Analysis of Dance Movement from Video Using Machine Learning
For my master thesis (MEng Biomedical Engineering) at University College London (UCL) I am working on a dance and technology project sponsored by Adobe Research. I am developing a tool that understands dance movement from video and is able to segment a video from a dance routine into the specific movements it comprises of. The approach I follow combines machine learning techniques with heuristics to analyze human motion in dance.
Additionally, I am exploring the applications of this movement analysis method in rehabilitation therapies; as a creative tool for dancers and choreographers; and to improve educational resources in the performing arts. This project is a continuation of the research I carried out during my internship at Adobe Research (June-Sept 2018), where I created a method for automatic segmentation of ballet videos using audiovisual cues.
Video source: Mokrin Choi, Prix de Lausanne 2018, Don Quixote female variation (link)