Track association and fusion with heterogeneous local trackers

Summary form only given. The problem of track-to-track association and track fusion has been considered in the literature where the local trackers assume the same target motion model and send their local state estimates to the fusion center on demand. Many issues arise when local trackers use different target motion models or even operate on different target state spaces. In this case, selecting an appropriate track association method at the fusion center is essential to the performance of the overall tracking system. In this paper, we examine several track association methods with different assumptions on the target distribution in a surveillance region. We found that the track association performance can be very different among these methods even when they have the same desired significance level of the correct association probability. We recommend to use the track association method that best approximates the likelihood ratio test with complete knowledge of the target distribution. In addition, existing track fusion techniques have to be modified to account for the model mismatch among some of the local trackers. The track association and fusion problem is illustrated by a two dimensional tracking example with both radar tracks and electronic support measures (ESM) tracks.