•   When: Monday, November 24, 2014 from 03:00 PM to 05:00 PM
•   Speakers: Hao Sun
•   Location: ENGR 4801
•   Export to iCal

Abstract

There are two important subjects in competitive sports training, namely the athlete's individual mechanics training and the team's tactics training. For the student athlete's individual mechanics training, existing training systems seek to capture and visualize the student's motions in 3D virtual environments. However, those systems leave the students themselves to figure out how to revise their motions to improve performance. We design a training system that is able to compare the coach's motions to the student's and quantify their distances. In addition, based on the motion comparison, we generate training advice to tell students where and how to improve.

Besides individual mechanics training, tactics training is an important training aspect for team sports. Tactics training studies the current state of the game from the existing broadcast video footages to determine a good tactic move. Because broadcast sports videos consist of both tactic relevant shots and irrelevant shots, many efforts have been made to automatically segment videos to separate these types of shots. Some methods use domain knowledge of the target sports activity, which are not able to be applied to other sports activities. Other systems use supervised learning to improve frame classification and shot boundary detection accuracy, but often fail to maintain the integrity of the tactic relevant segments and the video structure. We introduce a novel method S-CRP to segment broadcast sports videos into high quality semantic shots. In addition, we also introduced a new performance metric to provide a more accurate measure of how well the segmentation result maintains the structure of the original video.

Current tactic analysis systems provide only low level assistances in tactics training. They are able to capture certain events in the game and help the team with statistical analysis, but they provide little help towards finding a better tactic. After sports videos segmentation, we design a novel tactics training system that is able to consider players' attributes together with their positions to estimate each player's offense threat or defense ability and find the defense tactic that can minimizes the offense team's threat.