3D Pictorial Structures for Multiple View Articulated Pose Estimation

By Magnus Burenius, Josephine Sullivan, Stefan Carlsson. 2013

166 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, background): “Among a large number of human representation approaches [24], [25], [26], [27], [28], [29], most of the existing 3D based methods can be broadly grouped into two categories: representations based on local features [30], [31] and skeletonbased representations [32] [33] [34].”
Panoptic Studio: A Massively Multiview System for Social Motion Capture (2015, methodology): “We compare our method with two different baselines: multiple Kinects and 3D pictorial structure method similar to [8, 5].”
Multi-view Body Part Recognition with Random Forests (2013, methodology): “Depending on whether we have a continuous or discrete state space a solution can be found using either stochastic optimization [19] or dynamic programming [2, 4, 17].”
Efficient ConvNet-based marker-less motion capture in general scenes with a low number of cameras (2015, background): “The sequences vary in the numbers and identities of actors to track, the existence and number of moving objects in the background, and the lighting conditions (i.e. some body parts lit and some in shadow).”
Body Parts Dependent Joint Regressors for Human Pose Estimation in Still Images (2014, background): “E-mail: {dantone, vangool}@vision.ee.ethz.ch • Juergen Gall is with the Computer Vision Group, University of Bonn, Germany.”
MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior (2017, unknown): “so shown. TABLE 8 Quantitative results on KTH Football II [74]. The table presents the mean PCP scores (the higher the better). The sequences of Player 2 from Camera 1 are used. Sequence 1 Sequence 2 [74] [41] Proposed Proposed Upper Arms 14 74 89 61 Lower Arms 06 49 78 49 Upper Legs 63 98 99 77 Low”
Panoptic Studio: A Massively Multiview System for Social Interaction Capture (2016, methodology): “A few methods facilitate body pose detectors in multiple views to reconstruct 3D body poses [46], [47], [48], [49], [50].”
Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose (2016, background): “Finally, for KTH the percentage of the correctly estimated parts in 3D (3D PCP [7]) is reported.”
3D Pictorial Structures for Multiple Human Pose Estimation (2014, methodology): “Moreover, our prior model is stronger than a binary voting for a body part configuration [8] and less computational expensive than [24].”
Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation (2016, methodology): “6m [30] and KTH Multiview Football II [10] datasets.”
Self-Supervised Learning of 3D Human Pose Using Multi-View Geometry (2019, methodology): “Early work [1, 5, 6, 3, 4] used 2D pose estimations obtained from calibrated cameras to produce 3D pose by triangulation or pictorial structures model.”
Deep Learning-based Human Pose Estimation: A Survey (2020, methodology): “The widely used 3D pictorial structure model [13] is such a model.”
Fusing 2D Uncertainty and 3D Cues for Monocular Body Pose Estimation (2016, methodology): “On the KTH Multiview Football II dataset, we evaluate our method on the sequence containing Player 2, as in [6, 9, 59].”
3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network (2014, methodology): “[8] proposes to apply PSM to 3D pose estimation by discretizing the space.”
A Review of Human Activity Recognition Methods (2015, background): “Many approaches, which employ background subtraction (Sigal et al., 2012a) or assume fixed limb lengths and uniformly distributed rotations of body parts (Burenius et al., 2013), have been proposed to reduce the complexity of the 3D space.”
3D Human pose estimation: A review of the literature and analysis of covariates (2016, methodology): “[45] the first obstacle that the authors wanted to overcome is the high dimensional complex state space.”