Summary Novel Skeletal Representation for Articulated Creatures 1st edition by Gabriel Brostow, Irfan Essa, Drew Steedly, Vivek Kwatra ISBN - Digital Download

Novel Skeletal Representation for Articulated
Creatures 1st edition by Gabriel Brostow, Irfan
Essa, Drew Steedly, Vivek Kwatra ISBN 3540219828
9783540219828 pdf download
https://ebookball.com/product/novel-skeletal-representation-for-
articulated-creatures-1st-edition-by-gabriel-brostow-irfan-essa-
drew-steedly-vivek-kwatra-isbn-3540219828-9783540219828-10138/




Explore and download more ebooks or textbooks
at ebookball.com

, Get Your Digital Files Instantly: PDF, ePub, MOBI and More
Quick Digital Downloads: PDF, ePub, MOBI and Other Formats




Combining Geometric and View-Based Approaches for Articulated Pose
Estimation 1st edition by David Demirdjian ISBN 3540219828
9783540219828


https://ebookball.com/product/combining-geometric-and-view-based-
approaches-for-articulated-pose-estimation-1st-edition-by-david-
demirdjian-isbn-3540219828-9783540219828-11362/



Tracking Articulated Motion Using a Mixture of Autoregressive Models
1st edition by Ankur Agarwal, Bill Triggs ISBN 3540219828
9783540219828


https://ebookball.com/product/tracking-articulated-motion-using-
a-mixture-of-autoregressive-models-1st-edition-by-ankur-agarwal-
bill-triggs-isbn-3540219828-9783540219828-13696/



Intrinsic Images by Entropy Minimization 1st edition by Graham
Finlayson, Mark Drew, Cheng Lu ISBN 3540219828 9783540219828



https://ebookball.com/product/intrinsic-images-by-entropy-
minimization-1st-edition-by-graham-finlayson-mark-drew-cheng-lu-
isbn-3540219828-9783540219828-9776/



An Adaptive Window Approach for Image Smoothing and Structures
Preserving 1st edition by Charles Kervrann ISBN 3540219828
9783540219828


https://ebookball.com/product/an-adaptive-window-approach-for-
image-smoothing-and-structures-preserving-1st-edition-by-charles-
kervrann-isbn-3540219828-9783540219828-12036/

,Learning to Segment 1st edition by Eran Borenstein, Shimon Ullman ISBN
3540219828 9783540219828



https://ebookball.com/product/learning-to-segment-1st-edition-by-
eran-borenstein-shimon-ullman-
isbn-3540219828-9783540219828-10662/



An Information Based Measure for Grouping Quality 1st edition by Erik
Engbers, Michael Lindenbaum, Arnold Smeulders ISBN 3540219828
9783540219828


https://ebookball.com/product/an-information-based-measure-for-
grouping-quality-1st-edition-by-erik-engbers-michael-lindenbaum-
arnold-smeulders-isbn-3540219828-9783540219828-10624/



Bias in Shape Estimation 1st edition by Hui Ji, Cornelia Fermuller
ISBN 3540219828 9783540219828



https://ebookball.com/product/bias-in-shape-estimation-1st-
edition-by-hui-ji-cornelia-fermuller-
isbn-3540219828-9783540219828-9210/



Joint Bayes Filter A Hybrid Tracker for Non-rigid Hand Motion
Recognition 1st edition by Huang Fei, Ian Reid ISBN 3540219828
9783540219828


https://ebookball.com/product/joint-bayes-filter-a-hybrid-
tracker-for-non-rigid-hand-motion-recognition-1st-edition-by-
huang-fei-ian-reid-isbn-3540219828-9783540219828-9234/



Detection and Tracking Scheme for Line Scratch Removal in an Image
Sequence 1st edition by Bernard Besserer, Cedric Thire ISBN 3540219828
9783540219828


https://ebookball.com/product/detection-and-tracking-scheme-for-
line-scratch-removal-in-an-image-sequence-1st-edition-by-bernard-
besserer-cedric-thire-isbn-3540219828-9783540219828-13134/

, Novel Skeletal Representation
for Articulated Creatures

Gabriel J. Brostow, Irfan Essa, Drew Steedly, and Vivek Kwatra

Georgia Institute of Technology, Atlanta GA 30332, USA
http://www.cc.gatech.edu/cpl/projects/spines



Abstract. Volumetric structures are frequently used as shape descrip-
tors for 3D data. The capture of such data is being facilitated by devel-
opments in multi-view video and range scanning, extending to subjects
that are alive and moving. In this paper, we examine vision-based model-
ing and the related representation of moving articulated creatures using
spines. We define a spine as a branching axial structure representing
the shape and topology of a 3D object’s limbs, and capturing the limbs’
correspondence and motion over time.
Our spine concept builds on skeletal representations often used to de-
scribe the internal structure of an articulated object and the significant
protrusions. The algorithms for determining both 2D and 3D skeletons
generally use an objective function tuned to balance stability against the
responsiveness to detail. Our representation of a spine provides for en-
hancements over a 3D skeleton, afforded by temporal robustness and cor-
respondence. We also introduce a probabilistic framework that is needed
to compute the spine from a sequence of surface data.
We present a practical implementation that approximates the spine’s
joint probability function to reconstruct spines for synthetic and real
subjects that move.


1 Introduction

We are interested in the detection and tracking of features in volumetric images.
Volume images capture shape as a temporal sequence of boundary voxels or other
forms of 3D surfaces. Specifically, we wish to address situations where the subject
is known to have and is exercising an articulated structure. This assumption
grants us use of a specific class of geometric modeling solutions. The various
methods for skeletonizing 2D and 3D images share the objectives of identifying
extrema, features with some geometric significance, and capturing the spatial
relationships between them [9]. Skeletons, much like generalized cylinders [4,21],
serve the purpose of abstracting from raw volume or surface data to get higher
level structural information.
We propose that evaluating volumetric data of a subject over time can dis-
ambiguate real limbs from noisy protrusions. In a single image, knowledge of the
specific application alone would dictate the noise threshold to keep or cull small
branches of the skeleton. Many such algorithms exist. In the case of articulated

T. Pajdla and J. Matas (Eds.): ECCV 2004, LNCS 3023, pp. 66–78, 2004.


c Springer-Verlag Berlin Heidelberg 2004