This paper proposes a method for capturing the performance of a human or an animal from a multi-view video sequence. Given an articulated template model and silhouettes from a multi-view image sequence, our approach recovers not only the movement of the skeleton, but also the possibly non-rigid temporal deformation of the 3D surface. While large scale deformations or fast movements are captured by the skeleton pose and approximate surface skinning, true small scale deformations or non-rigid garment motion are captured by fitting the surface to the silhouette. We further propose a novel optimization scheme for skeleton-based pose estimation that exploits the skeleton’s tree structure to split the optimization problem into a local one and a lower dimensional global one. We show on various sequences that our approach can capture the 3D motion of animals and humans accurately even in the case of rapid movements and wide apparel like skirts. 1.

I am very grateful to my advisor, Prof. Stan Sclaroff, for supporting me over the years, and for giving me so much freedom to discover my own research interests and to study diverse topics. Prof. Margrit Betke has always been a very detailed and thorough reviewer, and has kept me honest about all the details. Profess David Fleet has provided me invaluable suggestions on using precise words and improving the technical presentation of this thesis with his deep insight into the problem. I would like to express my gratitude to Dr. Ming-Hsuan Yang for hiring me as an intern at Honda Research Institute in 2005, where the early framework of this thesis was formulated. Dr. Fatih Porikli gave me the opportunity to work at Mitsubishi Electronics Research Lab during June to December 2008. I had a good break from my thesis research and worked on medical image analysis problems. I really appreciate his great advice and suggestions on how to start my professional career. Looking back, this journey would not be as enjoyable and fun without all the members from the image and video computing group. I would to like thank John Isidoro for being a great mentor and has tolerated many silly questions I had during his busiest time. Joni

Abstract. We propose a method to estimate the detailed 3D shape of a person from images of that person wearing clothing. The approach exploits a model of human body shapes that is learned from a database of over 2000 range scans. We show that the parameters of this shape model can be recovered independently of body pose. We further propose a generalization of the visual hull to account for the fact that observed silhouettes of clothed people do not provide a tight bound on the true 3D shape. With clothed subjects, different poses provide different constraints on the possible underlying 3D body shape. We consequently combine constraints across pose to more accurately estimate 3D body shape in the presence of occluding clothing. Finally we use the recovered 3D shape to estimate the gender of subjects and then employ genderspecific body models to refine our shape estimates. Results on a novel database of thousands of images of clothed and “naked ” subjects, as well as sequences from the HumanEva dataset, suggest the method may be accurate enough for biometric shape analysis in video. 1

Abstract not found

... generic structured prediction method that uses Gaussian process (GP) priors on both covariates and responses, both multivariate, and estimates outputs by minimizing the Kullback-Leibler divergence between two GP modeled as normal distributions over finite index sets of training and testing examples, emphasizing the goal that similar inputs should produce similar percepts and this should hold, on average, between their marginal distributions. TGP captures not only the interdependencies between covariates, as in a typical GP, but also those between responses, so correlations among both inputs and outputs are accounted for. TGP is exemplified, with promising results, for the reconstruction of 3d human poses from monocular and multicamera video sequences in the recently introduced HumanEva benchmark, where we achieve 5 cm error on average per 3d marker for models trained jointly, using data from multiple people and multiple activities. The method is fast and automatic: it requires no hand-crafting of the initial pose, camera calibration parameters, or the availability of a 3d body model associated with human subjects used for training or testing.

This paper addresses the problem of human motion tracking from multiple image sequences. The human body is described by five articulated mechanical chains and human body-parts are described by volumetric primitives with curved surfaces. If such a surface is observed with a camera, an extremal contour appears in the image whenever the surface turns smoothly away from the viewer. We describe a method that recovers human motion through a kinematic parameterization of these extremal contours. The method exploits the fact that the observed image motion of these contours is a function of both the rigid displacement of the surface and of the relative position and orientation between the viewer and the curved surface. First, we describe a parameterization of an extremal-contour point velocity for the case of developable surfaces. Second, we use the zeroreference kinematic representation and we derive an explicit formula that links extremal contour velocities to the angular velocities associated with the kinematic model. Third, we show how the chamfer-distance may be used to measure the discrepancy between predicted extremal contours and observed image contours; moreover we show how the chamfer distance can be used as a differentiable multi-valued function and how the tracker based on this distance can be cast into a continuous non-linear optimization framework. Fourth, we describe implementation issues associated with a practical human-body tracker that may use an arbitrary number of cameras. One great methodological and practical advantage of our method is that it relies neither on model-toimage, nor on image-to-image point matches. In practice we

We present a distributed representation of pose and appearance of people called the “poselet activation vector”. First we show that this representation can be used to estimate the pose of people defined by the 3D orientations of the head and torso in the challenging PASCAL VOC 2010 person detection dataset. Our method is robust to clutter, aspect and viewpoint variation and works even when body parts like faces and limbs are occluded or hard to localize. We combine this representation with other sources of information like interaction with objects and other people in the image and use it for action recognition. We report competitive results on the PASCAL VOC 2010 static image action classification challenge. 1.

Model-based 3D tracker estimate the position, rotation, and joint angles of a given model from video data of one or multiple cameras. They often rely on image features that are tracked over time but the accumulation of small errors results in a drift away from the target object. In this work, we address the drift problem for the challenging task of human motion capture and tracking in the presence of multiple moving objects where the error accumulation becomes even more problematic due to occlusions. To this end, we propose an analysis-by-synthesis framework for articulated models. It combines the complementary concepts of patchbased and region-based matching to track both structured and homogeneous body parts. The performance of our method is demonstrated for rigid bodies, body parts, and full human bodies where the sequences contain fast movements, self-occlusions, multiple moving objects, and clutter. We also provide a quantitative error analysis and comparison with other model-based approaches. 1.

Automatic recovery of 3D human pose from monocular image sequences is a challenging and important research topic with numerous applications. Although current methods are able to recover 3D pose for a single person in controlled environments, they are severely challenged by realworld scenarios, such as crowded street scenes. To address this problem, we propose a three-stage process building on a number of recent advances. The first stage obtains an initial estimate of the 2D articulation and viewpoint of the person from single frames. The second stage allows early data association across frames based on tracking-by-detection. These two stages successfully accumulate the available 2D image evidence into robust estimates of 2D limb positions over short image sequences ( = tracklets). The third and final stage uses those tracklet-based estimates as robust image observations to reliably recover 3D pose. We demonstrate state-of-the-art performance on the HumanEva II benchmark, and also show the applicability of our approach to articulated 3D tracking in realistic street conditions. 1.

We introduce a physics-based model for 3D person tracking. Based on a biomechanical characterization of lower-body dynamics, the model captures important physical properties of bipedal locomotion such as balance and ground contact. The model generalizes naturally to variations in style due to changes in speed, step-length, and mass, and avoids common problems (such as footskate) that arise with existing trackers. The dynamics comprise a two degreeof-freedom representation of human locomotion with inelastic ground contact. A stochastic controller generates impulsive forces during the toe-off stage of walking, and springlike forces between the legs. A higher-dimensional kinematic body model is conditioned on the underlying dynamics. The combined model is used to track walking people in video, including examples with turning, occlusion, and varying gait. We also report quantitative monocular and binocular tracking results with the HumanEva dataset.