Articulated pose estimation via over-parametrization and noise projection

نویسنده

  • Jonathan Brookshire
چکیده

We describe an algorithm to estimate the pose of a generic articulated object. Our algorithm takes as input a description of the object and a potentially incomplete series of observations; it outputs an on-line estimate of the object’s configuration. This task is challenging because: (1) the distribution of object states is often multi-modal; (2) the object is not assumed to be under our control, limiting our ability to predict its motion; and (3) rotational joints make the state space highly non-linear. The proposed method represents three principal contributions to address these challenges. First, we use a particle filter implementation which is unique in that it does not require a reliable state transition model. Instead, the method relies primarily on observations during particle proposal, using the state transition model only at singularities. Second, our particle filter formulation explicitly handles missing observations via a novel proposal mechanism. Although existing particle filters can handle missing observations, they do so only by relying on good state transition models. Finally, our method evaluates noise in the observation space, rather than state space. This reduces the variability in performance due to choice of parametrization, and effectively handles non-linearities caused by rotational joints. We compare our method to a baseline implementation without these techniques and demonstrate, for a fixed error, more than an order-of-magnitude reduction in the number of required particles, an increase in the number of effective particles, and an increase in frame rate. Source code for the method is available at http://rvsn.csail.mit.edu/articulated.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Pose estimation from corresponding point data - Systems, Man and Cybernetics, IEEE Transactions on

Abstracr --Solutions for four different pose estimation problems are presented. Closed form least-squares solutions are given to the over constrained ZD-ZD and 3-D-3-D pose estimation problems. A globally convergent iterative technique is given for the 2-D perspective projection-3-D pose estimation problem. A simplified linear solution and a robust solution to the 2-D perspective projection-ZD ...

متن کامل

Learning Markerless Human Pose Estimation from Multiple Viewpoint Video

We present a novel human performance capture technique capable of robustly estimating the pose (articulated joint positions) of a performer observed passively via multiple view-point video (MVV). An affine invariant pose descriptor is learned using a convolutional neural network (CNN) trained over volumetric data extracted from a MVV dataset of diverse human pose and appearance. A manifold embe...

متن کامل

Bayesian Articulated Tracking Using Single Frame Pose Sampling

We propose a novel probabilistic tracking framework for articulated bodies that incorporates direct estimation of the pose posterior distribution. We derive a single frame articulated pose sampler, and perform Bayesian tracking over time via Monte Carlo integration. In contrast to traditional particle filtering approaches, which propagate individual samples through time and are sensitive to the...

متن کامل

Action recognition feedback-based framework for human pose reconstruction from monocular images

A novel framework based on action recognition feedback for pose reconstruction of articulated human body from monocular images is proposed in this paper. The intrinsic ambiguity caused by perspective projection makes it difficult to accurately recover articulated poses from monocular images. To alleviate such ambiguity, we exploit the high-level motion knowledge as action recognition feedback t...

متن کامل

Continuous - state Graphical Models for Object Localization , Pose Estimation and Tracking

of “Continuous-state Graphical Models for Object Localization, Pose Estimation and Tracking” by Leonid Sigal, Ph.D., Brown University, May 2008. Reasoning about pose and motion of objects, based on images or video, is an important task for many machine vision applications. Estimating the pose of articulated objects such as people and animals is particularly challenging due to the complexity of ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2014