Vision-based gait impairment analysis for aided diagnosis

Abstract

Gait is a firsthand reflection of health condition. This belief has inspired recent research efforts to automate the analysis of pathological gait, in order to assist physicians in decision-making. However, most of these efforts rely on gait descriptions which are difficult to understand by humans, or on sensing technologies hardly available in ambulatory services. This paper proposes a number of semantic and normalized gait features computed from a single video acquired by a low-cost sensor. Far from being conventional spatio-temporal descriptors, features are aimed at quantifying gait impairment, such as gait asymmetry from several perspectives or falling risk. They were designed to be invariant to frame rate and image size, allowing cross-platform comparisons. Experiments were formulated in terms of two databases. A well-known general-purpose gait dataset is used to establish normal references for features, while a new database, introduced in this work, provides samples under eight different walking styles: one normal and seven impaired patterns. A number of statistical studies were carried out to prove the sensitivity of features at measuring the expected pathologies, providing enough evidence about their accuracy. Graphical Abstract Graphical abstract reflecting main contributions of the manuscript: at the top, a robust, semantic and easy-to-interpret feature set to describe impaired gait patterns; at the bottom, a new dataset consisting of video-recordings of a number of volunteers simulating different patterns of pathological gait, where features were statistically assessed.

Using transfer learning for classification of gait pathologies

“…It should also be noted that although VGG-19 is fine-tuned for the INIT Gait Dataset, the resulting model improves the classification accuracy across the other two datasets. This is significant because the INIT Dataset is captured in a LABCOM studio [3], which produces perfectly segmented silhouettes. The other two datasets, however, are captured in less constrained environments, where the segmentation of silhouettes is far form perfect, often missing parts of the walking person's silhouette.…”

“…However, with recent development in technology, various devices can now be used to acquire features that allow such analysis to be performed automatically, or semi-automatically. Typically, biomechanical features such as speed, cadence, step length, stance time, or swing time, can be used to identify different gait pathologies [3]. However, as presented in [4], features acquired from a gait representation typically used for biometric recognition, called the gait energy image (GEI), can also be used.…”

Automatic Classification of Gait Impairments Using a Markerless 2D Video-Based System

“…The biometric features used for recognition can be derived from representations such as the gait energy image (GEI). Such features have also been used to perform classification of gait disorders, for instance resulting from Parkinson’s disease, neuropathy, hemiplegia and diplegia [ 22 ], or to detect the amount of movement and movement broadness of an individual’s feet [ 23 ].…”

“…The proposed system also computes a temporal feature, “foot flat ratio”, that estimates the fraction of time during which the foot is in complete contact with the ground during the stance phase. This feature is significantly more descriptive than the previously considered stance/swing phase during a gait cycle [ 23 ], and along with speed and normalized step count it allows the proposed system to more reliably detect deviations from normal gait. Also, novel body related features are proposed, such as torso orientation and shift in COG, which allow estimating posture instabilities, such as a hunchback.…”

Análisis automático del patrón de la marcha mediante visión por computador: problemas, métodos y aplicaciones

“…Capítulo 6: Caracterización de patologías en la forma de caminar [65] El trabajo propuesto en este capítulo es fruto de la colaboración con una neuróloga de reconocido prestigio 2 , con el objetivo de aportar solucioneś utiles a tres necesidades no resueltas al emplear el análisis de la forma de caminar como ayuda al diagnóstico médico: (1) la escasez de caracterizaciones del patrón de marcha directamente interpretables por un especialista;…”