| Many applications that utilize motion capture data require small, discrete, semantic segments of data, but most motion capture collection processes produce long sequences of data. The smaller segments are often created from the longer sequences manually. This segmentation process is very laborious and time consuming. An automatic motion capture segmentation method based on movement qualities derived from Laban Movement Analysis (LMA) is presented. LMA provides a good compromise between high-level semantic features, which are difficult to extract for general motions, and low-level kinematic features, which often yield unsophisticated segmentations. The LMA features are computed using a collection of neural networks trained with temporal variance in order to create a classifier that is more robust with regard to input boundaries. The actual segmentation points are derived through simple time series analysis of the LMA features. Segmentations produced using LMA features are more similar to manual segmentations, both at the frame and segment level, than are several other automatic segmentation methods. The LMA based segmentation method has the added benefit of improving the performance classifiers for which it segments the input. This has implications in many areas that utilize motion capture analysis including human-computer interaction and computer animation. |
