Abstract.
Successful multi-target tracking requires solving two prob- lems - localize the targets and label their identity. An isolated target’s identity can be unambiguously preserved from one frame to the next. However, for long sequences of many moving targets, like a football game, grouping scenarios will occur in which identity labellings cannot be main- tained reliably by using continuity of motion or appearance. This paper describes how to match targets’ identities despite these interactions. Tra jectories of when a target is isolated are found. These tra jectories end when targets interact and their labellings cannot be maintained. The interactions (merges and splits) of these tra jectories form a graph structure. Appropriate feature vectors summarizing particular qualities of each tra jectory are extracted. A clustering procedure based on these feature vectors allows the identities of temporally separated tra jectories to be matched. Results are shown from a football match captured by a wide screen system giving a full stationary view of the pitch.