Publication Date
Fall 2013
Degree Type
Master's Project
Degree Name
Master of Science (MS)
Department
Computer Science
Abstract
Today’s world wants quick, smart and cost effective solutions to their problems. People want to learn everything online. They are interested in learning new techniques and every kind of art in a limited amount of time because they are busy with their own work and have very short time to take in class instructor led training. This is an attempt to fulfill the same so that the people can easily learn and master a new kind of art by themselves by using Kinect. The focus of this project is to master Kung-Fu, an ancient form of Chinese Martial Arts. Kung-Fu requires a good amount of practice and therefore needs a Kung-Fu expert mentoring all the time, which is quite expensive. Therefore, the idea is to develop an application which will help the user in imitating the actions performed by the experts and then comparing the performed actions with the captured recordings of experts. While doing the same motions like a master, users can judge themselves by using Kinect. The User Interface is developed in such a way that it will give the user the summary of his performance by comparing his motions with the recorded motions along with the instructions for the next step and with the suggestions to improve, if user fails to do that . The UI provides User Progress Information on the completion of each task. It also provides a record and replay option which helps the user in reviewing his/her actions. Application focuses on simple Kung-Fu punch movement patterns to do quality analysis and data quantity. This project is a combination of Bio-Mechanical principles and Neural Networking technology. It implements real time motion tracking, coaching and evaluation by providing real time feedback using artificial neural network while capturing motion.
Recommended Citation
Kalyankar, Govind, "Repetitive Component Based Motion Learning with Kinect" (2013). Master's Projects. 339.
DOI: https://doi.org/10.31979/etd.hwx8-55d8
https://scholarworks.sjsu.edu/etd_projects/339