2019/06/27 by Tullio Facchinetti, Rodolfo Metulini, Facchinetti, Tullio +3
Economics, Econometrics and Finance · Engineering · Medicine · #Applications (stat.AP) #FOS: Computer and information sciences #Other Statistics (stat.OT) #Sports Analytics and Performance #Sports Dynamics and Biomechanics #Sports Performance and Training
paper · pdf · doi:10.48550/arxiv.1906.11720
openalex publication_date 2019/06/27 · openalex created_date 2022/07/28 · openalex updated_date 2026/07/28
Data analytics in sports is crucial to evaluate the performance of single\nplayers and the whole team. The literature proposes a number of tools for both\noffence and defence scenarios. Data coming from tracking location of players,\nin this respect, may be used to enrich the amount of useful information. In\nbasketball, however, actions are interleaved with inactive periods. This paper\ndescribes a methodological approach to automatically identify active periods\nduring a game and to classify them as offensive or defensive. The method is\nbased on the application of thresholds to players kinematic parameters, whose\nvalues undergo a tuning strategy similar to Receiver Operating Characteristic\ncurves, using a ground truth extracted from the video of the games.\n