Temporal multi-modal mean

A temporal reasoning technique is presented for scene analysis. Rather than simply classifying everything in a scene as either dynamically moving foreground or long-lasting, stationary background, a temporal model is used to place each scene object in time relative to each other. It attributes each scene object with temporal information, such as object age and observability (i.e., how often it is observed). This technique provides richer information about temporal scene events than traditional foreground/background segmentation. It builds on an existing low-cost adaptive background modeling technique that makes it suitable for embedded, real-time platforms.