Signature-driven multi-target tracking

Tracking multiple maneuvering targets remains a challenge because of clutter and spurious targets. We propose a Signature-Driven multiple target Tracking (SDT) method which fuses target data in spectral, spatial and temporary spaces to form signatures of targets. Markov properties of target features and dynamics are well defined in the signature of targets so that the data association process in SDT is efficient and effective. The experimental results have shown its superior performance.