25
1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications Adviser : Chih-Hung Lin Speaker : Kuan-Ju Chen Date : 2009/04/06

1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

Embed Size (px)

Citation preview

Page 1: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

1

Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE

A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

Adviser : Chih-Hung Lin Speaker : Kuan-Ju ChenDate    : 2009/04/06

Page 2: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

2

AuthorLucia Maddalena

received the Laurea degree (cum laude) in mathematics and the Ph.D. degree in applied mathematics and computer science from the University of Naples Federico II, Naples, Italy.

Alfredo Petrosino (SM’02) is an Associate Professor of

computer science at the University of Naples Parthenope, Naples, Italy.

Page 3: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

3

OUTLINE

INTRODUCTION1

METHOD2

EXPERIMENTAL RESULTS3

CONCLUSION4

Page 4: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

4

1.INTRODUCTION

VISUAL surveillance is a very active research area in computer vision

The main tasks in visual surveillance systems motion detection object classification Tracking activity understanding semantic description

Page 5: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

5

1.INTRODUCTIONThe usual approach to moving object

detection is through background subtraction

Compared to other approaches, The main problem is its sensitivity to dynamic scene changes light changes moving background cast shadows

Page 6: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

6

1.INTRODUCTIONBackground subtraction:

Unimodal versus multimodal: Recursive: Pixel-based :

Page 7: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

7

1.INTRODUCTIONUnimodal and multimodal:

Basic background models assume that the intensity values of a pixel can be modeled

• low complexity• cannot handle moving backgrounds

Page 8: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

8

1.INTRODUCTIONRecursive

recursively update a single background model based on each input frame.

• Space complexity is lower• Background model is carried out for a long time

period

Page 9: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

9

1.INTRODUCTIONPixel-based :

assume that the time series of observations is independent at each pixel

Page 10: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

10

1.INTRODUCTIONOur approach is based on the

background model automatically generated by a self-organizing method and can be broadly classified as multimodal,

recursive, and pixelbased.

Page 11: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

11

2.METHOD

Initial Background Model1

Subtraction and Update of the Background Model2

Page 12: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

12

2.1 Initial Background Model

a b c

d e f

a1 a2 a3

a4 a5 a6

a7 a8 a9

b1 b2 b3

b4 b5 b6

b7 b8 b9

c1 c2 c3

c4 c5 c6

c7 c8 c9

d1 d2 d3

d4 d5 d6

d7 d8 d9

e1 e2 e3

e4 e5 e6

e7 e8 e9

f1 f2 f3

f4 f5 f6

f7 f8 f9

Let be HSV components , ex: a1=(h,s,v)

Page 13: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

13

2.2 Subtraction of the Background Model

Input pixel tp

Build pixel model C(2.1)

Find best Match Cm

Cm is found

B(Pt)=0

NO

Pt is shadow

YES

B(Pt)=1

YES

NO

LastFrameNot LastFrame

Current Frame+1

Over

LastFrame

Self-Organizing Background Subtraction

Update Background

Model

Page 14: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

14

2.2 Subtraction of the Background Model

Use Euclidean distance to computeCn and Cother pixel distance

),(min),(

sinsincoscos),(

2,,1

222

tini

tm

jijjjiiijjjiiiji

pcdpcd

vvhsvhsvhsvhsvppd

Page 15: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

15

2.2 Subtraction of the Background Model

Page 16: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

16

2.2 Update of the Background Model

If best match cm Weight vector At to update in the

neighborhood cm

If best match cm isn`t found Not update

Page 17: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

17

2.2 Update of the Background Model

a b c

d e f

a1 a2 a3

a4 a5 a6

a7 a8 a9

b1 b2 b3

b4 b5 b6

b7 b8 b9

c1 c2 c3

c4 c5 c6

c7 c8 c9

d1 d2 d3

d4 d5 d6

d7 d8 d9

e1 e2 e3

e4 e5 e6

e7 e8 e9

f1 f2 f3

f4 f5 f6

f7 f8 f9If best match cm

Computer the weight vector to update background

Page 18: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

18

2.2 Update of the Background Model

a1 a2 a3

a4 a5 a6

a7 a8 a9

b1 b2 b3

b4 b5 b6

b7 b8 b9

c1 c2 c3

c4 c5 c6

c7 c8 c9

d1 d2 d3

d4 d5 d6

d7 d8 d9

e1 e2 e3

e4 e5 e6

e7 e8 e9

f1 f2 f3

f4 f5 f6

f7 f8 f9

),(),())(1(),( ,1, yxpjiAtjiA tjitjit

Page 19: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

19

SHADOW DETECTION

Foreground

Ayalyze Hue-Saturation-Value(HSV) color space

shadow mask:

otherwise 0

) ( )( )( 1SP s H

Hi

Ht

Si

StV

i

Vt

t cpcpc

pif

p

define a darkening effect of shadowsidentifying as shadows those points

average image luminance

Following three condition to mask shadow

Page 20: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

20

3.EXPERIMENTAL RESULTS

(a) original frame;(b) computed moving object detection mask(c) background model(d) background model change mask from previous frame

Page 21: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

21

3.EXPERIMENTAL RESULTS

(a) original frame;(b) computed moving object detection mask

Page 22: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

22

3.EXPERIMENTAL RESULTS

fpfntp

tp

F

fptp

tp

fntp

tp

Similarity

PrecisionRecall

PrecisionRecall2

Precision

Recall

1

Page 23: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

23

3.EXPERIMENTAL RESULTS

(a) test image (b) ground truth(c) SOBS result (d) Pfinder result(e) VSAM result (f) CB result

Page 24: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

24

4.CONCLUSIONThis paper also includes a

comprehensive accuracy testing, performed with both pixel-based and frame-based metrics Experimental results, using different sets of

data and comparing different methods, have demonstrated the effectiveness of the proposed approach

• illumination changes• cast shadows

ONGOING WORK improve detection results

Page 25: 1 Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications

25

www.themegallery.com