Seminar: First-Person Perspective Gesture Recognition

Thesis Proposal Presentation
Akhilesh Mishra
M.Sc. Candidate
Supervisor: Dr. Oscar Meruvia-Pastor


First-Person Perspective Gesture Recognition


Department of Computer Science
Tuesday, May 21, 2013, 1:00 pm, Room EN 2022

 


Abstract

Gesture recognition has gained a lot of popularity in the fields of Computer Graphics and Human- Computer Interaction. Gesture interaction is an easy and effective way of interacting with a computing system. Current devices like Microsoft's Kinect, Nintendo's Wii and Sony's Move make use of gestures for game play. However, gesture interaction is not limited to gaming applications and it can be used for general purpose interactions as well. The idea behind this research is to develop a first-person perspective gesture recognition module for a Telecollaboration and telecommunication system. Existing gesture recognition methods are primarily based on a thirdperson perspective, i.e., the camera or the gesture-recording device is in front of the user, and the computational analysis of the player's gestures is done from the perspective of an external viewer, or third-person. The main disadvantage of third-person gesture recognition is that the user would always have to be present in front the system and thus the system is not mobile. First-person gesture recognition would allow the user to be mobile and could be used in conjunction with Augmented Reality systems to improve the overall user experience. To test this hypothesis, the viability and efficacy of the first-person gesture recognition module will be evaluated through a user study