Date of Award:

5-2014

Document Type:

Dissertation

Degree Name:

Doctor of Philosophy (PhD)

Department:

Computer Science

Committee Chair(s)

Heng-Da Cheng

Committee

Heng-Da Cheng

Committee

Lie Zhu

Committee

Vicki Allan

Committee

Curtis Dyreson

Committee

Haitao Wang

Abstract

Short track speed skating was adopted by the International Skating Union in 1967, and upgraded to full winter Olympic sport status in 1992. Even though its history is short compared with long track speed skating, it became popular around the world because it is more intense and more entertaining for audiences. The demands of having a CAT system for gathering and analyzing competition data automatically is raising drastically due to its growing popularity all around the world.

There have been some commercial systems for some other sports, which are able to provide extrinsic feedback information to coaches and athletes. However, there is no commercial sports analysis system for short track speed skating yet, and the current commercial sports analysis systems have certain limitations including the requirement of operator intervention to process the video and the necessities of the restricted environments such as multiple cameras with complex camera settings and expensive peripherals.

The proposed CAT system greatly reduces the requirement of hardware settings and the system cost by utilizing only monocular videos captured using a single handycam. Moreover, it automatically tracks multiple skaters and output accurate skater spatial information which provides valuable references to the coaches to improve the skaters’ performances in international competitions.

Checksum

d4825b175c2b61136ca34f05d5089ad0

Download

Share

COinS

Copyright for this work is retained by the student. If you have any questions regarding the inclusion of this work in the Digital Commons, please email us at .