A Novel Gaussian Particle PHD Filter for Multi-Target Tracking
The Gaussian particle probability hypothesis density filter (GPPHDF) needs conventional Monte-Carlo (MC) sampling in predict step and update step, which decreases the accuracy and real-time performance of the algorithm. This paper employs Quasi-Monte-Carlo (QMC) sampling to replace MC sampling, and QMC integration method is introduced to approximating the prediction and update distributions of target states. Hence a tracking algorithm based on the QMC method is proposed, which reduces the computational complexity and improves the accuracy and stability of the tracking algorithm.
Z. J. Huang et al., "A Novel Gaussian Particle PHD Filter for Multi-Target Tracking", Applied Mechanics and Materials, Vols. 130-134, pp. 3143-3147, 2012