79 Hits in 4.0 sec

Cardboard people: a parameterized model of articulated image motion

S.X. Ju, M.J. Black, Y. Yacoob
Proceedings of the Second International Conference on Automatic Face and Gesture Recognition  
The parameterized image motion of these patches is constrained to enforce articulated motion and is solved for directly using a robust estimation technique.  ...  We define a "cardboard person model" in which a person's limbs are represented by a set of connected planar patches.  ...  Conclusion We have presented a method for tracking articulated motion in an image sequence using parameterized models of optical flow.  ... 
doi:10.1109/afgr.1996.557241 dblp:conf/fgr/JuBY96 fatcat:q2t2gvdyg5hjrfhraqggg5z64a

Predicting 3D People from 2D Pictures [chapter]

Leonid Sigal, Michael J. Black
2006 Lecture Notes in Computer Science  
First we infer a learned view-based 2D body model from a single image using non-parametric belief propagation.  ...  We propose a hierarchical process for inferring the 3D pose of a person from monocular images.  ...  Summary and Conclusions The automatic estimation of human pose and motion in monocular image data remains a challenging problem.  ... 
doi:10.1007/11789239_19 fatcat:ilvj2swqffak3a3hyyxt3sqwla

Recognizing Human Motion Using Parameterized Models of Optical Flow [chapter]

Michael J. Black, Yaser Yacoob, Shanon X. Ju
1997 Computational Imaging and Vision  
These parameterized motion models can be extended to model the articulated motion of the human limbs 18 .  ...  Models of Image Motion Parameterized models of image motion make explicit assumptions about the spatial variation of the optical ow within a region.  ... 
doi:10.1007/978-94-015-8935-2_11 fatcat:v52kzqzzg5fufnkq6afucqtwke

Hand modeling, analysis and recognition

Ying Wu, T.S. Huang
2001 IEEE Signal Processing Magazine  
(a) Input image, (b) segmentation result, and (c) hand blob located by analyzing the segmented image pixels. Capturing articulate hand motion using a cardboard hand model.  ...  Some examples are shown in Fig. 4 , in which the parameters of a cardboard hand model are adjusted to match three input images.  ... 
doi:10.1109/79.924889 fatcat:ynpygvmztrgx3opq5nhpbfr5ry

Automatic acquisition and initialization of articulated models

N. Krahnstoever, M. Yeasin, R. Sharma
2003 Machine Vision and Applications  
Tracking, classification and visual analysis of articulated motion is challenging due to the difficulties involved in separating noise and variabilities caused by appearance, size and view point fluctuations  ...  By incorporating powerful domain knowledge, model based approaches are able to overcome these problem to a great extent and are actively explored by many researchers.  ...  Motion segmentation algorithms take two images as input and perform a segmentation into non-overlapping regions that move according to independent parameterized motion models.  ... 
doi:10.1007/s00138-002-0081-2 fatcat:fkwignl2jzgcdi2lg3rlhbprmm

Human Pose Estimation [chapter]

Leonid Sigal
2014 Computer Vision  
- Human pose tracking -People tracking -Articulated pose tracking -Body parsing -People parsing Definition Human pose estimation is the process of estimating the configuration of the body (pose) from  ...  Learning: Obtaining the large datasets that are required for learning discriminative models that can generalize across motions and imaging conditions is challenging.  ... 
doi:10.1007/978-0-387-31439-6_584 fatcat:qqlk2n72qzc5tnprxcmbuonhbi

Tracking self-occluding articulated objects in dense disparity maps

N. Jojic, M. Turk, T.S. Huang
1999 Proceedings of the Seventh IEEE International Conference on Computer Vision  
The model also enforces articulation constraints among the parts of the structure. The tracking problem is formulated as an inference problem in the image formation model.  ...  This graphical model (a Bayesian network) assumes that the range image of each part of the structure is formed by drawing the depth candidates from a 3-D Gaussian distribution.  ...  In Fig. 1 , an example of a disparity map D(X,Y) is given. Tracking Articulated Motion An articulated object's posture can be parameterized in many different ways.  ... 
doi:10.1109/iccv.1999.791207 dblp:conf/iccv/JojicTH99 fatcat:byebbaohvnfv5bvwtf42ncbnea

Estimation of composite object and camera image motion

Y. Yacoob, L. Davis
1999 Proceedings of the Seventh IEEE International Conference on Computer Vision  
The performance of the algorithm is demonstrated on several image sequences of rigid and articulated bodies in motion.  ...  The spatiotemporal ow models of the object motion are represented as a set of orthogonal ow bases that are learned using principal component analysis of instantaneous ow measurements from a stationary  ...  Our approach makes extensive use of 2D regionbased parameterized ow models which have been employed to recover rigid 3], deformable 4] and articulated 8, 12] object motions.  ... 
doi:10.1109/iccv.1999.791217 dblp:conf/iccv/YacoobD99 fatcat:oge5yryiyfbmflquzdjd6cmkri

Computational Studies of Human Motion: Part 1, Tracking and Motion Synthesis

David A. Forsyth, Okan Arikan, Leslie Ikemoto, James O'Brien, Deva Ramanan
2005 Foundations and Trends in Computer Graphics and Vision  
Ju et al. score D ρ(I n+1 (x + δx(θ)) − I n (x)) Figure from "Cardboard People: A Parameterized Model of Articulated Image Motion", Ju et al., IEEE Int. Conf.  ...  Similarly, Black et al construct parametric families of flow Fig. 1 . 5 15 Typical flows generated by the model Figure from " from Cardboard People: A Parameterized Model of Articulated Image Motion  ... 
doi:10.1561/0600000005 fatcat:nvtjhflo3rettfodhiuebtcyv4

Articulated Object Tracking via a Genetic Algorithm [chapter]

Jairo Rocha, Arnau Mir
2001 Lecture Notes in Computer Science  
Within a human motion analysis system, body parts are modeled by simple virtual 3D rigid objects.  ...  Several successful experiments are presented for an arm motion and a leg motion from two and three cameras.  ...  The Cardboard People system [JBY96] performs robust estimation of motion parameters for 2D regions.  ... 
doi:10.1007/3-540-44745-8_10 fatcat:cd6k37nhofhu3po7ny3fgjbot4

Learning Montages of Transformed Latent Images as Representations of Objects That Change in Appearance [chapter]

Chris Pal, Brendan J. Frey, Nebojsa Jojic
2002 Lecture Notes in Computer Science  
We show how the approach and model are able to find representations of the appearance of full body images of people in motion.  ...  In contrast, for our model, we learn the library of small latent images from a set of examples of objects that are changing in shape.  ...  In related work [3] , this model was extended to a cardboard person representation for articulated image motion such as human walking.  ... 
doi:10.1007/3-540-47979-1_48 fatcat:iwfo6wlc2jcrngh6mnpi4esrke

Articulated pose estimation with tiny synthetic videos

Dennis Park, Deva Ramanan
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
We use these synthetic images to generate a custom labeled training set for the video in question.  ...  We address the task of articulated pose estimation from video sequences. We consider an interactive setting where the initial pose is annotated in the first frame.  ...  Pose parameterization: We parameterize the appearance of a person as "cardboard puppet" model [15] .  ... 
doi:10.1109/cvprw.2015.7301337 dblp:conf/cvpr/ParkR15 fatcat:xafkmbkr55dr3ebzmn3xu6osxa

Character animation from 2D pictures and 3D motion data

Alexander Hornung, Ellen Dekkers, Leif Kobbelt
2007 ACM Transactions on Graphics  
Given a single image of a person or essentially human-like subject, our method transfers the motion of a 3D skeleton onto the subject's 2D shape in image space, generating the impression of a realistic  ...  We present robust solutions to reconstruct a projective camera model and a 3D model pose which matches best to the given 2D image.  ...  The painting of Napoleon (see Figure 1 ) is courtesy of WebMuseum at The motion data used in this project was obtained from  ... 
doi:10.1145/1189762.1189763 fatcat:atparq4h7jdo5lrmmt4qmdddje

Automatic Detection and Tracking of Human Motion with a View-Based Representation [chapter]

Ronan Fablet, Michael J. Black
2002 Lecture Notes in Computer Science  
This paper proposes a solution for the automatic detection and tracking of human motion in image sequences.  ...  To represent the optical flow patterns of people from arbitrary viewpoints, we develop a novel representation of human motion using low-dimensional spatio-temporal models that are learned using motion  ...  to train the generic motion model.  ... 
doi:10.1007/3-540-47969-4_32 fatcat:7s3lcsbdyjcnddth3i7rg5awre

Analyzing Human Movements from Silhouettes Using Manifold Learning

Liang Wang, David Suter
2006 2006 IEEE International Conference on Video and Signal Based Surveillance  
Further, we present two kinds of methods to analyze and recognize learned motion manifolds.  ...  One is correlation matching based on the Hausdorrf distance, and the other is a probabilistic method using continuous hidden Markov models (HMM).  ...  In the work of Yaccob and Black [8] , an action was represented by 40 curves derived from the tracking results of five body parts of a cardboard people model.  ... 
doi:10.1109/avss.2006.25 dblp:conf/avss/WangS06 fatcat:3gk3v35btzgqjlbi7vjpzppfzu
« Previous Showing results 1 — 15 out of 79 results