"Person re-identification: a recent issue

"Person re
-
identification: a recent issue

for the
videosurveillance

community

and a technique for approaching it



Loris
Bazzani

Marco
Cristani

Modena,
17 maggio 2011

Before we start…

•
Download code and datasets for the exercises
(
iLIDS
,
VIPeR
, CAVIAR)
:


http://profs.scienze.univr.it/~bazzani/TMP/S4_SDALF_reid.zip

•
[opt.] Check out our CVPR 2010 paper:

http://www.lorisbazzani.info/papers/proceedings/FarenzenaetalCVPR10.pdf

•
[opt.] Check out the website:

http://www.lorisbazzani.info/code
-
datasets/sdalf
-
descriptor/

2

Outline of the lesson

1.
Person Re
-
identification
(few minutes…)


2.
A possible solution
:


SDALF, Symmetry
-
Driven Accumulation of
Local Features

(20 minutes…)


1.
Matlab

exercises

(~1 hour)

Person Re
-
identification

T = 1

T = 23

Different

overlapping

cameras

T = 222

T = 145

Same camera

•
Goal
:
Recognizing an
individual in
different
timings

Different

non overlapping

cameras

Person Re
-
identification

•
Issues
:

–
Many, you will see them in the exercises…

A possible solution: SDALF, Symmetry
-
Driven Accumulation of Local Features

•
Overview of the proposed descriptor:

STEP 2:
Chromatic
Feature

STEP 3:

Per
-
region
Feature

STEP 4:
Texture
Feature

STEP 0
-
1: Axes
of Symmetry
and Asymmetry

Descriptor

Accumulation

t

For each
body part

Step 0
–

Isolating the silhouette

•
We need to focus on the body of the person


•
We perform background
subtraction
or

•
We apply a statistical model of the
human appearance [
Jojic

et al.
2009]


Step 1
–

Axes of (A)
simmetry

•
We draw axes of
symmetry

and
asymmetry










•
Features near
the axes of
symmetry are
more reliable


Step 1
–

Axes of (A)
simmetry

BG subtraction using STEL generative model

Chromatic operator

Spatial covering operator

Step 2
-

Chromatic feature

•
For each part (no head), we compute a weighted color
histograms

•
HSV color space

•
“Gaussian Kernel” for each body part:







•
Low
-
weight to the background clutter

•
Robust to illumination changes, partial occlusions


Step 3
-

Per
-
region feature

•
Maximally Stable Color Region (MSCR)
detector

•
Detect “stable blobs”

•
Look at successive steps of an
agglomerative clustering of image
pixels

•
Covariant to affine transformations





Clustering of the detected blobs to
reduce the computational cost of the
matching


Step 4
-

Texture feature

•
Recurrent High
-
Structured Patches (RHSP) detector

Accumulation of features

•
Descriptor:

–
Single
-
shot: SDALF with only one image (no
accumulation)

–
Multi
-
shot: SDALF with multiple images


Testing the person re
-
identification

methods

A (probe)

B (gallery)

Pick a selection

Rank

Matching algorithm

•
Distance between two signatures

Bhattacharyya distance between HSV histograms

,

Distances between

blob descriptors

WHERE

How to evaluate

•
Cumulative Matching Characteristic (CMC)
curve
,

the
expectation of finding the correct
match in the top
n

matches


Ex. 1: The Datasets

•
Exercise 1
: take a look at the datasets and try
to find out the challenges of the re
-
id problem

17

For this, you can use the MATLAB file:

DEMO0_dataset.m

Ex. 2: SDALF

•
Exercise 2
: qualitative analysis of the SDALF
descriptor: display the weighted HSV hist.,
MSCR, RHSP


18

For this, you can use the MATLAB file:

DEMO1_SDALFextraction.m

Ex. 3: Cross
-
validation

•
Exercise 3
: try the cross
-
validation code
evaluating CMC, SRR and
nAUC

–
Compare
SvsS

and
MvsM

case

–

Vary the number of images for the
MvsM

case

19

For this, you can use the MATLAB file:

DEMO2_crossvalid.m

[set MAXCLUSTER=1 (
SvsS
) or >1 (
MvsM
)]


Ex 4: Matching

•
Exercise 4:
evaluate qualitatively the output of
the matching procedure

20

For this, you can use the MATLAB file:

DEMO2_crossvalid.m

[set
plotMatch
=1
]

And DEMO3_crossvalid.m


Take
-
home Message

•
Why this lesson?

–
To be able to use our system on new datasets

–
Compare your personal methods with SDALF

21

Questions?