A Novel Particle Filter based Object Tracking Framework via the Combination of State and Observation Optimization
Xudong Luo, Long Ye, Wei Zhong, Qin Zhang · 2013
Using particle filter to figure visual object tracking, a key problem is to choose appropriate image features as the observation model.In this paper, we present a novel particle filter based object tracking framework via the combination of state and observation optimization.We apply the technique to articulated human movement tracking.Result demonstrates the effectiveness of our method in solving the tracking problem like self-occlusion and cluttered background.