Doctoral Thesis Defense: Kaustubha Mendhurwar

Speaker: Kaustubha Mendhurwar

Supervisors: Drs. S. P. Mudur, T. Popa

Examining Committee:
Drs. A. Ben Hamza, A. Krzyzak, C. Poullis, E. Paquette,
I. Stiharu (Chair)

Title:  Data Driven Human Motion Analysis Using Multiple Data Modalities

Date: Tuesday, March 22, 2016

Time: 13:00

Place: EV 3.309

ABSTRACT

Human motion analysis attempts to understand the movements of the human body using techniques found in various disciplines. The movements of human body can be interpreted on a physical level through pose estimation, i.e., static reconstruction of 3D articulated configurations, or on a higher more semantic level through action recognition, i.e., understanding the body’s movements over time. It has a wide array of applications in the areas of, gaming, sports, security and surveillance, biomedical science, etc. In the gaming industry, learning human action style and creating character animation from a repertoire of actions is very popular. Gait analysis is a crucial step in many biomedical applications as well as security, surveillance and biometric applications. A plethora of sensors are available to capture human motion data in various modalities easily and in a very cost effective manner. The sheer amount of data produced by researchers, using such sensors, every day demand for human motion analysis methods that are computationally efficient.

This thesis attempts to develop effective techniques, based on computer vision and computer graphics, to solve some of the important problems in human motion analysis. Specifically, techniques from both vison and graphics domain such as support vector machines (SVM), hidden markov model (HMM), MotionGraph, rigid transformation, and rammer douglas peucker (RDP) algorithm are employed for applications such as human style learning, human gait analysis, gesture recognition, and time series matching.