Real-time control of three-dimensional avatars is an important problem in the context of computer games and virtual environments. Avatar animation and control is difficult, however, because a large repertoire of avatar behaviors must be made available, and the user must be able to select from this set of behaviors, possibly with a low-dimensional input device. One appealing approach to obtaining a rich set of avatar behaviors is to collect an extended, unlabeled sequence of motion data appropriate to the application. In this paper, we show that such a motion database can be preprocessed for flexibility in behavior and efficient search and exploited for real-time avatar control. Flexibility is created by identifying plausible transitions between motion segments, and efficient search through the resulting graph structure is obtained through clustering. Three interface techniques are demonstrated for controlling avatar motion using this data structure: the user selects from a set of available choices, sketches a path through an environment, or acts out a desired motion in front of a video camera. We demonstrate the flexibility of the approach through four different applications and compare the avatar motion to directly recorded human motion.

We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor prior labelling of body parts in the image. Instead, it recovers pose by direct nonlinear regression against shape descriptor vectors extracted automatically from image silhouettes. For robustness against local silhouette segmentation errors, silhouette shape is encoded by histogramof-shape-contexts descriptors. For the main regression, we evaluate both regularized least squares and Relevance Vector Machine (RVM) regressors over both linear and kernel bases. The RVM’s provide much sparser regressors without compromising performance, and kernel bases give a small but worthwhile improvement in performance. For realism and good generalization with respect to viewpoints, we train the regressors on images resynthesized from real human motion capture data, and test it both quantitatively on similar independent test data, and qualitatively on a real image sequence. Mean angular errors of 6–7 degrees are obtained — a factor of 3 better than the current state of the art for the much simpler upper body problem. 1.

We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor prior labelling of body parts in the image. Instead, it recovers pose by direct nonlinear regression against shape descriptor vectors extracted automatically from image silhouettes. For robustness against local silhouette segmentation errors, silhouette shape is encoded by histogram-of-shape-contexts descriptors. We evaluate several different regression methods: ridge regression, Relevance Vector Machine (RVM) regression and Support Vector Machine (SVM) regression over both linear and kernel bases. The RVMs provide much sparser regressors without compromising performance, and kernel bases give a small but worthwhile improvement in performance. Loss of depth and limb labelling information often makes the recovery of 3D pose from single silhouettes ambiguous. We propose two solutions to this: the first embeds the method in a tracking framework, using dynamics from the previous state estimate to disambiguate the pose; the second uses a mixture of regressors framework to return multiple solutions for each silhouette. We show that the resulting system tracks long sequences stably, and is also capable of accurately reconstructing 3D human pose from single images, giving multiple possible solutions in ambiguous cases. For realism and good generalization over a wide range of viewpoints, we train the regressors on images resynthesized from real human motion capture data. The method is demonstrated on a 54-parameter full body pose model, both quantitatively on independent but similar test data, and qualitatively on real image sequences. Mean angular errors of 4–5 degrees are obtained — a factor of 3 better than the current state of the art for the much simpler upper body problem.

this paper we present a particle filter-based visual tracker that fuses three cues in a novel way: color, motion, and sound (Fig. 1). More specifically, we will introduce color as the main visual cue and fuse it, depending on the scenario under consideration, with either sound localization cues or motion activity cues. The generic objective is to track a specified object or region of interest in the sequence of images captured by the camera. We employ weak object models so as not to be too restrictive about the types of objects the algorithm can track, and to achieve robustness to large variations in the object pose, illumination, motion, etc. In this generic context, contour cues are less appropriate than color cues to characterize the visual appearance of tracked entities. The use of edge-based cues indeed requires that the class of objects to be tracked is known a priori and that rather precise silhouette models can be learned beforehand. Note however that such conditions are met in a number of tracking applications where shape cues are routinely used [2], [3], [25], [30], [40], [44], [53]

A major difficulty for 3D human body tracking from monocular image sequences is the near non-observability of kinematic degrees of freedom that generate motion in depth. For known link (body segment) lengths, the strict non-observabilities reduce to twofold ‘forwards/backwards flipping ’ ambiguities for each link. These imply 2 # links formal inverse kinematics solutions for the full model, and hence linked groups of O(2 # links) local minima in the model-image matching cost function. Choosing the wrong minimum leads to rapid mistracking, so for reliable tracking, rapid methods of investigating alternative minima within a group are needed. Previous approaches to this have used generic search methods that do not exploit the specific problem structure. Here, we complement these by using simple kinematic reasoning to enumerate the tree of possible forwards/backwards flips, thus greatly speeding the search within each linked group of minima. Our methods can be used either deterministically, or within stochastic ‘jump-diffusion ’ style search processes. We give experimental results on some challenging monocular human tracking sequences, showing how the new kinematic-flipping based sampling method improves and complements existing ones.

We present a method for recovering 3D human body motion from monocular video sequences based on a robust image matching metric, incorporation of joint limits and non-self-intersection constraints, and a new sample-and-refine search strategy guided by rescaled cost-function covariances. Monocular 3D body tracking is challenging: besides the difficulty of matching an imperfect, highly flexible, self-occluding model to cluttered image features, realistic body models have at least 30 joint parameters subject to highly nonlinear physical constraints, and at least a third of these degrees of freedom are nearly unobservable in any given monocular image. For image matching we use a carefully designed robust cost metric combining robust optical flow, edge energy, and motion boundaries. The nonlinearities and matching ambiguities make the parameter-space cost surface multi-modal, ill-conditioned and highly nonlinear, so searching it is difficult. We discuss the limitations of CONDENSATION-like samplers, and describe a novel hybrid search algorithm that combines inflated-covariance-scaled sampling and robust continuous optimization subject to physical constraints and model priors. Our experiments on challenging monocular sequences show that robust cost modeling, joint and selfintersection constraints, and informed sampling are all essential for reliable monocular 3D motion estimation.

Probabilistic models have been adopted for many computer vision applications, however inference in highdimensional spaces remains problematic. As the statespace of a model grows, the dependencies between the dimensions lead to an exponential growth in computation when performing inference. Many common computer vision problems naturally map onto the graphical model framework; the representation is a graph where each node contains a portion of the state-space and there is an edge between two nodes only if they are not independent conditional on the other nodes in the graph. When this graph is sparsely connected, belief propagation algorithms can turn an exponential inference computation into one which is linear in the size of the graph. However belief propagation is only applicable when the variables in the nodes are discrete-valued or jointly represented by a single multivariate Gaussian distribution, and this rules out many computer vision applications.

Many difficult visual perception problems, like 3D human motion estimation, can be formulated in terms of inference using complex generative models, defined over high-dimensional state spaces. Despite progress, optimizing such models is difficult because prior knowledge cannot be flexibly integrated in order to reshape an initially designed representation space. Nonlinearities, inherent sparsity of high-dimensional training sets, and lack of global continuity makes dimensionality reduction challenging and lowdimensional search inefficient. To address these problems, we present a learning and inference algorithm that restricts visual tracking to automatically extracted, non-linearly embedded, lowdimensional spaces. This formulation produces a layered generative model with reduced state representation, that can be estimated using efficient continuous optimization methods. Our prior flattening method allows a simple analytic treatment of low-dimensional intrinsic curvature constraints, and allows consistent interpolation operations.

This paper introduces an approach to performance animation that employs video cameras and a small set of retro-reflective markers to create a low-cost, easy-to-use system that might someday be practical for home use. The low-dimensional control signals from the user's performance are supplemented by a database of pre-recorded human motion. At run time, the system automatically learns a series of local models from a set of motion capture examples that are a close match to the marker locations captured by the cameras. These local models are then used to reconstruct the motion of the user as a full-body animation. We demonstrate the power of this approach with real-time control of six different behaviors using two video cameras and a small set of retro-reflective markers. We compare the resulting animation to animation from commercial motion capture equipment with a full set of markers.

This paper address the problems of modeling the appearance of humans and distinguishing human appearance from the appearance of general scenes. We seek a model of appearance and motion that is generic in that it accounts for the ways in which people's appearance varies and, at the same time, is specific enough to be useful for tracking people in natural scenes. Given a 3D model of the person projected into an image we model the likelihood of observing various image cues conditioned on the predicted locations and orientations of the limbs. These cues are taken to be steered filter responses corresponding to edges, ridges, and motioncompensated temporal differences. Motivated by work on the statistics of natural scenes, the statistics of these filter responses for human limbs are learned from training images containing hand-labeled limb regions. Similarly, the statistics of the filter responses in general scenes are learned to define a "background" distribution. The likelihood of observing a scene given a predicted pose of a person is computed, for each limb, using the likelihood ratio between the learned foreground (person) and background distributions. Adopting a Bayesian formulation allows cues to be combined in a principled way. Furthermore, the use of learned distributions obviates the need for hand-tuned image noise models and thresholds. The paper provides a detailed analysis of the statistics of how people appear in scenes and provides a connection between work on natural image statistics and the Bayesian tracking of people.