Filters








203 Hits in 3.3 sec

POSTURE INVARIANT CORRESPONDENCE OF INCOMPLETE TRIANGULAR MANIFOLDS

STEFANIE WUHRER, CHANG SHU, PROSENJIT BOSE, ZOUHOUR BEN AZOUZ
2007 International journal of shape modeling  
This results in posture-invariant shapes that can be registered using rigid correspondence algorithms.  ...  The approach requires no prior knowledge about the shapes being registered or the initial alignment of the shapes. We consider surfaces that are represented by possibly incomplete triangular meshes.  ...  Posture Invariant Correspondence of Incomplete Triangular Manifolds 3 5, 2007 16:14 WSPC/INSTRUCTION FILE correspondence˙ijsm Posture Invariant Correspondence of Incomplete Triangular Manifolds  ... 
doi:10.1142/s0218654307000981 fatcat:yl24cj743rfsrfxckoeaa22rku

Posture invariant correspondence of triangular meshes in shape space

Stefanie Wuhrer, Chang Shu, Prosenjit Bose
2009 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops  
We register possibly incomplete triangular meshes.  ...  We find dense point-to-point correspondences between two surfaces corresponding to different postures of the same articulated object in a fully automatic way.  ...  If shapes are deformed isometrically, then canonical forms are posture-invariant shapes that represent the intrinsic geometry of a manifold.  ... 
doi:10.1109/iccvw.2009.5457426 dblp:conf/iccvw/Wuhrer0B09 fatcat:jic4pn5nnfeexobopddic4yvve

Bending invariant meshes and application to groupwise correspondences

Stefanie Wuhrer, Chang Shu, Jonathan Boisvert, Guy Godin, Pengcheng Xi
2009 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops  
We introduce a new bending invariant representation of a triangular mesh S.  ...  We apply bending invariant meshes to find dense point-to-point correspondences between a number of deformed surfaces corresponding to different postures of the same non-rigid object in a fully automatic  ...  Figure 3 . 3 (a): Correspondence between ten poses of a cat model. (b): Histogram of ECOR. This paper introduces a new bending invariant representation of a possibly incomplete triangular mesh S.  ... 
doi:10.1109/iccvw.2009.5457674 dblp:conf/iccvw/Wuhrer0BGX09 fatcat:irjdxidck5dtxpjcqyktdodkxe

Posture-invariant statistical shape analysis using Laplace operator

Stefanie Wuhrer, Chang Shu, Pengcheng Xi
2012 Computers & graphics  
To overcome this problem, we propose an approach to perform statistical shape analysis in a posture-invariant way.  ...  Statistical shape analysis is a tool that allows to quantify the shape variability of a population of shapes.  ...  This work has partially been funded by the Cluster of Excellence Multimodal Computing and Interaction within the Excellence Initiative of the German Federal Government.  ... 
doi:10.1016/j.cag.2012.03.026 fatcat:ypoexbpat5hqvmtqz6zf4yzsdm

Human shape correspondence with automatically predicted landmarks

Stefanie Wuhrer, Pengcheng Xi, Chang Shu
2011 Machine Vision and Applications  
We consider the problem of computing accurate point-to-point correspondences among a set of human bodies in similar posture using a landmark-free approach.  ...  The approach learns the locations of the anthropometric landmarks present in a database of human models in similar postures and uses this knowledge to automatically predict the locations of these anthropometric  ...  The shapes of the human bodies are represented by possibly incomplete triangular meshes, which can be acquired by 3D sensing devices such as laser or structured-light body scanners.  ... 
doi:10.1007/s00138-011-0361-9 fatcat:bewbkoh6qfbivamt2tf3uybqju

Semi-Automatic Prediction of Landmarks on Human Models in Varying Poses

Stefanie Wuhrer, Zouhour Ben Azouz, Chang Shu
2010 2010 Canadian Conference on Computer and Robot Vision  
The information is modeled by a Markov network, where each node of the network corresponds to a landmark position and where each edge of the network represents the spatial relationship between a pair of  ...  Our method is based on learning bending-invariant landmark properties. We also learn the spatial relationships between pairs of landmarks using canonical forms.  ...  The canonical form is computed via multi-dimensional scaling with the geodesic distances between vertices on the triangular manifold as dissimilarities.  ... 
doi:10.1109/crv.2010.25 dblp:conf/crv/WuhrerAS10 fatcat:r3enrhmtv5cqdia2zhw3gyozje

Robust Arbitrary-View Gait Recognition Based on 3D Partial Similarity Matching

Jin Tang, Jian Luo, Tardi Tjahjadi, Fan Guo
2017 IEEE Transactions on Image Processing  
Existing view-invariant gait recognition methods encounter difficulties due to limited number of available gait views and varying conditions during training.  ...  The gait pose is estimated by a level set energy cost function from silhouettes including incomplete ones.  ...  [15] modelled 3-D body poses and camera viewpoints with a low dimensional manifold, and use it to learn a generative model of the silhouette for view invariant 3-D gait tracking.  ... 
doi:10.1109/tip.2016.2612823 pmid:28113179 fatcat:yz3wordmtradnis7ieqleksxs4

FARM: Functional Automatic Registration Method for 3D Human Bodies [article]

Riccardo Marin, Simone Melzi, Emanuele Rodolà, Umberto Castellani
2018 arXiv   pre-print
; further, the pipeline can be applied invariably across different shape representations (e.g. meshes and point clouds), and in the presence of (even dramatic) missing parts such as those arising in real-world  ...  We introduce a new method for non-rigid registration of 3D human shapes.  ...  E so as to form a mesh of triangular faces F.  ... 
arXiv:1807.10517v1 fatcat:jk3yvyg23radxmolpt27a66b54

Representation, Analysis, and Recognition of 3D Humans

Stefano Berretti, Mohamed Daoudi, Pavan Turaga, Anup Basu
2018 ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)  
Many of these applications are centered of detection, representation, and analysis of face and body.  ...  We summarize some of the most successful 3D descriptors, and outline how they have been used in the modeling of body and face.  ...  They proposed an original computational framework, called mesh-LBP that allows the extraction of LBP-like patterns directly from a triangular mesh manifold, without the need of any intermediate representation  ... 
doi:10.1145/3182179 fatcat:ds55t4md2na2tibtyg4llerf3q

Hand synergies: Integration of robotics and neuroscience for understanding the control of biological and artificial hands

Marco Santello, Matteo Bianchi, Marco Gabiccini, Emiliano Ricciardi, Gionata Salvietti, Domenico Prattichizzo, Marc Ernst, Alessandro Moscatelli, Henrik Jörntell, Astrid M.L. Kappers, Kostas Kyriakopoulos, Alin Albu-Schäffer (+2 others)
2016 Physics of Life Reviews  
We will review how such an organization can be observed at different levels -postural, muscular, and neural -and quantified through different techniques -motion tracking, electromyography (EMG), and brain  ...  The aims of this review are to provide an overview of the neuroscientific bases of hand synergies -meant as common patterns of actuation of the human hand -and to report how robotics has leveraged the  ...  All these factors usually determine an incomplete and imperfect relation between the measurements and the anatomical DOFs of the human hand.  ... 
doi:10.1016/j.plrev.2016.02.001 pmid:26923030 pmcid:PMC5839666 fatcat:uu6cf7mc6ngvfpivx3qlk2iyda

Graph-based Normalizing Flow for Human Motion Generation and Reconstruction [article]

Wenjie Yin, Hang Yin, Danica Kragic, Mårten Björkman
2021 arXiv   pre-print
We evaluate the models on a mixture of motion capture datasets of human locomotion with foot-step and bone-length analysis.  ...  When the inputs are imperfect, our model shows improvements on robustness of generation.  ...  The idea is to exploit the invariant spatial correlation of human skeletons and to enforce this inductive bias with a graph structure.  ... 
arXiv:2104.03020v1 fatcat:wr5p2zx3j5bkjcfbkvhb6t4n5a

Computational Models for Neuromuscular Function

F.J. Valero-Cuevas, H. Hoffmann, M.U. Kurse, J.J. Kutch, E.A. Theodorou
2009 IEEE Reviews in Biomedical Engineering  
Computational models of the neuromuscular system hold the potential to allow us to reach a deeper understanding of neuromuscular function and clinical rehabilitation by complementing experimentation.  ...  We conclude that these tools, when used in combination, have the potential to further our understanding of neuromuscular function by serving as a rigorous means to test scientific hypotheses in ways that  ...  To assemble input-output training patterns, we take as input the observed time series of the arm state (posture, velocity) and acceleration, and as output the corresponding torque time series.  ... 
doi:10.1109/rbme.2009.2034981 pmid:21687779 pmcid:PMC3116649 fatcat:jycxrx5janbgdirmu2hvh4ojdi

A FRAMEWORK FOR LEARNING AND CONTROL IN INTELLIGENT HUMANOID ROBOTS

OLIVER BROCK, ANDREW FAGG, RODERIC GRUPEN, ROBERT PLATT, MICHAEL ROSENSTEIN, JOHN SWEENEY
2005 International Journal of Humanoid Robotics  
Future application areas for humanoid robots range from the household, to agriculture, to the military, and to the exploration of space.  ...  Service applications such as these must address a changing, unstructured environment, a collaboration with human clients, and the integration of manual dexterity and mobility.  ...  We also thank Steve Hart and Deepak Karuppiah, current members of the LPR who are helping to carry on this discussion.  ... 
doi:10.1142/s0219843605000491 fatcat:quucpz6uazfznfcgrr6ywkjltm

Disentangled Human Body Embedding Based on Deep Hierarchical Neural Network [article]

Boyi Jiang, Juyong Zhang, Jianfei Cai, Jianmin Zheng
2020 IEEE Transactions on Visualization and Computer Graphics   accepted
the learning of the neural network.  ...  This is inspired by recent progress of deformation-based latent representation learning.  ...  and posture, respectively.  ... 
doi:10.1109/tvcg.2020.2988476 pmid:32324557 arXiv:1905.05622v2 fatcat:tmdgr54fnjdxlk2ukburvkivxy

Feedback control of a redundant wheeled snake mechanism using transverse functions SO(4)

P. Morin, C. Samson
2012 IFAC Proceedings Volumes  
From a theoretical point of view, these complementary d.o.f. modify the Control Lie Algebra of the system so that only first-order Lie brackets of the control vector fields are needed to satisfy the Lie  ...  This study is complemented with recalls concerning the parametrization of SO(4) by pairs of isoclinic quaternions and with the derivation of complementary differential calculus relations associated with  ...  Mogi (2000) , are few, incomplete and (to our point of view) mostly inconclusive due to the non-existence of adequate control design tools.  ... 
doi:10.3182/20120905-3-hr-2030.00020 fatcat:uu4nwihzfngevfqqhfwbogkudy
« Previous Showing results 1 — 15 out of 203 results