Robust track-to-track association algorithm based on t-distribution mixture model
Baozhu Li, Ningbo Liu, Guoqing Wang, Lin Qi, Yunlong Dong · 2017
To address multi-sensor robust track-to-track association in the presence of sensor biases and missed detections, where sensors biases is time-varying and non-uniform, the target of different sensors is non-identical, the robust track-to-track association algorithm based on t-distribution mixture model is proposed. The robust track-to-track association problem is turned into the non-rigid point matching problem. Firstly, the orthogonal normalization reduce the general affine case of track point set; second, the heavy-tailed t-distribution mixture model is established with better robustness to tracks of non-common, solved by Expectation Maximization (EM) algorithm. The conditional expectation function is added a regular item of point sets that the points have a feature of Coherent Point Drift (CPD). Adaptability experiments are established to demonstrate the effectiveness of the proposed approaches compared with competing algorithms at the presence of sensor biases and missed detections.