Title :
An editable interface for motion data retrieval based on Labanotation
Author :
Qinghua Liang ; Zhenjiang Miao
Author_Institution :
Inst. of Inf. Sci., Beijing Jiaotong Univ., Beijing, China
fDate :
June 29 2015-July 3 2015
Abstract :
In this paper, we design a natural interface based on Labanotation, a 2-D graphical editable movement symbols, to describe the desired motion as input. A weighted directed hierarchical graph is built. Graph edge represents a unique motion from one pose to another pose and indexes by Labanotation symbols for retrieval. A motion metric is proposed to measure similarity between two motions based on Laban Movement Analysis (LMA) on the middle level. Experiments show that the presented system is easy to use and have a high quality of retrieval results. This interface can be easily applied on the mobile devices.
Keywords :
directed graphs; graphical user interfaces; information retrieval; mobile computing; 2D graphical editable movement symbols; LMA; Laban movement analysis; Labanotation symbols; editable interface; graph edge; mobile devices; motion data retrieval; motion metric; natural interface; similarity measure; weighted directed hierarchical graph; Bismuth; Dynamics; Indexes; Motion measurement; Motion segmentation; Shape; Content-based retrieval; LMA; Labanotation; Motion data retrieval; Movements language;
Conference_Titel :
Multimedia & Expo Workshops (ICMEW), 2015 IEEE International Conference on
Conference_Location :
Turin
DOI :
10.1109/ICMEW.2015.7169872