This paper presents new methods for automatic classification and retrieval of motion capture data facilitating the identification of logically related motions scattered in some database. As the main ingredient, we introduce the concept of motion templates (MTs), by which the essence of an entire class of logically related motions can be captured in an explicit and semantically interpretable matrix representation. The key property of MTs is that the variable aspects of a motion class can be automatically masked out in the comparison with unknown motion data. This facilitates robust and efficient motion retrieval even in the presence of large spatio-temporal variations. Furthermore, we describe how to learn an MT for a specific motion class from a given set of training motions. In our extensive experiments, which are based on several hours of motion data, MTs proved to be a powerful concept for motion annotation and retrieval, yielding accurate results even for highly variable motion classes such ascartwheels, lying down, or throwing motions.
展开▼
