Proposed Experiments on CMU Data


Experimental Question

The primary questions wish to address in this study are:


 
 

1.      Does our scale and parameter conversion method that maps between views perform appropriately on different data than upon which it was developed.

2.      Can we define static body parameter measurements performed during walking that our speed indpendent.

The mechanism to explore these questions will be the CMU “Mobo” database.

Available Data and CMU Experimental design

The CMU data consists of several views of subjects on a treadmill.  The data are labeled vrXX_YY for each of 3 conditions: slow walk, fast walk, and ball carrying walk.  The component XX refers to view number, and YY is subject number. In particular, view 03 is from side (person walking right to left), view 05 is from about 45 degrees, and view 07 is from straight ahead.

The CMU evaluation plan as posted on their web site is the following 22 tests (“experiments”):


 

Exp #

Train – Slow Walk

Test – Fast Walk

Test – Ball Walk

1,2

vr03

vr03

vr03

3,4

vr03

vr05

vr05

5,6

vr03

vr07

vr07

7,8

vr05

vr03

vr03

9,10

vr05

vr05

vr05

11,12

vr05

vr07

vr07

13,14

vr07

vr03

vr03

15,16

vr07

vr05

vr05

17,18

vr07

vr07

vr07

19,20

vr03 + vr07

vr03 + vr07

vr03 + vr07

21,22

vr03 + vr07

vr05

vr05

 

Our initial method of performing gait recognition uses static body measurements that are sensitive to stride length.  Therefore we should be able to go across views well, but poorly with different speeds.  Also, our feature extraction methods will not work on frontal views.  Thus any of the experiments that go between different speeds (all the odd tests) will be problematic for us.

Also, our paradigm of measuring a static body parameter feature vector does not require any specific “training” analogous to a set that helps define a model that is then applied to the gallery and the probes.  When performing matching across views we do use a small number of subjects to help relate the viewing conditions.  We will label them as “training” subjects..

\
To attempt to utilize the CMU data, we will first apply our algorithm to a subsets of  the experiments.  Those marked in bold will be first, with results by Sept 15, as they do not require new methods of feature extraction nor new methods of combining view information.  They do require our development of a speed compensation method as our current procedure uses stride length as a feature and biomechanics reveals that stride length changes with speed.

Expt #

Train – Slow Walk

Test – Fast Walk

Test - Ball

 

1,2

vr03

vr03

vr03

3,4

vr03

vr05

vr05

5,6

vr03

vr07

vr07

7,8

vr05

vr03

vr03

9,10

vr05

vr05

vr05

11,12

vr05

vr07

vr07

 

13,14

vr07

vr03

vr03

 

15,16

vr07

vr05

vr05

 

17,18

vr07

vr07

vr07

 

19,20

vr03 + vr07

vr03 + vr07

vr03 + vr07

 

21,22

vr03 + vr07

vr05

vr05

 

 

We will also perform tests on the same speed but different viewing angles:

Exp #

Train – Slow Walk

Test – Slow Walk

 

23

vr03

vr05

 

24

vr03

vr07

 

25

vr05

vr03

 

26

vr05

vr07

 

27

vr07

vr03

 

28

vr07

vr05

 

 

 

 

 

 

 

 

Exp #

Train – Fast Walk

Test – Fast Walk

29

vr03

vr05

30

vr03

vr07

31

vr05

vr03

32

vr05

vr07

 

33

vr07

vr03

 

34

vr07

vr05

 

 

Exp #

Train – Ball Walk

Test –Ball Walk

35

vr03

vr05

36

vr03

vr07

37

vr05

vr03

38

vr05

vr07

 

39

vr07

vr03

 

40

vr07

vr05

 

MAIN PAGE

 


Copyright © 1997-2001
 webmaster@cc.gatech.edu