In this paper, we discuss the key elements of a semantic dance-move representation model based on rule-based extractions of logical descriptions from existing Labanotation scores. This is part of a larger effort on representing and analyzing dance movement based on choreological approaches and notation systems. The main goal is to develop a Knowledge-Based System that provides functionality (a) to search by movement concepts and characteristics in a meaningful way for dance practitioners, who may not necessarily be specialists in notation or analysis, and (b) to link different manifestations of movement recordings, especially Labanotation scores. We use examples to highlight the primary and abstract representation model and outline the main challenges in interpreting and segmenting a Labanotation score to transform it in a semi-automated way into a sequence of meaningful recognizable movement concepts. We are not aiming to develop an alternative notation system, but to construct a model and methodology to access existing scores (in digital form) and exploit the underlying information about movement for further computational analysis. We take into account some existing choreological approaches, which use an analogy between dance structure analysis and morphological language studies, and identify multiple levels of describing dance and movement. Finally, we discuss limitations of our approach as well as potential uses of the "search by movement" idea and outline some theoretical observations that emerged during this work.
© Copyright 2014 Proceedings of the 2014 International Workshop on Movement and Computing. Veröffentlicht von ACM. Alle Rechte vorbehalten.