Distributed space-time correlation model trajectory tracking method based on statistical inference

The invention relates to a distributed space-time correlation model trajectory tracking method based on statistical inference. Beacon nodes are deployed in the shape of an equidistant grid in a locating space according to longitudinal and transverse directions, and beacon node information is saved in each unknown node; the beacon nodes receiving notification information transmitted by the unknown nodes emit locating signals at a fixed frequency, and the unknown nodes receive and form multiple time sequences according to the beacon nodes; each unknown node constructs a boundary time sequence to detect a boundary crossing event and determine a corresponding time point; each unknown node constructs regional time window statistical quantity and infers the current region; the position of the intersection points of the trajectories and the boundary is inferred; and the trajectories are formed and the result is uploaded to aggregation nodes. According to the method, RSSI locating information probability distribution characteristics in the trajectory tracking problem and space-time data mining are overall considered, and the boundary crossing event and regional information are discovered through the method of time-space information statistical inference so that trajectory tracking can be realized.