An Efficient Implementation of Track-Oriented Multiple Hypothesis Tracker Using Graphical Model Approaches

Algorithm 1

MPBP-MHT algorithm. Note. For computational stability, it is often recommended that messages should be normalized in each iteration.

Input: graph , including a cluster of family, track score and track ICL.

Output: best global hypothesis

(1) initialization: set with (15).

(2) iteration: At iteration n for all nodes

(a) Calculate new message which is sent by the node to all its neighbors with (17).

(b) Calculate the belief at each node with (19).

(c) Decision: for each node , compare and ; if , set .

(3) if converges, finish the iteration and output ; else set and go to step (2)