Estimating the Number of Soccer Players using Simulation-based Occlusion Handling

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

130 Downloads (Pure)

Resumé

Estimating the number of soccer players is crucial in- formation for occupancy analysis and other monitoring ac- tivities in sports analysis. It depends on player detection in the field that should be independent of the environment and light conditions. Thermal cameras are therefore a bet- ter option over normal RGB cameras. Detection of non- occluded players is doable but precise estimation of number of the players in groups is hard to achieve. Here we pro- pose a novel method for estimating number of the players in groups using computer graphics and virtual simulations. Occlusion conditions are first classified by using distinctive set of features trained by a bagged tree classifier. Estima- tion of the number of players is then performed by maximum likelihood of probability density based approach to further classify the occluded players. The results show that the im- plemented strategy is capable of providing precise results even during occlusion conditions.
OriginalsprogEngelsk
Titel2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
ForlagIEEE
Publikationsdato2018
Sider1937-1946
ISBN (Trykt)978-1-5386-6101-7
ISBN (Elektronisk)978-1-5386-6100-0
DOI
StatusUdgivet - 2018
BegivenhedIEEE Conference on Computer Vision and Pattern Recognition, 2018 - Salt Lake City, USA
Varighed: 18 jun. 201822 jun. 2018

Konference

KonferenceIEEE Conference on Computer Vision and Pattern Recognition, 2018
LandUSA
BySalt Lake City
Periode18/06/201822/06/2018
NavnIEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
ISSN2160-7516

Fingerprint

Cameras
Computer graphics
Sports
Maximum likelihood
Classifiers
Monitoring
Hot Temperature

Citer dette

Huda, N. U., Jensen, K. H., Gade, R., & Moeslund, T. B. (2018). Estimating the Number of Soccer Players using Simulation-based Occlusion Handling. I 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (s. 1937-1946). IEEE. IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) https://doi.org/10.1109/CVPRW.2018.00236
Huda, Noor Ul ; Jensen, Kasper Halkjær ; Gade, Rikke ; Moeslund, Thomas B. / Estimating the Number of Soccer Players using Simulation-based Occlusion Handling. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, 2018. s. 1937-1946 (IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)).
@inproceedings{33f1f790ee3f439b80c96de4f7a89b05,
title = "Estimating the Number of Soccer Players using Simulation-based Occlusion Handling",
abstract = "Estimating the number of soccer players is crucial in- formation for occupancy analysis and other monitoring ac- tivities in sports analysis. It depends on player detection in the field that should be independent of the environment and light conditions. Thermal cameras are therefore a bet- ter option over normal RGB cameras. Detection of non- occluded players is doable but precise estimation of number of the players in groups is hard to achieve. Here we pro- pose a novel method for estimating number of the players in groups using computer graphics and virtual simulations. Occlusion conditions are first classified by using distinctive set of features trained by a bagged tree classifier. Estima- tion of the number of players is then performed by maximum likelihood of probability density based approach to further classify the occluded players. The results show that the im- plemented strategy is capable of providing precise results even during occlusion conditions.",
author = "Huda, {Noor Ul} and Jensen, {Kasper Halkj{\ae}r} and Rikke Gade and Moeslund, {Thomas B.}",
year = "2018",
doi = "10.1109/CVPRW.2018.00236",
language = "English",
isbn = "978-1-5386-6101-7",
pages = "1937--1946",
booktitle = "2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)",
publisher = "IEEE",
address = "United States",

}

Huda, NU, Jensen, KH, Gade, R & Moeslund, TB 2018, Estimating the Number of Soccer Players using Simulation-based Occlusion Handling. i 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), s. 1937-1946, Salt Lake City, USA, 18/06/2018. https://doi.org/10.1109/CVPRW.2018.00236

Estimating the Number of Soccer Players using Simulation-based Occlusion Handling. / Huda, Noor Ul; Jensen, Kasper Halkjær; Gade, Rikke; Moeslund, Thomas B.

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, 2018. s. 1937-1946.

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - Estimating the Number of Soccer Players using Simulation-based Occlusion Handling

AU - Huda, Noor Ul

AU - Jensen, Kasper Halkjær

AU - Gade, Rikke

AU - Moeslund, Thomas B.

PY - 2018

Y1 - 2018

N2 - Estimating the number of soccer players is crucial in- formation for occupancy analysis and other monitoring ac- tivities in sports analysis. It depends on player detection in the field that should be independent of the environment and light conditions. Thermal cameras are therefore a bet- ter option over normal RGB cameras. Detection of non- occluded players is doable but precise estimation of number of the players in groups is hard to achieve. Here we pro- pose a novel method for estimating number of the players in groups using computer graphics and virtual simulations. Occlusion conditions are first classified by using distinctive set of features trained by a bagged tree classifier. Estima- tion of the number of players is then performed by maximum likelihood of probability density based approach to further classify the occluded players. The results show that the im- plemented strategy is capable of providing precise results even during occlusion conditions.

AB - Estimating the number of soccer players is crucial in- formation for occupancy analysis and other monitoring ac- tivities in sports analysis. It depends on player detection in the field that should be independent of the environment and light conditions. Thermal cameras are therefore a bet- ter option over normal RGB cameras. Detection of non- occluded players is doable but precise estimation of number of the players in groups is hard to achieve. Here we pro- pose a novel method for estimating number of the players in groups using computer graphics and virtual simulations. Occlusion conditions are first classified by using distinctive set of features trained by a bagged tree classifier. Estima- tion of the number of players is then performed by maximum likelihood of probability density based approach to further classify the occluded players. The results show that the im- plemented strategy is capable of providing precise results even during occlusion conditions.

U2 - 10.1109/CVPRW.2018.00236

DO - 10.1109/CVPRW.2018.00236

M3 - Article in proceeding

SN - 978-1-5386-6101-7

SP - 1937

EP - 1946

BT - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

PB - IEEE

ER -

Huda NU, Jensen KH, Gade R, Moeslund TB. Estimating the Number of Soccer Players using Simulation-based Occlusion Handling. I 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE. 2018. s. 1937-1946. (IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)). https://doi.org/10.1109/CVPRW.2018.00236