Simultaneous Pose Estimation of Multiple People using Multiple-View Cues with Hierarchical Sampling

Multiple Human Pose Estimation with Temporally Consistent 3D Pictorial Structures

“…In [14], a two-stage algorithm is applied on stereo data for detecting human and recovering their pose. Similar to our framework, a multi-view system has been employed in [20,21]. In [21], the proposed method can estimate the pose up to two people in a studio environment.…”

“…Similar to our framework, a multi-view system has been employed in [20,21]. In [21], the proposed method can estimate the pose up to two people in a studio environment. Our model does not have such limitations and it is mainly applied to unconstrained environments.…”

“…In the 3D space, the problem of multiple human pose estimation has been addressed using monocular [5,18,29], stereo [14,23] or multi-camera input information [21,20]. In [29] and [18], the monocular 3D pose estimation has been combined with tracking.…”

“…In every application, the human motion remains consistent over time. Different approaches have been proposed for multiple human pose estimation on 2D [1,4,10,24] or 3D space [5,6,14,20,21]. Nevertheless, the utility of temporal consistency for pose estimation has not been sufficiently addressed yet.…”

Feature-Based Annealing Particle Filter for Robust Body Pose Estimation

“…Particle Filters (Arulampalam et al, 2002) have become a relevant technique due to their ability to precisely estimate the statistics of such processes. Several approaches such as partitioned sampling (MacCormick and Isard, 2000), hierarchical sampling (Mitchelson and Hilton, 2003) and annealing particle filter (Deutscher et al, 2000) have been developed to cope with highdimensional limitations of the classical Condensation algorithm (Isard and Blake, 1998). This paper presents a new annealing particle filter approach based on the properties of image features.…”