Abstract
The present work proposes a method for human gait and kinematic analysis. Gait analysis consists of the determination of hip, knee and ankle positions through video analysis. Gait kinematic for the thigh and knee is then generated from this data. Evaluations of the gait analysis method indicate an acceptable performance of 86.66% for hip and knee position estimation, and comparable findings with other reported works for gait kinematic. A coordinate systems assignment is performed according to the DH algorithm and a direct kinematic model of the legs is obtained. The legs' angles obtained from the video analysis are applied to the kinematic model in order to revise the application of this model to robotic legs in a power assisted system.
Highlights
Nowdays a huge amount of research exists on human‐ robot interaction and hybridization between humans and robots
In order to obtain a better modelling of the gait kinematic, an adjustment to the estimation marks of the hip, knee and ankle is achieved
In general and according to the previous results the proposed method to determine information of human gait kinematic provides acceptable information to be used in a powered assistance robotic mechanism
Summary
The algorithm developed determines automatically position marks of the hip, knee and ankle associated to the different gait phases. This information is used to define the thigh and knee kinematic. The gait analysis algorithm is base on the Approximated Median method [14]. This method is used to segment the human silhouette from videos and gait markers of the hip, knee and ankle are found. The initial condition of the segmentation algorithm considers the first video frame as the initial background which is continuously updated through the analysis to generate the updated background needed to extract the human silhouette
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have