Team Activity Recognition in Sports

Abstract

We introduce a novel approach for team activity recognition in sports. Given the positions of team players from a plan view of the playing field at any given time, we solve a particular Poisson equation to generate a smooth distribution defined on whole playground, termed the position distribution of the team. Computing the position distribution for each frame provides a sequence of distributions, which we process to extract motion features for team activity recognition. The motion features are obtained at each frame using frame differencing and optical flow. We investigate the use of the proposed motion descriptors with Support Vector Machines (SVM) classification, and evaluate on a publicly available European handball dataset. Results show that our approach can classify six different team activities and performs better than a method that extracts features from the explicitly defined positions. Our method is new and different from other trajectory-based methods. These methods extract activity features using the explicitly defined trajectories, where the players have specific positions at any given time, and ignore the rest of the playground. In our work, on the other hand, given the specific positions of the team players at a frame, we construct a position distribution for the team on the whole playground and process the sequence of position distribution images to extract motion features for activity recognition. Results show that our approach is effective.

Take your eyes off the ball: Improving ball-tracking by focusing on team play

“…The approach to recognizing team-level activity in European handball was proposed in [21]. The set of six manually-specified labels included "slowly going into offense," "offense fast break", etc., and the features were based on players' on the player density function defined over the whole court (obtained by solving a Poisson equation).…”

“…Summary The approaches such as [15][16][17]21,23,24] would benefit from automatic ball tracking. An effective formulation for achieving this goal is the main contribution of our paper.…”

Social Role Discovery in Human Events

“…[20] studied the problem of face recognition in social context. Social Interaction in Action Recognition Another related line of work has been the use of social interaction to aid group action recognition [14,3,6]. [14] explicitly models human interaction, while [3] uses features of people in spatio-temporal vicinity to detect group activities and jointly track multiple people.…”

“…We are only provided the event label for each video, and the number of roles to be discovered in an event. We assume that every video is pre-processed to obtain individual human tracks similar to [6,13].…”

An Evaluation of Local Action Descriptors for Human Action Classification in the Presence of Occlusion

“…Therefore, extensive research efforts have been devoted to develop novel approaches for action-based video analysis. Action oriented event detection is an important component for many video management applications especially in surveillance and security [13], sports video [8], and video archive search and indexing domains.…”