Abstract.
This paper presents a scalable solution to the problem of tracking ob jects across spatially separated, uncalibrated, non-overlapping cameras. Unlike other approaches this technique uses an incremental learning method, to model both the colour variations and posterior prob- ability distributions of spatio-temporal links between cameras. These operate in parallel and are then used with an appearance model of the ob ject to track across spatially separated cameras. The approach requires no pre-calibration or batch preprocessing, is completely unsupervised, and becomes more accurate over time as evidence is accumulated.