First-Order Approximation of the Random Set Cluster Process for Extended Target Tracking
Jens Honer, Hauke Kaulbersch · 2023
This work extends the extended target cluster process tracker [1] on learned spatial distribution by a first-order approximation in its associations. The first-order approximation provides a uni-modal posterior of the closed-form Bayesian recursion and thus, significant improvements in computational complexity and runtime at relatively little cost in estimation quality. We compare the relative performance of the proposed model with previously proposed approaches in a large-scale evaluation based on the Nuscenes data set.