Exploiting visual cues for learning gait patterns associated with neurological disorders

Records of cases involving neurological disorders often exhibit abnormalities in the gait pattern of an individual. as mentioned in various articles,the causes of various gait disorders can be attributed to neurological disorders. hence analysis of gait abnormalities can be a key to predict the type of neurological disorders as a part of early diagnosis. a number of sensor-based measurements have aided towards quantifying the degree of abnormalities in a gait pattern. a shape oriented motion based approach has been proposed in this paper to envisage the task of classifying an abnormal gait pattern into one of the five types of gait viz. parkinsonian,scissor,spastic,steppage and normal gait. the motion and shape features for two cases viz. right-leg-front and left-leg-front will be taken into account. experimental results of application on real-time videos suggest the reliability of the proposed method. © 2017 penerbit utm press. all rights reserved.