An Improved Data Association Algorithm for Multiple-Target Tracking

In tracking a single target in clutter, many algorithms have been developed. In multiple-target tracking, a number of the techniques have been exercised such as the JPDA and the multiple Hypothesis (MHT) schemes. Sub-optimal algorithms, such as the PDA filter, have been used widely since the optimal algorithms have an exponentially increasing computational complexity. An improved data association algorithm was presented considering the association precision and the project practice. At first, the approximate confirmation matrix was obtained through removing the small probability events. Then, the same source observations were classified into the same sets and the relevant confirmation matrix of each area was constructed. Both the distance between echoes and center of validation gates and the number of echoes are considered. The state was estimated in the same way as JPDA at last. The simulation results show that the proposed algorithm can maintain high association precision and tracking success ratio, so it is fitted to engineering.