Joint Target Detection, Tracking and Classification with Forward-Backward PHD Smoothing
For multi-target tracking in dense clutter, this work provides a more accurate joint tracking and classification solution.
The paper extends forward-backward PHD smoothing to incorporate target class information, enabling joint detection, tracking, and classification. The proposed method outperforms the state-of-the-art, reducing OSPA distance by up to 40%.
Forward-backward Probability Hypothesis Density (PHD) smoothing is an efficient way for target tracking in dense clutter environment. Although the target class has been widely viewed as useful information to enhance the target tracking, there is no existing work in literature which incorporates the feature information into PHD smoothing. In this paper, we generalized the PHD smoothing by extending the general mode, which includes kinematic mode, class mode or their combinations etc., to forward-backward PHD filter. Through a top-down method, the general mode augmented forward-backward PHD smoothing is derived. The evaluation results show that our approach out-performs the state-of-art joint detection, tracking and classification algorithm in target state estimation, number estimation and classification. The reduction of OSPA distance is up to 40%.