Automatic behavior analysis in tag games: from traditional spaces to interactive playgrounds

Abstract

Tag is a popular children's playground game. It revolves around taggers that chase and then tag runners, upon which their roles switch. There are many variations of the game that aim to keep children engaged by presenting them with challenges and different types of gameplay. We argue that the introduction of sensing and floor projection technology in the playground can aid in providing both variation and challenge. To this end, we need to understand players' behavior in the playground and steer the interactions using projections accordingly. In this paper, we first analyze the behavior of taggers and runners in a traditional tag setting. We focus on behavioral cues that differ between the two roles. Based on these, we present a probabilistic role recognition model. We then move to an interactive setting and evaluate the model on tag sessions in an interactive tag playground. Our model achieves 77.96 % accuracy, which demonstrates the feasibility of our approach. We identify several avenues for improvement. Eventually, these should lead to a more thorough understanding of what happens in the playground, not only regarding player roles but also when the play breaks down, for example when players are bored or cheat.

Play with Me! Gender-Typed Social Play Behavior Analysis in Interactive Tag Games

“…Manual Annotation of Data Although the performance of ITP's tracker is good (on average, two track switches per game session) [32], occasionally, the label assigned to each player by the ITP changes when players run too close to each other. For this study, we had to ensure that the labels assigned to the players at the beginning of the game were maintained throughout the entire session, as a player's starting position indicates its gender.…”

(Steering) Interactive Play Behavior

“…Fourth and optional, depending on the type of device and the goals, systems can be made more interactive by sending and comparing the states of multiple devices/players (between devices) and this provides more opportunities for play with multiple players, for example, turning on the lights around another goal once a player has past a defender and has scored 1 [58]. Besides promoting interactions and providing pleasing forms of feedback, interactive play systems can sense, detect, and observe behavior of the user, this allows us to intervene during play and adapt the game based on their interaction and performance [128,154,207,260].…”

“…It seems this would also allow for long-term testing in real-life settings. Various systems can also make use of logs of the system regarding interactions speeding up the evaluation process, for example, time-played [112,168] or use [112,263], the performed movements/actions [201], and positions of players [154,260].…”

“…Such a method has been used to show the amount of movement of groups of players in an interactive playground [128]. Instead of using the information based on all players, computer vision also allows researchers to track movement and position of players which can be used for more detailed evaluation purposes as well [154].…”

“…One could also start with analyses of children's play behavior [154]. Which can be followed by an iterative process of testing (low-fi) prototypes to make decisions regarding the design [127].…”