Hierarchical Implicit Surface Joint Limits to Constrain Video-Based Motion Capture

Herda, Lorna; Urtasun, Raquel; Fua, Pascal

doi:10.1007/978-3-540-24671-8_32

Cited by 22 publications

(15 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The intermediate and recurrent calculations are stored to reuse, avoiding unnecessary computation. Another important optimization adopted was the implementation of the local rotations r i using quaternions [38], which allow the speed up of rotations calculations, specially when t i is null.…”

Section: Algorithm 2 Calculation the Goal Joints Positionsmentioning

confidence: 99%

Kinematic-based Markerless Human Tracking in 3D Probabilistic Occupancy Grids

Goulart

Simas

et al. 2015

Journal of Communication and Information Systems

View full text Add to dashboard Cite

Abstract-Markerless human motion tracking can be employed in many applications such as automatic surveillance, motion capture, human-machine interface and activity recognition. This problem has been extensively studied in the computer vision research community in the last years. In this context, the present paper presents an approach for 3D markerless human motion tracking based on a skeletal kinematic model of the human body. This method is applied over a 3D probabilistic occupancy grid of the environment, which is constructed by means of a Bayesian fusion of images from multiple synchronized sensoring cameras. Although the use of kinematic models in 3D human tracking is widely employed, its use over 3D probabilistic occupancy grids still was not vastly investigated in the literature. The experiments were performed using a public dataset with video sequences of people in motion. The results show that the method is capable of dealing adequately with the 3D markerless human motion tracking problem.Index Terms-skeletal kinematic model, 3D probabilistic occupancy grid, 3D markerless human tracking.

show abstract

Section: Algorithm 2 Calculation the Goal Joints Positionsmentioning

confidence: 99%

Kinematic-based Markerless Human Tracking in 3D Probabilistic Occupancy Grids

Goulart

Simas

et al. 2015

Journal of Communication and Information Systems

View full text Add to dashboard Cite

show abstract

“…We proposed a formalism that incorporates the use of implicit surfaces into earlier robotics approaches that were designed to handle articulated structures [6] and impose hierarchical joint limits [3]. We have further increased its robustness by introducing temporal motion models based on Principal Component Analysis to formulate the tracking problem as one of minimizing differentiable objective functions [8].…”

Section: Motion Capture From Video Sequencesmentioning

confidence: 99%

Human Shape and Motion from Video

Fua¹

2004

Procedings of the British Machine Vision Conference 2004

View full text Add to dashboard Cite

In recent years, because cameras have become inexpensive and ever more prevalent, there has been increasing interest in modeling human shape and motion from image data. This type of modeling has many applications, such as electronic publishing, entertainment, sports medicine and athletic training. This, however, is an inherently difficult task, both because the body is very complex and because the data that can be extracted from images is often incomplete, noisy and ambiguous. EPFL's Computer Vision Laboratory seeks to overcome these difficulties by using facial and body animation models, not only to represent the data, but also to guide the fitting process, thereby substantially improving performance. Start from sophisticated 3-D animation models, we reformulate them so that they can be used for data analysis in the three following research areas. Augmented reality and 3-D trackingIn augmented reality applications, tracking and registration of cameras and objects are required because, to combine real and rendered scenes, we must project synthetic models at the right location in real images. As shown in Fig. 1, we have developed robust realtime methods for 3-D tracking of rigid objects and human faces [9,10]. We formulate the tracking problem in terms of local bundle adjustment and merge the information from preceding frames with that provided by a very limited number of keyframes created during a training stage, which results in a real-time tracker that does not jitter or drift and can deal with significant aspect changes. We have also developed the fast 3-D object detection and pose estimation method [4,5] which can be used to initialize or reinitialize the tracker in real-time. It relies on matching keypoints but, by contrast with previous methods that rely either on using ad hoc local descriptors or on estimating local affine deformations, the wide baseline matching of these keypoints is treated as a classification problem, in which each class corresponds to the set of all possible views of such a point. We synthesize a large number of views of individual keypoints of the object and train a classifier to recognize them. At run-time, we rely on this description to decide to which class, if any, an observed feature belongs. This formulation allows us to use powerful and fast classification methods to reduce matching error rates. Face modeling from uncalibrated video sequencesIn recent years, the movie industry has produced such realistic 3-D face models from images that we have come to take them for granted. However, a quick look at the credits BMVC 2004

show abstract

“…The motion of one body segment can be described as the motion of the previous segment in the kinematic chain and an angular motion about a joint axis. Rotation about joint axis can be represented by Euler angles, quaternions [9,10] or exponential coordinates [3,4,14], see [7] for a comparison of rotation parameterizations. Euler angles rep- (3), at the expense of using 4 numbers.…”

Section: Introductionmentioning

confidence: 99%

“…In [10] they use real data taken from optical markers to learn the field boundaries of a quaternion based ball-and-socket joint. In [9] a hierarchical model for joint limits (e.g. a manifold for possible joint shoulder and elbow configurations) is proposed to penalize body intersections during tracking.…”

Section: Introductionmentioning

confidence: 99%

Ball joints for Marker-less human Motion Capture

Moll

Rosenhahn

2009

2009 Workshop on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

This work presents an approach for the modeling and numerical optimization of ball joints within a Marker-less Motion Capture (MoCap) framework. In skeleton based approaches, kinematic chains are commonly used to model 1 DoF revolute joints. A 3 DoF joint (e.g. a shoulder or hip) is consequently modeled by concatenating three consecutive 1 DoF revolute joints. Obviously such a representation is not optimal and singularities can occur. Therefore, we propose to model 3 DoF joints with spherical joints or ball joints using the representation of a twist and its exponential mapping (known from 1 DoF revolute joints). The exact modeling and numerical optimization of ball joints requires additionally the adjoint transform and the logarithm of the exponential mapping. Experiments with simulated and real data demonstrate that ball joints can better represent arbitrary rotations than the concatenation of 3 revolute joints. Moreover, we demonstrate that the 3 revolute joints representation is very similar to the Euler angles representation and has the same limitations in terms of singularities.

show abstract

Hierarchical Implicit Surface Joint Limits to Constrain Video-Based Motion Capture

Cited by 22 publications

References 19 publications

Kinematic-based Markerless Human Tracking in 3D Probabilistic Occupancy Grids

Kinematic-based Markerless Human Tracking in 3D Probabilistic Occupancy Grids

Human Shape and Motion from Video

Ball joints for Marker-less human Motion Capture

Contact Info

Product

Resources

About