D. Davcev and S. Kalajdziski (FYROM)
Augmented reality, Video annotation, Human-computer Interfaces
The main idea of this paper is to introduce the support mechanism for the augmented reality system interface for dance analysis and presentation of single dancer. In our previous work [1] we described the basic characteristics of our system for dance analysis and presentation including the high interactivity between the user and the 3D dancer. In this paper, we introduce a subsystem for indexing and retrieval of dance video data. Generated video shots based on particular dance steps are annotated by using MPEG-7 descriptors originated from human body hierarchy and basic movement directions. The MPEG-7 based annotation is used as an index for retrieval of dance segments from different dances that hold similar steps. The search/retrieval process is done by querying the system with semantic concepts, keywords or annotations. The results are displayed and additionally visualized through the augmented reality system interface.
Important Links:
Go Back
