Gaussian Mixture Reduction for Tracking Multiple Maneuvering Targets in Clutter
Jason Louis Williams · Defense Technical Information Center (DTIC) · 2003
The problem of tracking multiple maneuvering targets in clutter naturally leads to a Gaussian mixture representation of the Provability Density Function (PDF) of the target state vector. State-of-the-art Multiple Hypothesis Tracking (MHT) techniques maintain the mean, covariance and probability weight corresponding to each hypothesis, yet they rely on ad hoc merging and pruning rules to control the growth of hypotheses.