Partitioned Sampling, Articulated Objects, and Interface-Quality Hand Tracking

By John MacCormick, Michael Isard. European Conference on Computer Vision, 2000

569 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/86efc15754e34254e5991c3a0fdcffbffbc47a3e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Lattice Particle Filters (2001, methodology): “Towards this end MacCormick and Isard [16] used partitioned-sampling to track articulated objects.”
Data fusion for visual tracking with particles (2004, background): “…, including visual servoing (e.g., [34]), surveillance (e.g., [19]), gestural human–machine interfaces and smart environments (e.g., [11], [33], [38]), video compression (e.g., [56]), augmented reality and visual effects (e.g., [35]), motion capture (e.g., [36]), environmental imaging…”
Covariance scaled sampling for monocular 3D body tracking (2001, unknown): “Partitioned sampling [ 20 ] is another notable sampling technique for articulated models, under certain labelling assumptions [20, 9].”
Hand gesture recognition using multi-scale colour features, hierarchical models and particle filtering (2002, methodology): “The idea is related to previous works on partitioned sampling [15] and layered sampling [19].”
Interactive Markerless Articulated Hand Motion Tracking Using RGB and Depth Data (2013, background): “Other model-based global optimization approaches suffer from the same runtime performance problem [12, 22].”
Capturing Hands in Action Using Discriminative Salient Points and Physics Simulation (2015, background): “Several filtering approaches have been presented (Bray et al, 2007; MacCormick and Isard, 2000; Stenger et al, 2001; Wu et al, 2001), while also belief-propagation proved to be suitable for articulated objects (Hamer et al, 2009, 2010; Sudderth et al, 2004).”
Monocular Pedestrian Detection: Survey and Experiments (2009, unknown): “For this, either single [4], [26], [55], [70], [76] or multiple cues [32], [43], [50], [58], [65] are used.”
Learning Joint Reconstruction of Hands and Manipulated Objects (2019, unknown): “Early work focused on hand estimation and tracking using articulated models [15, 44, 58, 71] or statistical shape models [26].”
Pose estimation for a partially observable human body from RGB-D cameras (2015, unknown): “In fact, the method tries to bend the legs to the torso to reduce the cost function which yields to a tracking failure when the legs are visible again.”
Articulated Body Motion Capture by Stochastic Search (2005, methodology): “In fact it has been shown by MacCormick [16] that d e f h g p i r q s 1 t where d is the number of particles required, u is the number of dimensions.”
Capturing natural hand articulation (2001, methodology): “Different sampling techniques were also investigated to reduce the number of samples, such as partitioned sampling scheme [10] and annealed particle filtering scheme [2].”
Implicit Probabilistic Models of Human Motion for Synthesis and Tracking (2002, methodology): “Using particle filtering methods as we do here is problematic given that the number of required particles is N ∝ 1/α where α 1 depends on the generality of the motion model, and d is the number of parameters [23].”
A Survey on Human Motion Analysis from Depth Data (2013, methodology): “Other methods rely on filtering techniques like Kalman filter [122] or particle filter [123].”
Model-based 3D tracking of an articulated hand (2001, background): “Recently, a vision based drawing system was proposed in [ 16 ].”