Showing papers by "Patrick Lucey published in 2015"

"Quality vs Quantity": Improved Shot Prediction in Soccer using Strategic Features from Spatiotemporal Data

Abstract: In this paper, we present a method which accurately estimates the likelihood of chances in soccer using strategic features from an entire season of player and ball tracking data taken from a professional league. From the data, we analyzed the spatiotemporal patterns of the ten-second window of play before a shot for nearly 10,000 shots. From our analysis, we found that not only is the game phase important (i.e., corner, free-kick, open-play, counter attack etc.), the strategic features such as defender proximity, interaction of surrounding players, speed of play, coupled with the shot location play an impact on determining the likelihood of a team scoring a goal. Using our spatiotemporal strategic features, we can accurately measure the likelihood of each shot. We use this analysis to quantify the efficiency of each team and their strategy.

Predicting Serves in Tennis using Style Priors

Abstract: In professional sport, an enormous amount of fine-grain performance data can be generated at near millisecond intervals in the form of vision-based tracking data. One of the first sports to embrace this technology has been tennis, where Hawk-Eye technology has been used to both aid umpiring decisions, and to visualize shot trajectories for broadcast purposes. These data have tremendous untapped applications in terms of "opponent planning'', where a large amount of recent data is used to learn contextual behavior patterns of individual players, and ultimately predict the likelihood of a particular type of serve. Since the type of serve selected by a player may be contingent on the match context (i.e., is the player down break-point, or is serving for the match etc.), the characteristics of the player (i.e., the player may have a very fast serve, hit heavy with topspin or kick, or slice serves into the body) as well as the characteristics of the opponent (e.g., the opponent may prefer to play from the baseline or "chip-and-charge'' into the net). In this paper we present a method which recommends the most likely serves of a player in a given context. We show by utilizing a "style prior", we can improve the prediction/recommendation. Such an approach also allows us to quantify the similarity between players, which is useful in enriching the dataset for future prediction. We conduct our analysis on Hawk-Eye data collected from three recent Australian Open Grand-Slam Tournaments and show how our approach can be used in practice.

Predicting Ball Ownership in Basketball from a Monocular View Using Only Player Trajectories

Abstract: Tracking objects like a basketball from a monocular view is challenging due to its small size, potential to move at high velocities as well as the high frequency of occlusion. However, humans with a deep knowledge of a game like basketball can predict with high accuracy the location of the ball even without seeing it due to the location and motion of nearby objects, as well as information of where it was last seen. Learning from tracking data is problematic however, due to the high variance in player locations. In this paper, we show that by simply "permuting" the multi-agent data we obtain a compact role-ordered feature which accurately predict the ball owner. We also show that our formulation can incorporate other information sources such as a vision-based ball detector to improve prediction accuracy.

Discovering methods of scoring in soccer using tracking data

Abstract: In soccer, when analyzing the performance of a team one of the key events to analyze is that of shots and goal-scoring. With the availability of fine-grained player and ball tracking data, it is now possible to find the common patterns a team uses via clustering multi-agent trajectories. The effectiveness of these methods can be then quantified by using a "expected goal value" (EGV) model which was recently proposed. Using an entire season of player and ball tracking data from Prozone, we show a method of both "discovering" and "quantifying" goal scoring methods of a team, which we also use to compare the "goal-scoring styles" of teams.

Softstar: heuristic-guided probabilistic inference

Abstract: Recent machine learning methods for sequential behavior prediction estimate the motives of behavior rather than the behavior itself. This higher-level abstraction improves generalization in different prediction settings, but computing predictions often becomes intractable in large decision spaces. We propose the Softstar algorithm, a softened heuristic-guided search technique for the maximum entropy inverse optimal control model of sequential behavior. This approach supports probabilistic search with bounded approximation error at a significantly reduced computational cost when compared to sampling based methods. We present the algorithm, analyze approximation guarantees, and compare performance with simulation-based inference on two distinct complex decision tasks.