Screen-strategy analysis in broadcast basketball video using player tracking

Classification of Player Roles in the Team-Based Multi-player Game Dota 2

“…A notable domain difference compared to works for soccer is that not only the position of the goal is considered, but also the moment when the blue line is crossed. In basketball games, as presented by Fu et al [4], the actual tracking of the ball is less important for certain tactics. In order to detect offensive strategies they make use of the fact that defenders are closer to their basket than the offensive team to predict ball possession.…”

2D Histogram-based player localization in broadcast volleyball videos

“…Manually labeling the players and non-players in the game is labor intensive and time consuming, which motivates the development of automatic player localization systems. On the other hand, connected component analysis (CCA) [13] is one of the most employed methods [14,15] for fully automatic player localization. CCA retains the player regions by subtracting the court region and adopts morphological operations to remove noises.…”

“…Chang et al [14] extract players by CCA and design a wild-open warning (WOW) system to help basketball coaches and players in revealing possible tactics of their opponents according to the mutual players' locations between two teams. Fu et al [15] also first detect players by CCA and then analyze the screen strategies using player tracking in broadcast basketball accordingly. However, a main problem for CCA is to accurately locate the players while they occlude with others.…”

“…To validate the proposed 2D histogram-based player localization, we compare our approach to (1) connected component analysis (CCA)-based approach, which is a traditional object segmentation method widely used in most applications of automatic player localization [14,15], and (2) a supervised learning approach [11] adopting histogram of oriented gradient (HOG) features. A dominant color-based approach is also performed to retain the player masks for CCA.…”

Recognizing tactic patterns in broadcast basketball video using player trajectory

“…In basketball games, screen is the fundamental essence that most tactics are executed with. Enhanced from our previous work [24], a screen-strategy recognition system capable of detecting and classifying screen patterns in broadcast basketball video based on player trajectory is proposed in this paper. Fig.…”