Spatio-temporal reasoning in biometrics based smart environments

We discuss smart environments that identify and track their occupants using unobtrusive recognition modalities such as face, gait, and voice. In order to alleviate the inherent limitations of recognition, we propose spatio-temporal reasoning techniques based upon an analysis of the occupant tracks. The key technical idea underlying our approach is to determine the identity of a person based upon information from a track of events rather than a single event. We abstract a smart environment by a probabilistic state transition system in which each state records a set of individuals who are present in various zones of the smart environment. An event abstracts a recognition step and the transition function defines the mapping between states upon the occurrence of an event. We define the concepts of 'precision' and 'recall' to quantify the performance of the smart environment. We provide experimental results to show performance improvements from spatio-temporal reasoning. Our conclusion is that the state transition system is an effective abstraction of a smart environment and the application of spatial-temporal reasoning enhances its overall performance.