Presentation is loading. Please wait.

Presentation is loading. Please wait.

Drawing a Skeleton Fast From Motion Capture Data Jonathan Kipling Knight Nov 7, 2006.

Similar presentations


Presentation on theme: "Drawing a Skeleton Fast From Motion Capture Data Jonathan Kipling Knight Nov 7, 2006."— Presentation transcript:

1 Drawing a Skeleton Fast From Motion Capture Data Jonathan Kipling Knight Nov 7, 2006

2 7 Nov 2006JKK2 Introduction Purpose Motion Capture Data Files Skeleton Formation Closed Form Solution Conclusion

3 7 Nov 2006JKK3 Purpose Draw an articulated framework of solid segments connected by joints. Use live data capture to draw figure.

4 7 Nov 2006JKK4 Motion Capture Magnetic Trackers Position and Orientation Transmitted Light Dots 3D Position if in view Figure Tracking Computer vision and image analysis

5 7 Nov 2006JKK5 Motion Capture Session 05_05

6 7 Nov 2006JKK6 Data Files No international standard Proprietary, semi-open formats C3D oldest from Dr. Andrew Dainis Bad Data Users partially fill fields Units incorrect Frame rate incorrect Signed/unsigned mismatches

7 7 Nov 2006JKK7 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 Rotation Points are fixed on TWO segments but are not in data

8 7 Nov 2006JKK8 Producing a Skeleton How to Move Between Frames Inverse Kinematics popular Forward and Inverse Kinetics Closed Form Solutions

9 7 Nov 2006JKK9 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

10 7 Nov 2006JKK10 Inverse Kinematics Example

11 7 Nov 2006JKK11 Closed Form Solution Requires 1-3 positions on each segment Each frame independently drawn Quickest O(26N) As accurate as data O(  /  N)

12 7 Nov 2006JKK12 Segment Tree Root segment usually hips Leaf segments hands, head and feet No loops Root Leaves

13 7 Nov 2006JKK13 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

14 7 Nov 2006JKK14 Three Point Orientation Three Orthogonal Axes

15 7 Nov 2006JKK15 Two Point Orientation Three Orthogonal Axes

16 7 Nov 2006JKK16 One Point Orientation Three Orthogonal Axes

17 7 Nov 2006JKK17 Center of Sphere Asymptotically Unbiased Generalized Delogne-Kåsa Method

18 7 Nov 2006JKK18 UGDK Asymptotically unbiased if measurement error estimate is correct Fastest known O(26N) Cholesky inverse of 3x3 matrix

19 7 Nov 2006JKK19 100 Point Comparison MLE GDKE UGDK

20 7 Nov 2006JKK20 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)

21 7 Nov 2006JKK21 Break Dance

22 7 Nov 2006JKK22 Salsa Dance

23 7 Nov 2006JKK23 Conclusion UGDK is fastest available sphere solution O(26N) Asymptotically unbiased answer As accurate as data O(  /  N) 1-3 Marker requirements per segment Provides skeleton to attach solid shape


Download ppt "Drawing a Skeleton Fast From Motion Capture Data Jonathan Kipling Knight Nov 7, 2006."

Similar presentations


Ads by Google