摘要:
随着我国逐步迈入老龄化社会,脑卒中、脑外伤、脊椎损伤等疾病在人群中的发病率逐渐升高,未来社会对于康复医疗的需求将十分迫切,而康复机器人的出现将在很大程度上缓解这一状况。为了在康复过程中对患者的运动步态进行分析,本文首先利用微软开发的Kinect二代体感传感器跟踪和采集患者在康复运动过程中的姿态信息,然后采用经过优化的基于Slope Constraints的坡度加权多维微分动态时间规整算法来实现步态的全局分类。同时为了实现步态的局部分析,本文提出一种基于特征语义信息分割的步态分析方法,以有效得到局部的信息。
Abstract:
As China gradually entered the aging society, the incidence of stroke, traumatic brain injury, spinal cord injury and other diseases gradually increased. In the future, the medical needs for rehabilitation will be very urgent, and the appearance of the rehabilitation robot is a relief. In order to analyze the motion gait for patients in the course of rehabilitation, in this article, we use Kinect-II tracking and gather the gait motion of patients in the process of rehabilitation exercise, and then we achieve the global classification of gait by using multidimensional differential dynamic time warping algorithm based on slope constraints. At the same time, in order to realize the local analysis of the gait motion, we provide a gait analysis method which separates the gait information based on semantic feature.