The most common methods for the study of human movement use markers placed on the skin. While marker-based methods have demonstrated the value of quantitatively methods assessing human movement there are some drawbacks to marker -based including the impediment to the motion by the presence of skin markers and relative movement between the skin where the markers are placed and the underlying bone. Markerless motion capture represents a novel approach allowing the unencumbered capture of human motion. Human motion is captured as video data from multiple cameras subjects` kinematics is extracted in three dimensions using specific algorithms. A few alternative markerless systems developed by the authors are described. Results of different algorithms for the identification of the full body kinematics are presented, demonstrating the effectiveness and potential of markerless motion capture for human movement analysis in biomechanical applications.
© Copyright 2006 Ninth International Symposium on the 3-D Analysis of Human Movement, June 28-30, 2006, Valenciennes, France. Alle Rechte vorbehalten.