Multiple Target Tracking Using Reverse Prediction Weighted Neighbor Data Association
Zhongzhi Li, Xuegang Wang · Journal of Convergence Information Technology · 2010
Abstract A new data association method is presented for multiple target tracking. The proposed method is formulated using reverse prediction weighted neighbor to calculate the probability of candidate measurements from targets. The purpose of the proposed method is to eliminate the need to acquire prior knowledge such as detection probability and clutter density. The probability between targets and measurements are reflected in the reverse prediction residual norm.