Big MaMUT is watching you _ interaction-tracking for instrumented environments

A major challenge in ubiquitous computing applications in intelligent environments is the simultaneous support of multiple users, especially when users interact with and move freely within the environment - without being equipped with sensors or personal devices. In such a situation, it is difficult to provide personalized services, which - for example - rely on user profiles or histories, if the user does not explicitly identify her- or himself with the system, whenever an interaction takes place. We chose a computer vision based approach to tackle this problem and divided the problem space into two concerns: Macro-tracking takes care of people tracking and consistent labelling of users in order to determine which user is in vicinity of a specific interactive device (e.g. a touchscreen); Micro-tracking observes the adjacency of such an interactive device to resolve ambiguities, in case that more than one person are potential interactors. The results of these two trackers are fused to conclude and assign persons to interactions, detected by the environment. We describe our implementation that can theoretically integrate arbitrary numbers of cameras, utilizing off-the-shelf-hardware, i.e. personal computers and cameras - which was one of the main requirements of MaMUT, the Macro- and Micro User Tracker.