3D human motion tracking by using interactive multiple models

Of different model-based methods in vision based human tracking, many state of the art works focus on the stochastic optimization method to search in a very high dimensional space and try to find the optimal solution according to a proper likelihood function. Seldom works perform a framework of interactive multiple models (IMM) to track a human for challenging problems, such as uncertainty of motion styles, imprecise detection of feature points and ambiguity of joint location. This paper presents a two-layer filter framework based on IMM to track human motion. First, a method of model based points location is proposed to detect key feature points automatically and the filter in the first layer is performed to estimate the undetected points. Second, multiple models of motion are learned by the prior motion data with ridge regression and the IMM algorithm is used to estimate the quaternion vectors of joints rotation. Finally, experiments using real images sequences, simulation videos and 3D voxel data demonstrate that this human tracking framework is efficient.     

Viewpoint manipulation for interactive television by using human pose estimation

In current interactive television schemes, the viewpoints should be manipulated by the user. However, there is no efficient method, to assist a user in automatically identifying and tracking the optimum viewpoint when the user observes the object of interest because many objects, most often humans, move rapidly and frequently. This paper proposes a novel framework for determining and tracking the virtual camera to best capture the front of the person of interest (PoI). First, one PoI is interactively chosen in a segmented 3D scene reconstructed by space carving method. Second, key points of the human torso of the PoI are detected by using a model-based method and the human’s global motion including rotation and translation is estimated by using a close-formed method with 3 corresponding points. At the last step, the front direction of PoI is tracked temporally by using the unscented particle filter (UPF). Experimental results show that the method can properly compute the front direction of the PoI and robustly track the best viewpoints.