Joint Tracking and Ground Plane Estimation下载

Abstract—We propose a novel framework that jointly estimates the ground plane and a target’s motion trajectory. This results in improvements for both. Estimating their joint posterior is based on Particle Markov Chain Monte Carlo (Particle MCMC). In Par- ticle MCMC, the best target state is inferred by a particle filter and the best ground plane is obtained by MCMC. Compared with conventional sampling methods that iteratively infer the best tar- get states and ground plane parameters, our method infers them jointly. This reduces sampling errors drastically. Experimental re- sults demonstrate that our method outperforms several state-of- the-art tracking methods, while the ground plane accuracy is also improved.