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.

This paper addresses the problem of recognizing signs generated by a person to guide a robot. The proposed method is based on video color analysis of a moving person making signs. The analysis consists of segmentation of the middle body, arm and forearm location and recognition of the arm and forearm positions. The proposed method was experimentally tested on videos with different target colors and illumination conditions. Quantitative evaluations indicate 97.76% of correct detection of the signs in 1807 frames.

In this paper we expose theoretically and experimentally some of issues induced by wireless Ethernet when it is used to transmit plant state information to the controller, and control signals to the plant, in a closed-loop system. We also propose some compensation actions, and evaluate their performance in the experimental set up.

Development of human gait analysis systems has become of great interest in the medical field because of their capacity to acquire information and perform diagnosis. This paper presents the design of a fuzzy system able to provide a linguistic interpretation of the kinematic analysis for the thigh and knee in the sagittal plane. This analysis allows the detection of anomalies like hyperflexion, excessive flexion, inadequate flexion, inadequate extension, slight extension, excessive extension or normal angular movements during the gait cycle phases. The fuzzy system is based on the mapping of reported normal behavior curves to fuzzy rules. The fuzzy system is expected to work directly with information generated by 2D or 3D vision systems. Tests on pathological as well as normal cases for thigh and knee showed correct analysis by the fuzzy system.

No abstract