Automated Extraction and Parameterization of Motions in Large Data Sets SIGGRAPH’ 2004 Lucas Kovar, Michael Gleicher University of Wisconsin-Madison.

Slides:



Advertisements
Similar presentations
Active Shape Models Suppose we have a statistical shape model –Trained from sets of examples How do we use it to interpret new images? Use an “Active Shape.
Advertisements

13-Optimization Assoc.Prof.Dr. Ahmet Zafer Şenalp Mechanical Engineering Department Gebze Technical.
Evaluating “find a path” reachability queries P. Bouros 1, T. Dalamagas 2, S.Skiadopoulos 3, T. Sellis 1,2 1 National Technical University of Athens 2.
Word Spotting DTW.
Approximations of points and polygonal chains
Text Scaffolds for Effective Surface Labeling Gregory Cipriano and Michael Gleicher.
By Lydia E. Kavraki, Petr Svestka, Jean-Claude Latombe, Mark H. Overmars Emre Dirican
Extended Gaussian Images
Verbs and Adverbs: Multidimensional Motion Interpolation Using Radial Basis Functions Presented by Sean Jellish Charles Rose Michael F. Cohen Bobby Bodenheimer.
Automatic Feature Extraction for Multi-view 3D Face Recognition
Automating Graph-Based Motion Synthesis Lucas Kovar Michael Gleicher University of Wisconsin-Madison.
Computing the Fréchet Distance Between Folded Polygons
Qualifying Exam: Contour Grouping Vida Movahedi Supervisor: James Elder Supervisory Committee: Minas Spetsakis, Jeff Edmonds York University Summer 2009.
1 Minimum Ratio Contours For Meshes Andrew Clements Hao Zhang gruvi graphics + usability + visualization.
Lapped Textures Emil Praun and Adam Finkelstien (Princeton University) Huges Hoppe (Microsoft Research) SIGGRAPH 2000 Presented by Anteneh.
Randomized Motion Planning for Car-like Robots with C-PRM Guang Song and Nancy M. Amato Department of Computer Science Texas A&M University College Station,
A New Block Based Motion Estimation with True Region Motion Field Jozef Huska & Peter Kulla EUROCON 2007 The International Conference on “Computer as a.
Introduction to Data-driven Animation Jinxiang Chai Computer Science and Engineering Texas A&M University.
Geometric reasoning about mechanical assembly By Randall H. Wilson and Jean-Claude Latombe Henrik Tidefelt.
Hierarchical Region-Based Segmentation by Ratio-Contour Jun Wang April 28, 2004 Course Project of CSCE 790.
Advanced Computer Graphics (Fall 2010) CS 283, Lecture 24: Motion Capture Ravi Ramamoorthi Most slides courtesy.
1Ellen L. Walker Recognizing Objects in Computer Images Ellen L. Walker Mathematical Sciences Dept Hiram College Hiram, OH 44234
Motion Planning for Camera Movements in Virtual Environments Authors: D. Nieuwenhuisen, M. Overmars Presenter: David Camarillo.
SST:an algorithm for finding near- exact sequence matches in time proportional to the logarithm of the database size Eldar Giladi Eldar Giladi Michael.
Image Manifolds : Learning-based Methods in Vision Alexei Efros, CMU, Spring 2007 © A.A. Efros With slides by Dave Thompson.
Motion Map: Image-based Retrieval and Segmentation of Motion Data EG SCA ’ 04 學生 : 林家如
1 Expression Cloning Jung-yong Noh Ulrich Neumann Siggraph01.
Dynamic Response for Motion Capture Animation Victor B. Zordan Anna Majkowska Bill Chiu Matthew Fast Riverside Graphics Lab University of California, Riverside.
Chapter 5: Path Planning Hadi Moradi. Motivation Need to choose a path for the end effector that avoids collisions and singularities Collisions are easy.
Multiple Object Class Detection with a Generative Model K. Mikolajczyk, B. Leibe and B. Schiele Carolina Galleguillos.
Introduction to Robot Motion Planning. Example A robot arm is to build an assembly from a set of parts. Tasks for the robot: Grasping: position gripper.
Scale-Invariant Feature Transform (SIFT) Jinxiang Chai.
Fast Subsequence Matching in Time-Series Databases Christos Faloutsos M. Ranganathan Yannis Manolopoulos Department of Computer Science and ISR University.
Domain decomposition in parallel computing Ashok Srinivasan Florida State University COT 5410 – Spring 2004.
BIONFORMATIC ALGORITHMS Ryan Tinsley Brandon Lile May 9th, 2014.
Efficient Algorithms for Robust Feature Matching Mount, Netanyahu and Le Moigne November 7, 2000 Presented by Doe-Wan Kim.
© Manfred Huber Autonomous Robots Robot Path Planning.
CS 551/651 Advanced Computer Graphics Warping and Morphing Spring 2002.
7.1. Mean Shift Segmentation Idea of mean shift:
ALIGNMENT OF 3D ARTICULATE SHAPES. Articulated registration Input: Two or more 3d point clouds (possibly with connectivity information) of an articulated.
Gapped BLAST and PSI- BLAST: a new generation of protein database search programs By Stephen F. Altschul, Thomas L. Madden, Alejandro A. Schäffer, Jinghui.
1 Efficient Search Ranking in Social Network ACM CIKM2007 Monique V. Vieira, Bruno M. Fonseca, Rodrigo Damazio, Paulo B. Golgher, Davi de Castro Reis,
Automated Construction of Parameterized Motions Lucas Kovar Michael Gleicher University of Wisconsin-Madison.
PMLAB Finding Similar Image Quickly Using Object Shapes Heng Tao Shen Dept. of Computer Science National University of Singapore Presented by Chin-Yi Tsai.
1 Interactive Thickness Visualization of Articular Cartilage Author :Matej Mlejnek, Anna Vilanova,Meister Eduard GröllerMatej MlejnekAnna VilanovaMeister.
Semantic Wordfication of Document Collections Presenter: Yingyu Wu.
Administration Feedback on assignment Late Policy
Flexible Spanners: A Proximity and Collision Detection Tool for Molecules and Other Deformable Objects Jie Gao, Leonidas Guibas, An Nguyen Computer Science.
Domain decomposition in parallel computing Ashok Srinivasan Florida State University.
Flexible Automatic Motion Blending with Registration Curves
Motion Graphs By Lucas Kovar, Michael Gleicher, and Frederic Pighin Presented by Phil Harton.
1 Microarray Clustering. 2 Outline Microarrays Hierarchical Clustering K-Means Clustering Corrupted Cliques Problem CAST Clustering Algorithm.
Planning Tracking Motions for an Intelligent Virtual Camera Tsai-Yen Li & Tzong-Hann Yu Presented by Chris Varma May 22, 2002.
Matching Geometric Models via Alignment Alignment is the most common paradigm for matching 3D models to either 2D or 3D data. The steps are: 1. hypothesize.
Project by: Qi-Xing & Samir Menon. Motion Planning for the Human Hand Generate Hand Skeleton Define Configuration Space Sample Configuration Space for.
3D Object Representations 2009, Fall. Introduction What is CG?  Imaging : Representing 2D images  Modeling : Representing 3D objects  Rendering : Constructing.
Response network emerging from simple perturbation Seung-Woo Son Complex System and Statistical Physics Lab., Dept. Physics, KAIST, Daejeon , Korea.
Jo˜ao Carreira, Abhishek Kar, Shubham Tulsiani and Jitendra Malik University of California, Berkeley CVPR2015 Virtual View Networks for Object Reconstruction.
Spectral Methods for Dimensionality
Week 9 Emily Hand UNR.
Morphing and Shape Processing
3D Object Representations
Date of download: 1/1/2018 Copyright © ASME. All rights reserved.
Outline Nonlinear Dimension Reduction Brief introduction Isomap LLE
RIO: Relational Indexing for Object Recognition
PRAKASH CHOCKALINGAM, NALIN PRADEEP, AND STAN BIRCHFIELD
Automated Layout and Phase Assignment for Dark Field PSM
Motion Graphs Davey Krill May 3, 2006.
Fragment Assembly 7/30/2019.
Initial Progress Report
Presentation transcript:

Automated Extraction and Parameterization of Motions in Large Data Sets SIGGRAPH’ 2004 Lucas Kovar, Michael Gleicher University of Wisconsin-Madison

CAIG/CS/NCTU2 Outline Introduction Searching for Motions Parameterizing Motion Results & Discussion

CAIG/CS/NCTU3 Introduction Goal Finding similar motion segments in a data set and using them to construct parameterized motions

CAIG/CS/NCTU4 Introduction (Cont.) How Searching “Similar” Motion Data Sets Multi-step search Using time correspondences to determine similarity Interactivity through precomputation(match web) Creating Parameterized Motions User-specified function F maps blend weights to motion parameters, actually we want F¯¹

CAIG/CS/NCTU5 Searching for Motions (Cont.) Determine similarity Corresponding frames should have similar skeleton poses Frame correspondences should be easy to identify Time alignment Monotonically increasing Continuous Non-degenerate

CAIG/CS/NCTU6 Searching for Motions (Cont.) Cell(i, j) : d(M1(ti), M2(tj))d(M1(ti), M2(tj)) Find the avg and compare against a user-specified threshold € 1D minima

CAIG/CS/NCTU7 Searching for Motions (Cont.) D(F 1, F 2 ) : distance between two frames of motion( Kovar SCA 2003)

CAIG/CS/NCTU8 Match Webs Looking for chains of 1D minima Remove chains below a threshold length Connecting chains as long as the connecting path is inside the valid region and has a length less than a threshold L Valid region: extend local minima

CAIG/CS/NCTU9

10 Searching With Match Webs Match sequence Remove whose avg cell value if greater than € and remove redundant

CAIG/CS/NCTU11 Searching With Match Webs Match graph Node: motion segments Edge: time alignment

CAIG/CS/NCTU12 Parameterizing Motion F: maps a set of blend weights w to a parameter vector p What we want: a set of parameters => blend weights that produce the corresponding motion Not guaranteed to be dense or uniform => generate blends to create additional samples

CAIG/CS/NCTU13 Parameterizing Motion (Cont.) Motion registration Sampling strategy Fast interpolation that preserves constraints

CAIG/CS/NCTU14 Registration Timewarp curve s(u) N e example motions => each point on s is an N e -dimensional vector Automatic determination may fail for more distant motions => identify the shortest path from Mq to every other motion in the match graph

CAIG/CS/NCTU15 Sampling Produce a dense sampling of parameter space to fill the gaps Compute the parameters of each example motion Compute a bounding box Randomly sample points in this region

CAIG/CS/NCTU16 Interpolation Given a new set of parameters, to find blend weights D(): distance between two parameters

CAIG/CS/NCTU17 Interpolation (Cont.) Parameters that are not attainable are projected onto the accessible region of parameter space

CAIG/CS/NCTU18 Results and Discussion Future works The development of alternatives to match webs that are more efficient Developing methods to ease the data requirements while preserving motion quality Construct more parameterized motion, ex: leaping motion