Classification of sports types from tracklets

Research output: Contribution to conference without publisher/journalConference abstract for conferenceResearchpeer-review

213 Downloads (Pure)

Abstract

Automatic analysis of video is important in order to process and exploit large amounts of data, e.g. for sports analysis. Classification of sports types is one of the first steps to- wards a fully automatic analysis of the activities performed at sports arenas. In this work we test the idea that sports types can be classified from features extracted from short trajectories of the players. From tracklets created by a Kalman filter tracker we extract four robust features; Total distance, lifespan, distance span and mean speed. For clas- sification we use a quadratic discriminant analysis. In our experiments we use 30 2-minutes thermal video sequences from each of five different sports types. By applying a 10- fold cross validation we obtain a correct classification rate of 94.5 %.
Original languageEnglish
Publication dateAug 2014
Number of pages4
Publication statusPublished - Aug 2014
EventKDD Workshop on Large-scale Sports Analytics - New York, United States
Duration: 24 Aug 201427 Aug 2014
Conference number: 20
http://www.kdd.org/kdd2014/

Workshop

WorkshopKDD Workshop on Large-scale Sports Analytics
Number20
CountryUnited States
CityNew York
Period24/08/201427/08/2014
Internet address

Fingerprint

Sports
Discriminant analysis
Kalman filters
Trajectories
Experiments

Cite this

Gade, R., & Moeslund, T. B. (2014). Classification of sports types from tracklets. Abstract from KDD Workshop on Large-scale Sports Analytics, New York, United States.
Gade, Rikke ; Moeslund, Thomas B. / Classification of sports types from tracklets. Abstract from KDD Workshop on Large-scale Sports Analytics, New York, United States.4 p.
@conference{ab55d1b8958c4dcdbc46744e2fb5df61,
title = "Classification of sports types from tracklets",
abstract = "Automatic analysis of video is important in order to process and exploit large amounts of data, e.g. for sports analysis. Classification of sports types is one of the first steps to- wards a fully automatic analysis of the activities performed at sports arenas. In this work we test the idea that sports types can be classified from features extracted from short trajectories of the players. From tracklets created by a Kalman filter tracker we extract four robust features; Total distance, lifespan, distance span and mean speed. For clas- sification we use a quadratic discriminant analysis. In our experiments we use 30 2-minutes thermal video sequences from each of five different sports types. By applying a 10- fold cross validation we obtain a correct classification rate of 94.5 {\%}.",
author = "Rikke Gade and Moeslund, {Thomas B.}",
year = "2014",
month = "8",
language = "English",
note = "null ; Conference date: 24-08-2014 Through 27-08-2014",
url = "http://www.kdd.org/kdd2014/",

}

Gade, R & Moeslund, TB 2014, 'Classification of sports types from tracklets', New York, United States, 24/08/2014 - 27/08/2014, .

Classification of sports types from tracklets. / Gade, Rikke; Moeslund, Thomas B.

2014. Abstract from KDD Workshop on Large-scale Sports Analytics, New York, United States.

Research output: Contribution to conference without publisher/journalConference abstract for conferenceResearchpeer-review

TY - ABST

T1 - Classification of sports types from tracklets

AU - Gade, Rikke

AU - Moeslund, Thomas B.

PY - 2014/8

Y1 - 2014/8

N2 - Automatic analysis of video is important in order to process and exploit large amounts of data, e.g. for sports analysis. Classification of sports types is one of the first steps to- wards a fully automatic analysis of the activities performed at sports arenas. In this work we test the idea that sports types can be classified from features extracted from short trajectories of the players. From tracklets created by a Kalman filter tracker we extract four robust features; Total distance, lifespan, distance span and mean speed. For clas- sification we use a quadratic discriminant analysis. In our experiments we use 30 2-minutes thermal video sequences from each of five different sports types. By applying a 10- fold cross validation we obtain a correct classification rate of 94.5 %.

AB - Automatic analysis of video is important in order to process and exploit large amounts of data, e.g. for sports analysis. Classification of sports types is one of the first steps to- wards a fully automatic analysis of the activities performed at sports arenas. In this work we test the idea that sports types can be classified from features extracted from short trajectories of the players. From tracklets created by a Kalman filter tracker we extract four robust features; Total distance, lifespan, distance span and mean speed. For clas- sification we use a quadratic discriminant analysis. In our experiments we use 30 2-minutes thermal video sequences from each of five different sports types. By applying a 10- fold cross validation we obtain a correct classification rate of 94.5 %.

M3 - Conference abstract for conference

ER -

Gade R, Moeslund TB. Classification of sports types from tracklets. 2014. Abstract from KDD Workshop on Large-scale Sports Analytics, New York, United States.