Sports Type Classification using Signature Heatmaps

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

12 Citations (Scopus)
380 Downloads (Pure)

Abstract

Automatic classification of activities in a sports arena is important in order to analyse and optimise the use of the arenas. In this work we classify five sports types based only on occupancy heatmaps produced from position data. Due to privacy issues we use thermal imaging for detecting people and then calculate their positions on the court us- ing homography. Heatmaps are produced by summarising Gaussian distributions respresenting people over 10-minute periods. Before classification the heatmaps are projected to a low-dimensional discriminative space using the principle of Fisherfaces. Our result using two weeks of video are very promising with a correct classification of 90.76 %.
Original languageEnglish
Title of host publicationProceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Number of pages6
PublisherIEEE
Publication date2013
Pages999-1004
ISBN (Print)9781479909940
ISBN (Electronic)978-0-7695-4990-3
DOIs
Publication statusPublished - 2013
Event2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) - Portland, Oregon, United States
Duration: 23 Jun 201328 Jun 2013

Conference

Conference2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
CountryUnited States
CityPortland, Oregon
Period23/06/201328/06/2013
SeriesI E E E Conference on Computer Vision and Pattern Recognition. Proceedings
ISSN1063-6919

Fingerprint

Sports
Gaussian distribution
Infrared imaging

Cite this

Gade, R., & Moeslund, T. B. (2013). Sports Type Classification using Signature Heatmaps. In Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 999-1004). IEEE. I E E E Conference on Computer Vision and Pattern Recognition. Proceedings https://doi.org/10.1109/CVPRW.2013.145
Gade, Rikke ; Moeslund, Thomas B. / Sports Type Classification using Signature Heatmaps. Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, 2013. pp. 999-1004 (I E E E Conference on Computer Vision and Pattern Recognition. Proceedings).
@inproceedings{46d906a967754ebd8f439f05e11d6fff,
title = "Sports Type Classification using Signature Heatmaps",
abstract = "Automatic classification of activities in a sports arena is important in order to analyse and optimise the use of the arenas. In this work we classify five sports types based only on occupancy heatmaps produced from position data. Due to privacy issues we use thermal imaging for detecting people and then calculate their positions on the court us- ing homography. Heatmaps are produced by summarising Gaussian distributions respresenting people over 10-minute periods. Before classification the heatmaps are projected to a low-dimensional discriminative space using the principle of Fisherfaces. Our result using two weeks of video are very promising with a correct classification of 90.76 {\%}.",
author = "Rikke Gade and Moeslund, {Thomas B.}",
year = "2013",
doi = "10.1109/CVPRW.2013.145",
language = "English",
isbn = "9781479909940",
series = "I E E E Conference on Computer Vision and Pattern Recognition. Proceedings",
publisher = "IEEE",
pages = "999--1004",
booktitle = "Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)",
address = "United States",

}

Gade, R & Moeslund, TB 2013, Sports Type Classification using Signature Heatmaps. in Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, I E E E Conference on Computer Vision and Pattern Recognition. Proceedings, pp. 999-1004, 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Portland, Oregon, United States, 23/06/2013. https://doi.org/10.1109/CVPRW.2013.145

Sports Type Classification using Signature Heatmaps. / Gade, Rikke; Moeslund, Thomas B.

Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, 2013. p. 999-1004 (I E E E Conference on Computer Vision and Pattern Recognition. Proceedings).

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Sports Type Classification using Signature Heatmaps

AU - Gade, Rikke

AU - Moeslund, Thomas B.

PY - 2013

Y1 - 2013

N2 - Automatic classification of activities in a sports arena is important in order to analyse and optimise the use of the arenas. In this work we classify five sports types based only on occupancy heatmaps produced from position data. Due to privacy issues we use thermal imaging for detecting people and then calculate their positions on the court us- ing homography. Heatmaps are produced by summarising Gaussian distributions respresenting people over 10-minute periods. Before classification the heatmaps are projected to a low-dimensional discriminative space using the principle of Fisherfaces. Our result using two weeks of video are very promising with a correct classification of 90.76 %.

AB - Automatic classification of activities in a sports arena is important in order to analyse and optimise the use of the arenas. In this work we classify five sports types based only on occupancy heatmaps produced from position data. Due to privacy issues we use thermal imaging for detecting people and then calculate their positions on the court us- ing homography. Heatmaps are produced by summarising Gaussian distributions respresenting people over 10-minute periods. Before classification the heatmaps are projected to a low-dimensional discriminative space using the principle of Fisherfaces. Our result using two weeks of video are very promising with a correct classification of 90.76 %.

U2 - 10.1109/CVPRW.2013.145

DO - 10.1109/CVPRW.2013.145

M3 - Article in proceeding

SN - 9781479909940

T3 - I E E E Conference on Computer Vision and Pattern Recognition. Proceedings

SP - 999

EP - 1004

BT - Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

PB - IEEE

ER -

Gade R, Moeslund TB. Sports Type Classification using Signature Heatmaps. In Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE. 2013. p. 999-1004. (I E E E Conference on Computer Vision and Pattern Recognition. Proceedings). https://doi.org/10.1109/CVPRW.2013.145