Details
| Original language | English |
|---|---|
| Article number | 15878 |
| Journal | Scientific reports |
| Volume | 13 |
| Publication status | Published - 23 Sept 2023 |
Abstract
The majority of soccer analysis studies investigates specific scenarios through the implementation of computational techniques, which involve the examination of either spatiotemporal position data (movement of players and the ball on the pitch) or event data (relating to significant situations during a match). Yet, only a few applications perform a joint analysis of both data sources despite the various involved advantages emerging from such an approach. One possible reason for this is a non-systematic error in the event data, causing a temporal misalignment of the two data sources. To address this problem, we propose a solution that combines the SwiftEvent online algorithm (Gensler and Sick in Pattern Anal Appl 21:543–562, 2018) with a subsequent refinement step that corrects pass timestamps by exploiting the statistical properties of passes in the position data. We evaluate our proposed algorithm on ground-truth pass labels of four top-flight soccer matches from the 2014/15 season. Results show that the percentage of passes within half a second to ground truth increases from 14 to 70%, while our algorithm also detects localization errors (noise) in the position data. A comparison with other models shows that our algorithm is superior to baseline models and comparable to a deep learning pass detection method (while requiring significantly less data). Hence, our proposed lightweight framework offers a viable solution that enables groups facing limited access to (recent) data sources to effectively synchronize passes in the event and position data.
ASJC Scopus subject areas
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Scientific reports, Vol. 13, 15878, 23.09.2023.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Synchronization of passes in event and spatiotemporal soccer data
AU - Biermann, Henrik
AU - Komitova, Rumena
AU - Raabe, Dominik
AU - Müller-Budack, Eric
AU - Ewerth, Ralph
AU - Memmert, Daniel
N1 - Funding Information: Open Access funding enabled and organized by Projekt DEAL. This study was funded by the BMBF (MM4SPA). The authors declare that they have no relevant financial or non-financial interests to disclose.
PY - 2023/9/23
Y1 - 2023/9/23
N2 - The majority of soccer analysis studies investigates specific scenarios through the implementation of computational techniques, which involve the examination of either spatiotemporal position data (movement of players and the ball on the pitch) or event data (relating to significant situations during a match). Yet, only a few applications perform a joint analysis of both data sources despite the various involved advantages emerging from such an approach. One possible reason for this is a non-systematic error in the event data, causing a temporal misalignment of the two data sources. To address this problem, we propose a solution that combines the SwiftEvent online algorithm (Gensler and Sick in Pattern Anal Appl 21:543–562, 2018) with a subsequent refinement step that corrects pass timestamps by exploiting the statistical properties of passes in the position data. We evaluate our proposed algorithm on ground-truth pass labels of four top-flight soccer matches from the 2014/15 season. Results show that the percentage of passes within half a second to ground truth increases from 14 to 70%, while our algorithm also detects localization errors (noise) in the position data. A comparison with other models shows that our algorithm is superior to baseline models and comparable to a deep learning pass detection method (while requiring significantly less data). Hence, our proposed lightweight framework offers a viable solution that enables groups facing limited access to (recent) data sources to effectively synchronize passes in the event and position data.
AB - The majority of soccer analysis studies investigates specific scenarios through the implementation of computational techniques, which involve the examination of either spatiotemporal position data (movement of players and the ball on the pitch) or event data (relating to significant situations during a match). Yet, only a few applications perform a joint analysis of both data sources despite the various involved advantages emerging from such an approach. One possible reason for this is a non-systematic error in the event data, causing a temporal misalignment of the two data sources. To address this problem, we propose a solution that combines the SwiftEvent online algorithm (Gensler and Sick in Pattern Anal Appl 21:543–562, 2018) with a subsequent refinement step that corrects pass timestamps by exploiting the statistical properties of passes in the position data. We evaluate our proposed algorithm on ground-truth pass labels of four top-flight soccer matches from the 2014/15 season. Results show that the percentage of passes within half a second to ground truth increases from 14 to 70%, while our algorithm also detects localization errors (noise) in the position data. A comparison with other models shows that our algorithm is superior to baseline models and comparable to a deep learning pass detection method (while requiring significantly less data). Hence, our proposed lightweight framework offers a viable solution that enables groups facing limited access to (recent) data sources to effectively synchronize passes in the event and position data.
UR - http://www.scopus.com/inward/record.url?scp=85172250639&partnerID=8YFLogxK
U2 - 10.1038/s41598-023-39616-2
DO - 10.1038/s41598-023-39616-2
M3 - Article
C2 - 37741829
AN - SCOPUS:85172250639
VL - 13
JO - Scientific reports
JF - Scientific reports
SN - 2045-2322
M1 - 15878
ER -