Skip to Main Content
In this paper, we present an approach for multitarget association in 3D space using independent 2D based particle filters. The independent 2D particle filters decompose the 3D formulation and support multiple chances for the association. The proposed approach increases the association success rate. Furthermore, the approach is able to enhance the each target position estimation less sensitive to measurement noise. In this paper, we formulate the independent 2D based particle filters for multitarget association and compare the performance to a conventional approach through the Cramer Rao low bound (CRLB).