Advanced statistics have proved to be a crucial tool for basketball coaches in order to improve training skills. Indeed, the performance of the team can be further optimized by studying the behaviour of players under certain conditions. In the United States of America, companies such as STATS or Second Spectrum use a complex multi-camera setup to deliver advanced statistics to all NBA teams, but the price of this service is far beyond the budget of the vast majority of European teams. For this reason, a first prototype based on positioning sensors is presented. An experimental dataset has been created and meaningful basketball features have been extracted. 97.9% accuracy is obtained using Support Vector Machines when identifying 5 different classic plays: floppy offense, pick and roll, press break, post-up situation and fast breaks. After recognizing these plays in video sequences, advanced statistics could be extracted with ease.
2019
IMVIP
Multi-Person Tracking by Multi-Scale Detection in Basketball Scenarios
Arbués-Sangüesa, A.,
Haro, G.,
and Ballester, C.
In Proceedings of the International Conference of Irish Machine Vision and Image Processing
2019
Tracking data is a powerful tool for basketball teams in order to extract advanced semantic information and statistics that might lead to a performance boost. However, multi-person tracking is a challenging task to solve in single-camera video sequences, given the frequent occlusions and cluttering that occur in a restricted scenario. In this paper, a novel multi-scale detection method is presented, which is later used to extract geometric and content features, resulting in a multi-person video tracking system. Having built a dataset from scratch together with its ground truth (more than 10k bounding boxes), standard metrics are evaluated, obtaining notable results both in terms of detection (F1-score) and tracking (MOTA). The presented system could be used as a source of data gathering in order to extract useful statistics and semantic analyses a posteriori.
ICAIS
Single-Camera Basketball Tracker through Pose and Semantic Feature Fusion
Arbués-Sangüesa, A.,
Ballester, C.,
and Haro, G.
In Proceedings of the International Conference on Artificial Intelligence in Sports
2019
Tracking sports players is a widely challenging scenario, specially in single-feed videos recorded in tight courts, where cluttering and occlusions cannot be avoided. This paper presents an analysis of several geometric and semantic visual features to detect and track basketball players. An ablation study is carried out and then used to remark that a robust tracker can be built with Deep Learning features, without the need of extracting contextual ones, such as proximity or color similarity, nor applying camera stabilization techniques. The presented tracker consists of: (1) a detection step, which uses a pretrained deep learning model to estimate the players pose, followed by (2) a tracking step, which leverages pose and semantic information from the output of a convolutional layer in a VGG network. Its performance is analyzed in terms of MOTA over a basketball dataset with more than 10k instances.
FCB
Head, Shoulders, Hip and Ball... Hip and Ball! Using Pose Data to Leverage Football Player Orientation
Arbués-Sangüesa, A.,
Martín, A.,
Ballester, C.,
and Haro, G.
Although orientation has proven to be a key skill of soccer players in order to succeed in a broad spectrum of plays, body orientation is a yet-little-explored area in sports analytics' research. Despite being an inherently ambiguous concept, player orientation can be defined as the projection (2D) of the normal vector placed in the center of the upper-torso of players (3D). This research presents a novel technique to obtain player orientation from monocular video recordings by mapping pose parts (shoulders and hips) in a 2D field by combining OpenPose with a super-resolution network, and merging the obtained estimation with contextual information (ball position). Results have been validated with players-held EPTS devices, obtaining a median error of 27 degrees/player. Moreover, three novel types of orientation maps are proposed in order to make raw orientation data easy to visualize and understand, thus allowing further analysis at team- or player-level.
CVSports
Using Player's Body-Orientation to Model Pass Feasibility in Soccer
Arbués-Sangüesa, A.,
Martín, A.,
Fernández, J.,
Ballester, C.,
and Haro, G.
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
2020
Given a monocular video of a soccer match, this paper presents a computational model to estimate the most feasible pass at any given time. The method leverages offensive player's orientation (plus their location) and opponents' spatial configuration to compute the feasibility of pass events within players of the same team. Orientation data is gathered from body pose estimations that are properly projected onto the 2D game field; moreover, a geometrical solution is provided, through the definition of a feasibility measure, to determine which players are better oriented towards each other. Once analyzed more than 6000 pass events, results show that, by including orientation as a feasibility measure, a robust computational model can be built, reaching more than 0.7 Top-3 accuracy. Finally, the combination of the orientation feasibility measure with the recently introduced Expected Possession Value metric is studied; promising results are obtained, thus showing that existing models can be refined by using orientation as a key feature. These models could help both coaches and analysts to have a better understanding of the game and to improve the players' decision-making process.
2021
AISA
Learning Football Body-Orientation as a Matter of Classification
Arbués-Sangüesa, A.,
Martín, A.,
Granero, P.,
Ballester, C.,
and Haro, G.
In Proceedings of the Artificial Intelligence in Sports Analytics workshop at the International Joint Conference on Artificial Intelligence
2021
Orientation is a crucial skill for football players that becomes a differential factor in a large set of events, especially the ones involving passes. However, existing orientation estimation methods, which are based on computer-vision techniques, still have a lot of room for improvement. To the best of our knowledge, this article presents the first deep learning model for estimating orientation directly from video footage. By approaching this challenge as a classification problem where classes correspond to orientation bins, and by introducing a cyclic loss function, a well-known convolutional network is refined to provide player orientation data. The model is trained by using ground-truth orientation data obtained from wearable EPTS devices, which are individually compensated with respect to the perceived orientation in the current frame. The obtained results outperform previous methods; in particular, the absolute median error is less than 12 degrees per player. An ablation study is included in order to show the potential generalization to any kind of football video footage.
RJSP
Towards Soccer Pass Feasibility Maps: the Role of Players' Orientation
Arbués-Sangüesa, A.,
Martín, A.,
Fernández, J.,
Haro, G.,
and Ballester, C.
Once player tracking has been established as one of the main data sources in soccer, many challenges have emerged for data scientists, who attempt to recognize patterns from 2D trajectories in order to build tools that might help coaches to improve the performance of their teams. For instance, pass models predict where the ball should go next during pass events. However, existing models are mainly fed with players' location and prior data, hence omitting critical pieces of information such as players' body orientation. This paper presents a computational model to obtain pass feasibility maps, where player orientation is exploited and analyzed. As a matter of fact, orientation proves to be crucial when modelling field-of-view and correct positioning of players, since it limits the potential receiving area of all candidates. Different proposals are given to evaluate the proposed pass feasibility map, reaching 0.46 and 0.79 in Top1 and Top3 accuracy, respectively, with a +0.2 boost obtained after merging positional data with orientation.
Awards
PhD Workshop: (UPF-DTIC 2018) - The Collider mVentures Award.