Dancing Cloud

• Main Author: Ong, Nicholas Jun Jie
• Other Authors: Liu Linbo
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2020
• Subjects: Engineering::Electrical and electronic engineering
• Online Access: https://hdl.handle.net/10356/140452
• Institution: Nanyang Technological University

With the growth of the Dancing Scene in Singapore, there has been an increase in the number of new dancers in the country. A survey was conducted to with both experienced and beginner dancers, to understand and address their needs to help them retain their interest in dancing. Concerns regarding recognizing and learning new dance moves were found to be one of the leading issues which they faced during their journey through dance. A solution was created in a form of a mobile application which can be used to recognize dance movements through Machine Learning and Pose Estimation. In this project, I have conducted research to implement this solution in a mobile application using various software and compared them to determine the best way to for this purpose. It is concluded that the best way to implement this mobile application is through the use of Google’s Teachable Machine, where the Machine Learning Neural Network is created. Using Android Studio, along with TensorFlow Lite and PoseNet, the Neural Network will then be used as a trained data model to implement a Pose Recognition Mobile Application.