We propose a new method to quickly and accurately predict 3D positions of body joints from a single depth image, using no temporal information. We take an object recognition approach, designing an intermediate body parts representation that maps the difficult pose estimation problem into a simpler per-pixel classification problem. Our large and highly varied training dataset allows the classifi...

This paper presents a method for markerless human motion capture using a single camera. It uses tree-based filtering to efficiently propagate a probability distribution over poses of a 3D body model. The pose vectors and associated shapes are arranged in a tree, which is constructed by hierarchical pairwise clustering, in order to efficiently evaluate the likelihood in each frame. A new likelih...

Our paper addresses the problem of enforcing constraints in human body tracking. A projection technique is derived to impose kinematic constraints on independent multi-body motion: we show that for small motions the multi-body articulated motion space can be approximated by a linear manifold estimated directly from the previous body pose. We propose a learning approach to model non-linear const...

Reliable extraction of human pose features that are invariant to view angle and body shape changes is critical for advancing human movement analysis. In this dissertation, the multifactor analysis techniques, including the multilinear analysis and the multifactor Gaussian process methods, have been exploited to extract such invariant pose features from video data by decomposing various key cont...

This literature survey attempts to recent developments and current state-of-the-art in the field of body analysis by the use of non-intrusive optical systems. Markerless based human motion capture describes the activity of analysing and expressing human motion in mathematical terms. The survey shows that the task of motion capture can be divided into a number of systematically distinct groups, ...

A regression based method is proposed to recover human body pose from 3D voxel data. In order to do this we need to convert the voxel data into a feature vector. This is done using a Bayesian approach based on Mixture of Probabilistic PCA that transforms a collection of 3D shape context descriptors, extracted from the voxels, to a compact feature vector. For the regression, the newly-proposed M...

This paper presents an algorithm (SPEAR) for visually estimating the pose and shape of an underwater target without fiducials. The goal is to enable AUV/ROV stationkeeping with respect to targets about which nothing is known a priori. It will also enable relative positioning with respect to any face on the 3-D body. It uses a particle filter to simultaneously track the pose and reconstruct a 3-...

The objective of this work is to estimate upper body pose for signers in TV broadcasts. Given suitable training data, the pose is estimated using a random forest body joint detector. However, obtaining such training data can be costly. The novelty of this paper is a method of transfer learning which is able to harness existing training data and use it for new domains. Our contributions are: (i)...

This paper presents an approach for view-based recognition of gestures. The approach is based on representing each gesture as a sequence of learned body poses. The gestures are recognized through a probabilistic framework for matching these body poses and for imposing temporal constrains between different poses. Matching individual poses to image data is performed using a probabilistic formulat...

We present intuitive interfaces for interactively posing 3D human characters. The user can create desired fullbody poses by directly dragging points, modifying bone directions, or specifying distances between two points in 2D screen space. Designing such an interface for full-body pose modeling is challenging because many unnatural poses might be consistent with the ambiguous user input. The sy...