Single camera pose estimation using Bayesian filtering and Kinect motion priors

by   Michael Burke, et al.

Traditional approaches to upper body pose estimation using monocular vision rely on complex body models and a large variety of geometric constraints. We argue that this is not ideal and somewhat inelegant as it results in large processing burdens, and instead attempt to incorporate these constraints through priors obtained directly from training data. A prior distribution covering the probability of a human pose occurring is used to incorporate likely human poses. This distribution is obtained offline, by fitting a Gaussian mixture model to a large dataset of recorded human body poses, tracked using a Kinect sensor. We combine this prior information with a random walk transition model to obtain an upper body model, suitable for use within a recursive Bayesian filtering framework. Our model can be viewed as a mixture of discrete Ornstein-Uhlenbeck processes, in that states behave as random walks, but drift towards a set of typically observed poses. This model is combined with measurements of the human head and hand positions, using recursive Bayesian estimation to incorporate temporal information. Measurements are obtained using face detection and a simple skin colour hand detector, trained using the detected face. The suggested model is designed with analytical tractability in mind and we show that the pose tracking can be Rao-Blackwellised using the mixture Kalman filter, allowing for computational efficiency while still incorporating bio-mechanical properties of the upper body. In addition, the use of the proposed upper body model allows reliable three-dimensional pose estimates to be obtained indirectly for a number of joints that are often difficult to detect using traditional object recognition strategies. Comparisons with Kinect sensor results and the state of the art in 2D pose estimation highlight the efficacy of the proposed approach.


page 5

page 14

page 17

page 18

page 19

page 20

page 21


Enhanced Mixtures of Part Model for Human Pose Estimation

Mixture of parts model has been successfully applied to 2D human pose es...

ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses

Human pose estimation from single images is a challenging problem that i...

Real-time Tracking-by-Detection of Human Motion in RGB-D Camera Networks

This paper presents a novel real-time tracking system capable of improvi...

RePose: Learning Deep Kinematic Priors for Fast Human Pose Estimation

We propose a novel efficient and lightweight model for human pose estima...

Automatic Analysis of Human Body Representations in Western Art

The way the human body is depicted in classical and modern paintings is ...

Split Happens! Imprecise and Negative Information in Gaussian Mixture Random Finite Set Filtering

In object tracking and state estimation problems, ambiguous evidence suc...

Automatic Assessment of Infant Face and Upper-Body Symmetry as Early Signs of Torticollis

We apply computer vision pose estimation techniques developed expressly ...

Please sign up or login with your details

Forgot password? Click here to reset