Search For:

Displaying 1-12 out of 12 total
Body Parts Dependent Joint Regressors for Human Pose Estimation in Still Images
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Matthias Dantone,Juergen Gall,Christian Leistner,Luc Van Gool
Issue Date:November 2014
pp. 1-1
In this work, we address the problem of estimating 2d human pose from still images. Articulated body pose estimation is challenging due to the large variation in body poses and appearances of the different body parts. Recent methods that rely on the pictor...
 
Outdoor human motion capture using inverse kinematics and von mises-fisher sampling
Found in: Computer Vision, IEEE International Conference on
By Gerard Pons-Moll,Andreas Baak,Juergen Gall,Laura Leal-Taixe,Meinard Muller,Hans-Peter Seidel,Bodo Rosenhahn
Issue Date:November 2011
pp. 1243-1250
Human motion capturing (HMC) from multiview image sequences is an extremely difficult problem due to depth and orientation ambiguities and the high dimensionality of the state space. In this paper, we introduce a novel hybrid HMC system that combines video...
 
Fast articulated motion tracking using a sums of Gaussians body model
Found in: Computer Vision, IEEE International Conference on
By Carsten Stoll,Nils Hasler,Juergen Gall,Hans-Peter Seidel,Christian Theobalt
Issue Date:November 2011
pp. 951-958
We present an approach for modeling the human body by Sums of spatial Gaussians (SoG), allowing us to perform fast and high-quality markerless motion capture from multi-view video sequences. The SoG model is equipped with a color model to represent the sha...
 
Hough Forests for Object Detection, Tracking, and Action Recognition
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Juergen Gall,Angela Yao,Nima Razavi,Luc Van Gool,Victor Lempitsky
Issue Date:November 2011
pp. 2188-2202
The paper introduces Hough forests, which are random forests adapted to perform a generalized Hough transform in an efficient way. Compared to previous Hough-based systems such as implicit shape models, Hough forests improve the performance of the generali...
 
A Hough transform-based voting framework for action recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Angela Yao, Juergen Gall, Luc Van Gool
Issue Date:June 2010
pp. 2061-2068
We present a method to classify and localize human actions in video using a Hough transform voting framework. Random trees are trained to learn a mapping between densely-sampled feature patches and their corresponding votes in a spatio-temporal-action Houg...
 
An object-dependent hand pose prior from sparse training data
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Henning Hamer, Juergen Gall, Thibaut Weise, Luc Van Gool
Issue Date:June 2010
pp. 671-678
In this paper, we propose a prior for hand pose estimation that integrates the direct relation between a manipulating hand and a 3d object. This is of particular interest for a variety of applications since many tasks performed by humans require hand-objec...
 
Combined Region and Motion-Based 3D Tracking of Rigid and Articulated Objects
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Thomas Brox, Bodo Rosenhahn, Juergen Gall, Daniel Cremers
Issue Date:March 2010
pp. 402-415
In this paper, we propose the combined use of complementary concepts for 3D tracking: region fitting on one side and dense optical flow as well as tracked SIFT features on the other. Both concepts are chosen such that they can compensate for the shortcomin...
 
Drift-free tracking of rigid and articulated objects
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Juergen Gall, Bodo Rosenhahn, Hans-Peter Seidel
Issue Date:June 2008
pp. 1-8
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 ...
 
Video-based reconstruction of animatable human characters
Found in: ACM Transactions on Graphics (TOG)
By Carsten Stoll, Christian Theobalt, Edilson de Aguiar, Juergen Gall, Sebastian Thrun, Carsten Stoll, Christian Theobalt, Edilson de Aguiar, Juergen Gall, Sebastian Thrun
Issue Date:December 2010
pp. 1-12
We present a new performance capture approach that incorporates a physically-based cloth model to reconstruct a rigged fully-animatable virtual double of a real person in loose apparel from multi-view video recordings. Our algorithm only requires a minimum...
     
Towards Understanding Action Recognition
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Hueihan Jhuang,Juergen Gall,Silvia Zuffi,Cordelia Schmid,Michael J. Black
Issue Date:December 2013
pp. 3192-3199
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 mo...
 
Human Pose Estimation Using Body Parts Dependent Joint Regressors
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Matthias Dantone,Juergen Gall,Christian Leistner,Luc Van Gool
Issue Date:June 2013
pp. 3041-3048
In this work, we address the problem of estimating 2d human pose from still images. Recent methods that rely on discriminatively trained deformable parts organized in a tree model have shown to be very successful in solving this task. Within such a pictori...
 
Video-based reconstruction of animatable human characters
Found in: ACM SIGGRAPH Asia 2010 papers (SIGGRAPH ASIA '10)
By Carsten Stoll, Christian Theobalt, Edilson de Aguiar, Juergen Gall, Sebastian Thrun
Issue Date:December 2010
pp. 20-21
We present a new performance capture approach that incorporates a physically-based cloth model to reconstruct a rigged fully-animatable virtual double of a real person in loose apparel from multi-view video recordings. Our algorithm only requires a minimum...
     
 1