Segmentation of Human Motion into Dynamics Based Primitives with Application to Drawing Tasks D. Del Vecchio, R.M. Murray, P. Perona

1
Segmentation of Human Motion into Dynamics Based
Primitives with Application to Drawing TasksD.
Del Vecchio, R.M. Murray, P. Perona

• Alvina Goh
• Reading group 07/10/06

2
Motivation

• Develop a framework for the decomposition of
  human motion using tools from dynamical systems
  and systems identification.
• In the paper by Bregler and Malik,
• their approach does not include an input and
• therefore only applicable to periodic or
  stereotypical motions, like walking and running
  where the motion is always the same and movemes
  are repeatable segments of trajectory.

3
Aim of Paper

• Build an alphabet of movemes which one can
  compose to represent and describe human motion
  similar to phonemes used in speech.
• Segmentation and Classification
• Can a continuous trajectory of the human body be
  decomposed automatically into its component
  movemes?

4
Dynamical Definition of Moveme

• Basic definitions and properties

5
Dynamical Definition of Moveme

• Definition of a moveme

6
Dynamical Definition of Moveme

• Model used in paper

7
Dynamical Definition of Moveme
8
Construction of Set of Movemes
9
Classification Noiseless Case
10
Classification Noiseless Case
11
Classification Perturbed Case
12
Classification Perturbed Case
13
Segmentation
14
Segmentation
15
Segmentation Assumptions
16
Segmentation Assumptions
17
Segmentation Assumptions
18
Segmentation Solution
19
Segmentation Solution
20
Segmentation Solution
21
Main Theorem in Segmentation
22
Lemmas Used in Proof
23
Lemmas Used in Proof
24
Lemmas Used in Proof
25
Lemmas Used in Proof
26
Proposed Algorithm
27
Experimental Setup

• Subjects are shown 4 different prototypes car,
  sun, ship and house.
• Asked to reproduce them on a 700 x 500 canvas
  dimensions are chosen arbitrarily.
• Each drawing task is accomplished by performing a
  sequence of actions such as reach pt A, draw a
  line to pt B. These actions define elementary
  motions.
• Use Theorem 4.1 to find the sequence of reach and
  draw movements that the user did to accomplish
  the task and the switching times.
• The (x,y) position is sampled everywhere on the
  screen at the rate of 100Hz and a spatial
  resolution of 1 pixel

28
Experimental Setup

• Draws straight lines traced with a specific
  intention (like drawing a side of the house)
• Reaches happens with the intention of shifting
  fast the equilibrium position
• Both the first and second order dynamical systems
  are considered. The second order decoupled system
  is found to be the best fit.
• The circle class is also introduced since
  circular shapes like the wheels of the cars exist.

29
Experimental Results

• Classification error trajectory correctly
  segmented, wrongly classified
• Segmentation error trajectory over segmented or
  missed segmentation

30
Experimental Results
Finally to differentiate the different category
(car, house etc), a Gaussian classifier is built
based on the number of reach, draw and circles.
31
Discussion