Using symmetric state transformations for multi-target tracking

This paper is about the use of symmetric state transformations for multi-target tracking. First, a novel method for obtaining point estimates for multi-target states is proposed. The basic idea is to apply a symmetric state transformation to the original state in order to compute a minimum mean-square-error (MMSE) estimate in a transformed state. By this means, the known shortcomings of MMSE estimates for multi-target states can be avoided. Second, a new multi-target tracking method based on state transformations is suggested, which entirely performs the time and measurement update in a transformed space and thus, avoids the explicit calculation of data association hypotheses and removes the target identity from the estimation problem. The performance of the new approach is evaluated by means of tracking two crossing targets.