Performance evaluation of people tracking systems

Abstract

A tracking system outputs a separate motion trajectory for each moving object in a scene. The paper presents a problem of performance evaluation and performance metrics for real time systems that track people, or moving objects, in video sequences, and it proposes performance measurement methodology for such systems. Two approaches to measuring performance are presented. The first approach compares the computed motion trajectories to the reference trajectories. It enables a complete evaluation of tracking results, but reference trajectories it requires are difficult to get. The second, more practical approach identifies in the computed trajectories specific discrete events, such as line crossings, and compares sequences of these events to sequences of reference events, which are much easier to obtain than reference trajectories. These events can usually be chosen such that they reflect the application goal of a tracking system, e.g. counting people in an area. Precision of evaluation increases with density of events. Short event sequences measure the sensitivity and selectivity of a tracking method, i.e. how well it satisfies the "one person one trajectory" objective. Long sequences measure continuity of trajectories: how long a method can keep track of one person. The paper shows performance measurement results for a real time people tracking system developed by the authors.