This paper presents a methodology for automatically identifying human action. We use a new approach to human activity recognition that incorporates a Bayesian framework. By tracking the movement of the head of the subject over consecutive frames of monocular grayscale image sequences, we recognize actions in the frontal or lateral view. Input sequences captured from a CCD camera are matched aga...

Euler angle decomposition and inverse dynamics were used to determine the knee angles and net forces and moments applied to the tibia during kneeling and squatting with and without kneepads for 10 subjects in four postures: squatting (Squat), kneeling on the right knee (One Knee), bilateral kneeling near full flexion (Near Full) and bilateral kneeling near 90° flexion (Near 90). Kneepads affect...

Simulation of high flexion tasks such as squatting is hindered through invalid moment length estimation when using generic musculoskeletal (MSK) models. The purpose of this study was to examine the effect of wrapping surface (WS) at the knee and hip joints on the muscle moment arms calculated using a MSK model during squatting tasks. A generic full body model was modified by (1) increasing knee...