previous studies [ 51 , 72 ], the 3D trajectories of joints and segments were compared to a gold reference system, verifying the accuracy and robustness of angular and linear measurements.…”

“…The analysis procedure works on the collected 3D trajectories of joints to automatically segment every step and estimate the gait parameters that will be compared with the 3D-GA system: the Data Processing section ( Section 2.4 ) describes the analysis procedure in detail. In addition, the RGB-D system has a Graphical User Interface (GUI), managed by MATLAB scripts, to simplify motion capture through specific utilities to check device operation, start and stop acquisition, and check data acquisition correctness [ 72 ].…”

“…However, for the gait analysis with RGB-D system, it was essential to detect the time when the subject entered and left the GAP zone to identify the time window to be analyzed. To this end, the algorithm firstly estimated the 3D body center of mass (COM BODY ) as in [ 51 ] and then used its 3D Euclidean distance from the sensor to determine the time when the subject entered and left the GAP, as in [ 72 ]. After identifying the time window, the step segmentation algorithm used the 3D trajectories of left (ANK L ) and right (ANK R ) ankles to analyze each leg individually inside the GAP and estimate the related gait parameters.…”

“…The stationary ankle period was when the difference between two consecutive z-component values was less than the prefixed threshold; the “in movement” ankle period was when the difference was over the prefixed threshold. As in [ 72 ], the threshold was 2 cm: the aim was to verify that the threshold defined for post-stroke subjects was also valid for PD subjects and that the step segmentation algorithm worked exactly the same way without tuning parameters. The results of the step segmentation algorithm were two binary arrays that allowed the extraction of some traditional gait parameters per leg and overall, as in other reference studies using RGB-D approaches [ 37 , 46 , 56 , 61 , 66 ].…”

“…Along this line of research, this study aims to extend our previous work [ 72 ] by validating the spatio-temporal gait parameters in level walking for both post-stroke individuals and subjects with Parkinson’s disease. A single-camera approach on a reduced walking path, which is thus suitable for the limited spaces in domestic environments, is proposed to this end.…”