WSCG’07 Jonathan Kipling Knight 1 Feb 2007 Copyright © Jonathan Kipling Knight 2007 Fast Skeleton Estimation from Motion Capture Data using Generalized.

Slides:



Advertisements
Similar presentations
Wednesday March 1st Dr. Moran
Advertisements

Lecture 5: Constraints I
Outline: Introduction Link Description Link-Connection Description
Rotational Motion Chapter Opener. Caption: You too can experience rapid rotation—if your stomach can take the high angular velocity and centripetal acceleration.
Links and Joints.
Manipulator’s Inverse kinematics
University of Bridgeport
Kinematic Modelling in Robotics
Animation Following “Advanced Animation and Rendering Techniques” (chapter 15+16) By Agata Przybyszewska.
3/5/2002Phillip Saltzman Video Motion Capture Christoph Bregler Jitendra Malik UC Berkley 1997.
1Notes  Handing assignment 0 back (at the front of the room)  Read the newsgroup!  Planning to put 16mm films on the web soon (possibly tomorrow)
1Notes  Assignment 0 marks should be ready by tonight (hand back in class on Monday)
Rational Trigonometry Applied to Robotics
Introduction to Robotics
Advanced Computer Graphics (Fall 2010) CS 283, Lecture 20: Inverse Kinematics Ravi Ramamoorthi Most slides courtesy.
COMP322/S2000/L221 Relationship between part, camera, and robot (cont’d) the inverse perspective transformation which is dependent on the focal length.
Chapter 10 Rotational Motion
Passive Object Tracking from Stereo Vision Michael H. Rosenthal May 1, 2000.
Kinematics. ILE5030 Computer Animation and Special Effects2 Kinematics The branch of mechanics concerned with the motions of objects without regard to.
Introduction to Robotics Lecture II Alfred Bruckstein Yaniv Altshuler.
Drawing a Skeleton Fast From Motion Capture Data Jonathan Kipling Knight Nov 7, 2006.
Mobile Robotics: 11. Kinematics 2
Week 4 Lecture 3: Character Animation Based on Interactive Computer Graphics (Angel) - Chapter 10 1 Angel: Interactive Computer Graphics 5E © Addison-Wesley.
The linear algebra of Canadarm
KINEMATICS ANALYSIS OF ROBOTS (Part 1) ENG4406 ROBOTICS AND MACHINE VISION PART 2 LECTURE 8.
More details and examples on robot arms and kinematics
Computer Animation Rick Parent Computer Animation Algorithms and Techniques Motion Capture.
Computer Animation Thesis “brief” Vic, CS 288, 10/22/98.
ME/ECE Professor N. J. Ferrier Forward Kinematics Professor Nicola Ferrier ME Room 2246,
Copyright © Ed2Net Learning Inc Warm Up 1. Rotations can occur in a__________ or _____________ direction. 2. Unit circle moves in a ___________direction.
Advanced Graphics (and Animation) Spring 2002
Inverse Kinematics Kris Hauser
Lecture 2: Introduction to Concepts in Robotics
Chapter 2 Robot Kinematics: Position Analysis
ROTATIONAL MOTION AND EQUILIBRIUM
Copyright © 2009 Pearson Education, Inc. Lecture 1 Rotational Motion.
Jinxiang Chai Composite Transformations and Forward Kinematics 0.
T. Bajd, M. Mihelj, J. Lenarčič, A. Stanovnik, M. Munih, Robotics, Springer, 2010 GEOMETRIC DESCRIPTION OF THE ROBOT MECHANISM T. Bajd and M. Mihelj.
Algirdas Beinaravičius Gediminas Mazrimas.  Introduction  Motion capture and motion data  Used techniques  Animating human body  Problems  Conclusion.
Vision-based human motion analysis: An overview Computer Vision and Image Understanding(2007)
Kinematics Jehee Lee Seoul National University. Kinematics How to animate skeletons (articulated figures) Kinematics is the study of motion without regard.
Tracking CSE 6367 – Computer Vision Vassilis Athitsos University of Texas at Arlington.
CS-378: Game Technology Lecture #13: Animation Prof. Okan Arikan University of Texas, Austin Thanks to James O’Brien, Steve Chenney, Zoran Popovic, Jessica.
Robot Kinematics: Position Analysis 2.1 INTRODUCTION  Forward Kinematics: to determine where the robot ’ s hand is? (If all joint variables are known)
CHAPTER 8 Geometry Slide 2Copyright 2012, 2008, 2004, 2000 Pearson Education, Inc. 8.1Basic Geometric Figures 8.2Perimeter 8.3Area 8.4Circles 8.5Volume.
Real-Time Simultaneous Localization and Mapping with a Single Camera (Mono SLAM) Young Ki Baik Computer Vision Lab. Seoul National University.
Kinematic Synthesis 2 October 8, 2015 Mark Plecnik.
1cs426-winter-2008 Notes  Will add references to splines on web page.
Just a quick reminder with another example
Chapter 2: Description of position and orientation Faculty of Engineering - Mechanical Engineering Department ROBOTICS Outline: Introduction. Descriptions:
Chapter 3 Differential Motions and Velocities
Forward Kinematics and Configurations
1cs426-winter-2008 Notes. 2 Kinematics  The study of how things move  Usually boils down to describing the motion of articulated rigid figures Things.
Forward Kinematics Where is my hand ?. Examples Denavit-Hartenberg Specialized description of articulated figures (joints) Each joint has only one degree.
Unit 2 Vocabulary. Line of Reflection- A line that is equidistant to each point corresponding point on the pre- image and image Rigid Motion- A transformation.
End effector End effector - the last coordinate system of figure Located in joint N. But usually, we want to specify it in base coordinates. 1.
COORDINATE SYSTEMS & TRANSFORMATION
What is a rigid transformation?  A transformation that does not change the size or shape of a figure.
Surface Area Total area on the surface of the figure, amount of paper needed to cover it.
Character Animation Forward and Inverse Kinematics
Journal of Vision. 2015;15(9):3. doi: / Figure Legend:
Computer Animation Algorithms and Techniques
CHAPTER 2 FORWARD KINEMATIC 1.
Hierarchical and Object-Oriented Graphics
Reflections & Rotations
DRILL If A is in between points B and C and AC is 4x + 12 and AB is 3x – 4 and BC is 57 feet how long is AB? Angles A and B are Supplementary if.
Hierarchical and Object-Oriented Graphics
Reflections in Coordinate Plane
Computer Graphics Lecture 15.
Day 47 – Fixed points and invertibility in rigid motion
Presentation transcript:

WSCG’07 Jonathan Kipling Knight 1 Feb 2007 Copyright © Jonathan Kipling Knight 2007 Fast Skeleton Estimation from Motion Capture Data using Generalized Delogne-Kåsa

1 Feb 2007JKK2 Synopsis Purpose Motion Capture Skeleton Formation Closed Form Solution Conclusion

1 Feb 2007JKK3 Purpose Draw an articulated framework of solid segments connected by joints. Fastest possible solution from motion capture data

1 Feb 2007JKK4 Motion Capture Magnetic Trackers Position and Orientation Marker Reflectors Position if in view Figure Tracking Computer vision and image analysis

1 Feb 2007JKK5 Motion Capture Session CMU 05-05

1 Feb 2007JKK6 Producing a Skeleton Single Time Frame Produce position, size and orientation of each segment Markers are fixed 3D positions on segment Orientation is included with magnetic trackers Draw lines between rotation points

1 Feb 2007JKK7 Time Slice

1 Feb 2007JKK8 Inverse Kinematics What joint angles are needed to get to next position and orientation? Good for filling in large frame gaps Sometimes more than one answer

1 Feb 2007JKK9 Inverse Kinematics Example CMU 05-05

1 Feb 2007JKK10 Closed Form Solution Find centers of rotation for each segment Each frame independently drawn No iterations Quick solution

1 Feb 2007JKK11 Segment Tree Root segment usually hips Leaf segments hands, head and feet No loops Root Leaves

1 Feb 2007JKK12 Solve Sphere at Each Joint One marker on child produces sphere around joint relative to parent Must know orientation of parent 1-3 markers needed or Magnetic trackers

1 Feb 2007JKK13 Three Point Orientation Three Orthogonal Axes

1 Feb 2007JKK14 Two Point Orientation Three Orthogonal Axes Substitute center of rotation

1 Feb 2007JKK15 One Point Orientation Three Orthogonal Axes Substitute center of rotation and constant axis

1 Feb 2007JKK16 Extra Information Center of Rotation is available from previously calculated segment Constant Axis is available for segments with near cylindrical motion.

1 Feb 2007JKK17 Center of Sphere Generalized Delogne-Kåsa Method for points on a hypersphere x i

1 Feb 2007JKK18 Constant Axis Test by condition number or determinant of C Null vector is axis of cylinder motion Center of circle

1 Feb 2007JKK19 GDK Properties Closed form solution for any dimension Fastest known 26N Cholesky inverse of 3x3 matrix Biased when partial coverage of sphere As accurate as data O(  )

1 Feb 2007JKK20 Marker Requirements 3 Markers on root segment of tree 1-3 Markers on all other segments Segments with 1 Marker should have one degree of freedom (e.g.knee,elbow)

1 Feb 2007JKK21 Break Dance CMU 85-14

1 Feb 2007JKK22 Salsa Dance CMU 60-08

1 Feb 2007JKK23 Conclusion GDK is fastest available sphere solution 26N As accurate as data O(  ) 1-3 Marker requirements per segment Provides skeleton to attach solid shape

1 Feb 2007JKK24 Future Research Unbiased version of GDK Full analysis of statistical nature Condition for acceptable data

1 Feb 2007JKK25 Acknowledgments The data used in this project was obtained from mocaps.cs.cmu.edu. The database was created with funding from NSF EIA