A trajectory-based analysis of coordinated team activity in a basketball game

Perše, Matej; Kristan, Matej; Kovačič, Stanislav; Vučković, Goran; Perš, Janez

doi:10.1016/j.cviu.2008.03.001

Cited by 102 publications

(80 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Notably missing from the scope was tracking the basketball itself, which was explained in the paper by the "state of technology." However, the authors of [16] noted that knowing the ball location would "considerably improve the performance..." of their system. Systems for analyzing hockey games were described in [18][19][20].…”

Section: Exploiting the Context Of A Ball-centric Team Sportmentioning

confidence: 99%

“…Systems for analyzing hockey games were described in [18][19][20]. Similar to the system of [16], the system of [20] comprised components for player tracking, and the recognition of several elements of the play, e.g., power play shot. The location of the hockey puck was essential for their recognition algorithm, but the authors relied on the manual localization of the puck.…”

Section: Exploiting the Context Of A Ball-centric Team Sportmentioning

confidence: 99%

“…We view the relation between the two sets of approaches as complimentary: many of those prior approaches to game analysis rely on a manual labeling of the ball and would therefore benefit from our formulation. Conversely, our end-to-end demonstration system requires an estimate of the phase of the game, which is obtained using the features of [16], and which we describe next.…”

Section: Exploiting the Context Of A Ball-centric Team Sportmentioning

confidence: 99%

“…Recognizing elements of the game from player trajectories A system for analyzing basketball games was described in [16]. The system comprised several components, including tracking, recognizing which team was attacking, which elements of the play were being executed, etc.…”

Section: Exploiting the Context Of A Ball-centric Team Sportmentioning

confidence: 99%

“…Summary The approaches such as [15][16][17]21,23,24] would benefit from automatic ball tracking. An effective formulation for achieving this goal is the main contribution of our paper.…”

Section: Exploiting the Context Of A Ball-centric Team Sportmentioning

confidence: 99%

See 4 more Smart Citations

Take your eyes off the ball: Improving ball-tracking by focusing on team play

Wang

Ablavsky

Shitrit

et al. 2014

Computer Vision and Image Understanding

View full text Add to dashboard Cite

Abstract. Accurate video-based ball tracking in team sports is important for automated game analysis, and has proven very difficult because the ball is often occluded by the players. In this paper, we propose a novel approach to addressing this issue by formulating the tracking in terms of deciding which player, if any, M is in possession of the ball at any given time. This is very different from standard approaches that first attempt to track the ball and only then to assign possession. We will show that our method substantially increases performance when applied to long basketball and soccer sequences.

show abstract

Section: Exploiting the Context Of A Ball-centric Team Sportmentioning

confidence: 99%

Section: Exploiting the Context Of A Ball-centric Team Sportmentioning

confidence: 99%

Section: Exploiting the Context Of A Ball-centric Team Sportmentioning

confidence: 99%

Section: Exploiting the Context Of A Ball-centric Team Sportmentioning

confidence: 99%

“…Summary The approaches such as [15][16][17]21,23,24] would benefit from automatic ball tracking. An effective formulation for achieving this goal is the main contribution of our paper.…”

Section: Exploiting the Context Of A Ball-centric Team Sportmentioning

confidence: 99%

See 3 more Smart Citations

Take your eyes off the ball: Improving ball-tracking by focusing on team play

Wang

Ablavsky

Shitrit

et al. 2014

Computer Vision and Image Understanding

View full text Add to dashboard Cite

show abstract

Using machine learning to draw inferences from pass location data in soccer

Brooks

Kerr

Guttag

2016

Statistical Analysis

View full text Add to dashboard Cite

In this paper, we present two approaches to analyzing pass event data to uncover sometimes-nonobvious insights into the game of soccer. We illustrate the utility of our methods by applying them to data from the 2012-2013 La Liga season. We first show that teams are characterized by where on the pitch they attempt passes, and can be identified by their passing styles. Using heatmaps of pass locations as features, we achieved a mean accuracy of 87% in a 20-team classification task. We also investigated using pass locations over the course of a possession to predict shots. For this task, we achieved an area under the receiver operating characteristic (AUROC) of 0.785. Finally, we used the weights of the predictive model to rank players by the value of their passes. Shockingly, Cristiano Ronaldo and Lionel Messi topped the rankings.Despite this problem, we demonstrate in this paper that by using machine learning techniques on passing data from the 2012-2013 La Liga season, we could uncover relevant data-driven insights into soccer.1. We show that heatmaps built using only the origins of passes provide fingerprints that can be used to identify teams with 87% accuracy.2. We further show that even when we only consider passes originating from the midfield, the resulting heatmaps can still be used to identify teams.3. We construct a model relating pass origins and destinations during a possession with the probability of a shot. The resulting weights offer insights into the offensive utility of passes.4. We utilize this model to rank players by the frequency with which their passes are highly valued by the model.The rest of the paper is organized as follows. In Section 2, we outline some previous related work on using machine learning for knowledge discovery in soccer and other sports. In Section 3, we describe the event-based dataset we used

show abstract

SAI: Sports Analysis and Informatics

Kambhamettu

2020

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

A trajectory-based analysis of coordinated team activity in a basketball game

Cited by 102 publications

References 18 publications

Take your eyes off the ball: Improving ball-tracking by focusing on team play

Take your eyes off the ball: Improving ball-tracking by focusing on team play

Using machine learning to draw inferences from pass location data in soccer

SAI: Sports Analysis and Informatics

Contact Info

Product

Resources

About