Model-based 3D tracking of an articulated hand

Stenger, Björn; Mendonça, Paulo R. S.; Cipolla, Roberto

doi:10.1109/cvpr.2001.990976

Cited by 191 publications

(133 citation statements)

References 21 publications

(20 reference statements)

Supporting

Mentioning

130

Contrasting

Unclassified

Order By: Relevance

“…The channels are combined using Bayesian framework that reduces to a sum of squared differences equation. Stenger et al [94] presented a model-based hand tracking system that used quadrics to build the underlying 3D model from which contours (handling occlusion) were generated that could be compared to edges in the image. Tracking is then done using an Unscented Kalman Filter.…”

Section: Finger Spellingmentioning

confidence: 99%

Sign Language Recognition

Cooper

Holt

Bowden

2011

Visual Analysis of Humans

181

View full text Add to dashboard Cite

This chapter covers the key aspects of Sign Language Recognition (SLR), starting with a brief introduction to the motivations and requirements, followed by a précis of sign linguistics and their impact on the field. The types of data available and the relative merits are explored allowing examination of the features which can be extracted. Classifying the manual aspects of sign (similar to gestures) is then discussed from a tracking and non-tracking viewpoint before summarising some of the approaches to the non-manual aspects of sign languages. Methods for combining the sign classification results into full SLR are given showing the progression towards speech recognition techniques and the further adaptations required for the sign specific case. Finally the current frontiers are discussed and the recent research presented. This covers the task of continuous sign recognition, the work towards true signer independence, how to effectively combine the different modalities of sign, making use of the current linguistic research and adapting to larger more noisy data sets.

show abstract

Section: Finger Spellingmentioning

confidence: 99%

Sign Language Recognition

Cooper

Holt

Bowden

2011

Visual Analysis of Humans

181

View full text Add to dashboard Cite

show abstract

“…3), which is widely used in vision-based hand motion captures [19,5]. The joints in this model are either pivot or Cardan joints.…”

Section: Structurementioning

confidence: 99%

“…Our method belongs to the latter class, and uses data extracted from stereoscopic image sequences, namely trajectories of 3D points, to extract the parameters of a 27 DOF hand model. Other tracking methods may use template images of each phalanx [16], or a combination of optical flow [11,13], contours or silhouette [11,13,20,6,21,9,19], and depth [6]. A few methods are first trying to reduce the number of DOF of the hand model by analyzing a database of digitized motions [21,9,19], with the risk of losing generality in the set of possible hand poses.…”

Section: Introductionmentioning

confidence: 99%

“…Other tracking methods may use template images of each phalanx [16], or a combination of optical flow [11,13], contours or silhouette [11,13,20,6,21,9,19], and depth [6]. A few methods are first trying to reduce the number of DOF of the hand model by analyzing a database of digitized motions [21,9,19], with the risk of losing generality in the set of possible hand poses. In this context multiple cameras were previously used either to recover depth and use it in the tracking process [6], or to recognize the pose in the best view, and then use other images to get a better estimation of the 3D pose [20].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hand Motion from 3D Point Trajectories and a Smooth Surface Model

Dewaele¹,

Devernay²,

Horaud³

2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract.A method is proposed to track the full hand motion from 3D points reconstructed using a stereoscopic set of cameras. This approach combines the advantages of methods that use 2D motion (e.g. optical flow), and those that use a 3D reconstruction at each time frame to capture the hand motion. Matching either contours or a 3D reconstruction against a 3D hand model is usually very difficult due to self-occlusions and the locally-cylindrical structure of each phalanx in the model, but our use of 3D point trajectories constrains the motion and overcomes these problems. Our tracking procedure uses both the 3D point matches between two time frames and a smooth surface model of the hand, build with implicit surface. We used animation techniques to represent faithfully the skin motion, especially near joints. Robustness is obtained by using an EM version of the ICP algorithm for matching points between consecutive frames, and the tracked points are then registered to the surface of the hand model. Results are presented on a stereoscopic sequence of a moving hand, and are evaluated using a side view of the sequence.

show abstract

“…Body pose can be calculated at several scales and granularities including full body [14,18], head [13] and hand pose [3,4,10,12,19]. Recovering the articulation of a human hand can be proven very useful in a number of application domains including but not limited to advanced HCI/HRI, games, AR applications, sign language understanding, etc.…”

Section: Introductionmentioning

confidence: 99%

Dimensionality Reduction for Efficient Single Frame Hand Pose Estimation

Douvantzis

Oikonomidis

Kyriazis

et al. 2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Model based approaches for the recovery of the 3D position, orientation and full articulation of the human hand have a number of attractive properties. One bottleneck towards their practical exploitation is their computational cost. To a large extent, this is determined by the large dimensionality of the problem to be solved. In this work we exploit the fact that the parametric joints space representing hand configurations is highly redundant. Thus, we employ Principal Component Analysis (PCA) to learn a lower dimensional space that describes compactly and effectively the human hand articulation. The reduced dimensionality of the resulting space leads to a simpler optimization problem, so model-based approaches require less computational effort to solve it. Experiments demonstrate that the proposed approach achieves better accuracy in hand pose recovery compared to a state of the art baseline method using only 1/4 of the latter's computational budget.

show abstract

Model-based 3D tracking of an articulated hand

Abstract: Abstract

Cited by 191 publications

References 21 publications

Sign Language Recognition

Sign Language Recognition

Hand Motion from 3D Point Trajectories and a Smooth Surface Model

Dimensionality Reduction for Efficient Single Frame Hand Pose Estimation

Contact Info

Product

Resources

About