AAAI Publications, Twenty-Fifth International FLAIRS Conference

Font Size: 
Research Modules for Undergraduates in Machine Learning for Automatic Gesture Classification
Sambit Bhattacharya, Denny Bogdan Czejdo, Nicolas Perez

Last modified: 2012-05-16


In this paper we describe ongoing undergraduate research projects that allow us to shift emphasis from teaching to a more active form of student participation. More specifically our projects are on automatic gesture recognition using the Kinect 3D sensor from Microsoft Research and machine learning systems. We have observed the following benefits for our undergraduate students: learning a topic area in AI relatively early; developing proficiency in laboratory practice, specifically, systematic data collection and programming on multiple platforms; learning to use appropriate methodology; applying knowledge to a real situation; learning to analyze data and transform it to various representations; appreciation of scientific experiments and learning what scientific research actually entails.


automatic gesture recognition; human skeleton tracking; 3D sensor; machine learning

Full Text: PDF