This paper studies the notion of hierarchical (chained) structure of stochastic tracking of marked feature points while a person is\nmoving in the field of view of a RGB and depth sensor.The objective is to explore how the information between the two sensing\nmodalities (namely, RGB sensing and depth sensing) can be cascaded in order to distribute and share the implicit knowledge\nassociated with the tracking environment. In the first layer, the prior estimate of the state of the object is distributed based on the\nnovel expected motion constraints approach associated with the movements. For the second layer, the segmented output resulting\nfrom the RGB image is used for tracking marked feature points of interest in the depth image of the person. Here we proposed two\napproaches for associating a measure (weight) for the distribution of the estimates (particles) of the tracking feature points using\ndepth data. The first measure is based on the notion of spin-image and the second is based on the geodesic distance. The paper\npresents the overall implementation of the proposed method combined with some case study results.
Loading....