We estimate 2D human pose from video using only optical flow. The key insight is that dense optical flow can provide information about 2D body pose. Like range data, flow is largely invariant to appearance but unlike depth it can be directly computed from monocular video. We demonstrate that body parts can be detected from dense flow using the same random forest approach used by the Microsoft Kinect. Unlike range data, however, when people stop moving, there is no optical flow and they effectively disappear. To address this, our FlowCap method uses a Kalman filter to propagate body part positions and ve- locities over time and a regression method to predict 2D body pose from part centers. No range sensor is required and FlowCap estimates 2D human pose from monocular video sources containing human motion. Such sources include hand-held phone cameras and archival television video. We demonstrate 2D body pose estimation in a range of scenarios and show that the method works with real-time optical flow. The results suggest that optical flow shares invariances with range data that, when complemented with tracking, make it valuable for pose estimation.

The estimation of 3D human pose from 2D joint locations is central to many vision problems involving the analysis of people in images and video. To address the fact that the problem is inherently ill posed, many methods impose a prior over human poses. Unfortunately these priors admit invalid poses because they do not model how joint-limits vary with pose. Here we make two key contributions. First, we collected a motion capture dataset that explores a wide range of human poses. From this we learn a pose-dependent model of joint limits that forms our prior. The dataset and the prior will be made publicly available. Second, we define a general parameterization of body pose and a new, multistage, method to estimate 3D pose from 2D joint locations that uses an over-complete dictionary of human poses. Our method shows good generalization while avoiding impossible poses. We quantitatively compare our method with recent work and show state-of-the-art results on 2D to 3D pose estimation using the CMU mocap dataset. We also show superior results on manual annotations on real images and automatic part-based detections on the Leeds sports pose dataset.

Hand motion capture has been an active research topic in recent years, following the success of full-body pose tracking. Despite similarities, hand tracking proves to be more challenging, characterized by a higher dimensionality, severe occlusions and self-similarity between fingers. For this reason, most approaches rely on strong assumptions, like hands in isolation or expensive multi-camera systems, that limit the practical use. In this work, we propose a framework for hand tracking that can capture the motion of two interacting hands using only a single, inexpensive RGB-D camera. Our approach combines a generative model with collision detection and discriminatively learned salient points. We quantitatively evaluate our approach on 14 new sequences with challenging interactions.

Although action recognition in videos is widely studied, current methods often fail on real-world datasets. Many recent approaches improve accuracy and robustness to cope with challenging video sequences, but it is often unclear what affects the results most. This paper attempts to provide insights based on a systematic performance evaluation using thoroughly-annotated data of human actions. We annotate human Joints for the HMDB dataset (J-HMDB). This annotation can be used to derive ground truth optical flow and segmentation. We evaluate current methods using this dataset and systematically replace the output of various algorithms with ground truth. This enables us to discover what is important – for example, should we work on improving flow algorithms, estimating human bounding boxes, or enabling pose estimation? In summary, we find that highlevel pose features greatly outperform low/mid level features; in particular, pose over time is critical, but current pose estimation algorithms are not yet reliable enough to provide this information. We also find that the accuracy of a top-performing action recognition framework can be greatly increased by refining the underlying low/mid level features; this suggests it is important to improve optical flow and human detection algorithms. Our analysis and JHMDB dataset should facilitate a deeper understanding of action recognition algorithms.

We introduce Puppet Flow (PF), a layered model describing the optical flow of a person in a video sequence. We consider video frames composed by two layers: a foreground layer corresponding to a person, and background. We model the background as an affine flow field. The foreground layer, being a moving person, requires reasoning about the articulated nature of the human body. We thus represent the foreground layer with the Deformable Structures model (DS), a parametrized 2D part-based human body representation. We call the motion field defined through articulated motion and deformation of the DS model, a Puppet Flow. By exploiting the DS representation, Puppet Flow is a parametrized optical flow field, where parameters are the person's pose, gender and body shape.

We address the problem of upper-body human pose estimation in uncontrolled monocular video sequences, without manual initialization. Most current methods focus on isolated video frames and often fail to correctly localize arms and hands. Inferring pose over a video sequence is advantageous because poses of people in adjacent frames exhibit properties of smooth variation due to the nature of human and camera motion. To exploit this, previous methods have used prior knowledge about distinctive actions or generic temporal priors combined with static image likelihoods to track people in motion. Here we take a different approach based on a simple observation: Information about how a person moves from frame to frame is present in the optical flow field. We develop an approach for tracking articulated motions that "links" articulated shape models of people in adjacent frames trough the dense optical flow. Key to this approach is a 2D shape model of the body that we use to compute how the body moves over time. The resulting "flowing puppets" provide a way of integrating image evidence across frames to improve pose inference. We apply our method on a challenging dataset of TV video sequences and show state-of-the-art performance.

Benchmarking methods for 3d hand tracking is still an open problem due to the difficulty of acquiring ground truth data. We introduce a new dataset and benchmarking protocol that is insensitive to the accumulative error of other protocols. To this end, we create testing frame pairs of increasing difficulty and measure the pose estimation error separately for each of them. This approach gives new insights and allows to accurately study the performance of each feature or method without employing a full tracking pipeline. Following this protocol, we evaluate various directional distances in the context of silhouette-based 3d hand tracking, expressed as special cases of a generalized Chamfer distance form. An appropriate parameter setup is proposed for each of them, and a comparative study reveals the best performing method in this context.

We present a random forest-based framework for real time head pose estimation from depth images and extend it to localize a set of facial features in 3D. Our algorithm takes a voting approach, where each patch extracted from the depth image can directly cast a vote for the head pose or each of the facial features. Our system proves capable of handling large rotations, partial occlusions, and the noisy depth data acquired using commercial sensors. Moreover, the algorithm works on each frame independently and achieves real time performance without resorting to parallel computations on a GPU. We present extensive experiments on publicly available, challenging datasets and present a new annotated head pose database recorded using a Microsoft Kinect.

Pictorial Structures (PS) define a probabilistic model of 2D articulated objects in images. Typical PS models assume an object can be represented by a set of rigid parts connected with pairwise constraints that define the prior probability of part configurations. These models are widely used to represent non-rigid articulated objects such as humans and animals despite the fact that such objects have parts that deform non-rigidly. Here we define a new Deformable Structures (DS) model that is a natural extension of previous PS models and that captures the non-rigid shape deformation of the parts. Each part in a DS model is represented by a low-dimensional shape deformation space and pairwise potentials between parts capture how the shape varies with pose and the shape of neighboring parts. A key advantage of such a model is that it more accurately models object boundaries. This enables image likelihood models that are more discriminative than previous PS likelihoods. This likelihood is learned using training imagery annotated using a DS “puppet.” We focus on a human DS model learned from 2D projections of a realistic 3D human body model and use it to infer human poses in images using a form of non-parametric belief propagation.

We formulate the problem of 3D human pose estimation and tracking as one of inference in a graphical model. Unlike traditional kinematic tree representations, our model of the body is a collection of loosely-connected body-parts. In particular, we model the body using an undirected graphical model in which nodes correspond to parts and edges to kinematic, penetration, and temporal constraints imposed by the joints and the world. These constraints are encoded using pair-wise statistical distributions, that are learned from motion-capture training data. Human pose and motion estimation is formulated as inference in this graphical model and is solved using Particle Message Passing (PaMPas). PaMPas is a form of non-parametric belief propagation that uses a variation of particle filtering that can be applied over a general graphical model with loops. The loose-limbed model and decentralized graph structure allow us to incorporate information from "bottom-up" visual cues, such as limb and head detectors, into the inference process. These detectors enable automatic initialization and aid recovery from transient tracking failures. We illustrate the method by automatically tracking people in multi-view imagery using a set of calibrated cameras and present quantitative evaluation using the HumanEva dataset.

The 3D shape of the human body is useful for applications in fitness, games and apparel. Accurate body scanners, however, are expensive, limiting the availability of 3D body models. We present a method for human shape reconstruction from noisy monocular image and range data using a single inexpensive commodity sensor. The approach combines low-resolution image silhouettes with coarse range data to estimate a parametric model of the body. Accurate 3D shape estimates are obtained by combining multiple monocular views of a person moving in front of the sensor. To cope with varying body pose, we use a SCAPE body model which factors 3D body shape and pose variations. This enables the estimation of a single consistent shape while allowing pose to vary. Additionally, we describe a novel method to minimize the distance between the projected 3D body contour and the image silhouette that uses analytic derivatives of the objective function. We propose a simple method to estimate standard body measurements from the recovered SCAPE model and show that the accuracy of our method is competitive with commercial body scanning systems costing orders of magnitude more.

While research on articulated human motion and pose estimation has progressed rapidly in the last few years, there has been no systematic quantitative evaluation of competing methods to establish the current state of the art. We present data obtained using a hardware system that is able to capture synchronized video and ground-truth 3D motion. The resulting HumanEva datasets contain multiple subjects performing a set of predefined actions with a number of repetitions. On the order of 40,000 frames of synchronized motion capture and multi-view video (resulting in over one quarter million image frames in total) were collected at 60 Hz with an additional 37,000 time instants of pure motion capture data. A standard set of error measures is defined for evaluating both 2D and 3D pose estimation and tracking algorithms. We also describe a baseline algorithm for 3D articulated tracking that uses a relatively standard Bayesian framework with optimization in the form of Sequential Importance Resampling and Annealed Particle Filtering. In the context of this baseline algorithm we explore a variety of likelihood functions, prior models of human motion and the effects of algorithm parameters. Our experiments suggest that image observation models and motion priors play important roles in performance, and that in a multi-view laboratory environment, where initialization is available, Bayesian filtering tends to perform well. The datasets and the software are made available to the research community. This infrastructure will support the development of new articulated motion and pose estimation algorithms, will provide a baseline for the evaluation and comparison of new methods, and will help establish the current state of the art in human pose estimation and tracking.

Detection, tracking, segmentation and pose estimation of people in monocular images are widely studied. Two-dimensional models of the human body are extensively used, however, they are typically fairly crude, representing the body either as a rough outline or in terms of articulated geometric primitives. We describe a new 2D model of the human body contour that combines an underlying naked body with a low-dimensional clothing model. The naked body is represented as a Contour Person that can take on a wide variety of poses and body shapes. Clothing is represented as a deformation from the underlying body contour. This deformation is learned from training examples using principal component analysis to produce eigen clothing. We find that the statistics of clothing deformations are skewed and we model the a priori probability of these deformations using a Beta distribution. The resulting generative model captures realistic human forms in monocular images and is used to infer 2D body shape and pose under clothing. We also use the coefficients of the eigen clothing to recognize different categories of clothing on dressed people. The method is evaluated quantitatively on synthetic and real images and achieves better accuracy than previous methods for estimating body shape under clothing.

The detection and tracking of three-dimensional human body models has progressed rapidly but successful approaches typically rely on accurate foreground silhouettes obtained using background segmentation. There are many practical applications where such information is imprecise. Here we develop a new image likelihood function based on the visual appearance of the subject being tracked. We propose a robust, adaptive, appearance model based on the Wandering-Stable-Lost framework extended to the case of articulated body parts. The method models appearance using a mixture model that includes an adaptive template, frame-to-frame matching and an outlier process. We employ an annealed particle filtering algorithm for inference and take advantage of the 3D body model to predict self occlusion and improve pose estimation accuracy. Quantitative tracking results are presented for a walking sequence with a 180 degree turn, captured with four synchronized and calibrated cameras and containing significant appearance changes and self-occlusion in each view.

We propose a hierarchical process for inferring the 3D pose of a person from monocular images. First we infer a learned view-based 2D body model from a single image using non-parametric belief propagation. This approach integrates information from bottom-up body-part proposal processes and deals with self-occlusion to compute distributions over limb poses. Then, we exploit a learned Mixture of Experts model to infer a distribution of 3D poses conditioned on 2D poses. This approach is more general than recent work on inferring 3D pose directly from silhouettes since the 2D body model provides a richer representation that includes the 2D joint angles and the poses of limbs that may be unobserved in the silhouette. We demonstrate the method in a laboratory setting where we evaluate the accuracy of the 3D poses against ground truth data. We also estimate 3D body pose in a monocular image sequence. The resulting 3D estimates are sufficiently accurate to serve as proposals for the Bayesian inference of 3D human motion over time