Interactive dance is a new form of dance in which there is a two-way communication between dancers and visual backgrounds. The visual background is one of the most important features for an interactive dance performance as it helps to create the scene and atmosphere. However, selecting or producing dance background images is labor intensive and technically demanding. Therefore, the first challenge is how to ease this process and help dancers find the images they would like to use as backgrounds. Another aspect of interactive dance is using distance, which is the stage information that can be most easily perceived by the audience. However, current sensing devices have limitations on tracking distance information for an interactive dance performance. Therefore, the second challen...[ Read more ]

Interactive dance is a new form of dance in which there is a two-way communication between dancers and visual backgrounds. The visual background is one of the most important features for an interactive dance performance as it helps to create the scene and atmosphere. However, selecting or producing dance background images is labor intensive and technically demanding. Therefore, the first challenge is how to ease this process and help dancers find the images they would like to use as backgrounds. Another aspect of interactive dance is using distance, which is the stage information that can be most easily perceived by the audience. However, current sensing devices have limitations on tracking distance information for an interactive dance performance. Therefore, the second challenge is how to overcome the limitation of current sensing devices and enable interaction based on the distance information.

This thesis proposes a visual background analytics and triggering system to enable dancers to design and interact with visual backgrounds during interactive dance performances. To solve the first challenge, the system incorporates visual background analytics with a recommendation engine. The core of the recommendation engine is a deep matrix factorization (DMF) model which recommends dance background images by considering the object feature, style feature, and dancers' rating information simultaneously. To solve the second challenge, the system incorporates a Bluetooth Low Energy (BLE) beacon-based triggering engine. The engine leverages a BLE beacon body area network and a smartphone to monitor a dancer's relative distance during a dance performance. The effectiveness of the proposed methods has been proven through a series of experiments. Additionally, a live performance was conducted to demonstrate the practicability of the proposed system.