Gait parameter and speed estimation from the frontal view gait video data based on the gait motion and spatial modeling

We study the problem of analyzing and classifying frontal view gait video data. In this study, we suppose that frontal view gait data as a mixing of scale changing, human movements and speed changing parameters. We estimate these parameters using the statistical registration and modeling on a video data. Our gait model is based on human gait structure and temporal-spatial relations between camera and subject. To demonstrate the effectiveness of our method, we conducted two sets of experiments, assessing the proposed method in gait analysis for young/elderly person and abnormal gait detection. In abnormal gait detection experiment, we apply K-nearestneighbor classifier, using the estimated parameters, to perform normal/abnormal gait detect, and present results from an experiment involving 120 subjects (young person), and 60 subjects (elderly person). As a result, our method shows high detection rate.