3D People Tracking with Gaussian Process Dynamical Models

By Raquel Urtasun, David J. Fleet, Pascal Fua. Computer Vision and Pattern Recognition, 2006

534 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/ced298a2a8e39127b8adecfa56256f5c693f3a25

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

In Statistics and Probability

Citations in the corpus

Vision-based human motion analysis: An overview (2007, background): “In later work [119,115], a Gaussian Process Dynamical Model (GPDM) is learned from training data.”
Will the Pedestrian Cross? A Study on Pedestrian Path Prediction (2014, unknown): “Urtasun et al. [23] used a GPDM to track a small number of 3-”
Bayesian Optimization and Semiparametric Models with Applications to Assistive Technology (2014, methodology): “This was used by Urtasun et al. [2006] to very accurately infer the dynamics of a person in a visual tracking setting even in the presence of full occlusions.”
On Human Motion Prediction Using Recurrent Neural Networks (2017, background): “wide variety of fields, such as action prediction for sociallyaware robotics [21], 3D people tracking within computer vision [13,43], motion generation for computer graphics [22] or modeling biological motion in psychology [42].”
People-tracking-by-detection and people-detection-by-tracking (2008, background): “To work around these problems, a number of recent tracking approaches turned to feature-based detectors for matching tracking hypotheses, discriminative components, strong dynamical models, or alternative methods for exploring the search space [4, 23, 7, 22].”
A Non-parametric Bayesian Network Prior of Human Pose (2013, unknown): “The GPLVM model has also been extended to incorporate a temporal model (GPDM) [24].”
Pictorial structures revisited: People detection and articulated pose estimation (2009, background): “It is certainly possible to incorporate action specific constraints into the prior, and to combine them with articulation dynamics to enable tracking, as is done for example in [10] [23].”
HuMoR: 3D Human Motion Model for Robust Pose Estimation (2021, methodology): “, in PCA space [68, 93, 83] or via future-predicting autoregressive processes [88, 92, 74].”
Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation (2016, background): “feature descriptors [58, 62, 63] and 2D joint locations [2, 3, 5, 20, 36, 51, 57, 69, 70].”
Fusing 2D Uncertainty and 3D Cues for Monocular Body Pose Estimation (2016, background): “Over the years, two main classes of approaches have been proposed: Discriminative ones, that directly regress 3D pose from image data [2, 7, 31, 50, 61], and generative ones that search the pose space for a plausible skeleton configuration that aligns with the image data [20, 53, 62].”
VIBE: Video Inference for Human Body Pose and Shape Estimation (2019, methodology): “Early approaches also exploit methods like PCA and GPLVMs to learn motion priors from mocap data [49, 63] but these approaches were limited to simple motions.”
Hierarchical Gaussian process latent variable models (2007, methodology): “, 2004) learning a prior model for tracking (Urtasun et al., 2005; Urtasun et al., 2006) and robot simultaneous localisation and mapping (Ferris et al.”
Learning GP-BayesFilters via Gaussian process latent variable models (2009, methodology): “To see, we initialized the latent state of GPBF-LEARN using PCA, as is typically done for GPLVMs (Lawrence 2005; Urtasun et al. 2006; Wang et al. 2008).”