Movement Tracking from Monocular Video Based on the Particle Filter
Lei Lyu, Naiqi Ma, Hong Liu · 2017
Human motion tracking from monocular video has received increasing attention in recent years due to its broad applications. Among these human motion tracking methods, the particle filter is considered as an effective approach for human motion tracking. However, there are still two limitations of current particle filter approaches such as the prior used for the filtering step is often poor due to relatively large, poorly modeled inter-frame motion and the use of the prior as an importance function results in inefficient sampling of the posterior. In this paper, we present a new approach to track 3D human motion from video clips with the assistance of a pre-captured motion library. We studied the application of particle filter to realize the basic principle of 3d human motion tracking, three-dimensional human body model, the evaluation function of the posture and dynamic model of the movement, and the results of the tracking test is given.