+ All Categories
Home > Technology > A computationally efficient method for sequential MAP-MRF cloud detection

A computationally efficient method for sequential MAP-MRF cloud detection

Date post: 05-Dec-2014
Category:
Upload: geographical-analysis-urban-modeling-spatial-statistics
View: 265 times
Download: 3 times
Share this document with a friend
Description:
A computationally efficient method for sequential MAP-MRF cloud detectionPaolo Addesso, Roberto Conte, Maurizio Longo, Rocco Restaino, Gemine Vivone- University of Salerno
22
A COMPUTATIONALLY EFFICIENT METHOD FOR SEQUENTIAL MAP-MRF CLOUD DETECTION Paolo Addesso , Roberto Conte, Maurizio Longo, Rocco Restaino and Gemine Vivone University of Salerno, D.I.E.I.I., Fisciano, Italy; e-mail {paddesso,rconte,longo,restaino,gvivone}@ unisa.it
Transcript
Page 1: A computationally efficient method for sequential MAP-MRF cloud detection

A COMPUTATIONALLY EFFICIENT METHOD FOR

SEQUENTIAL MAP-MRF CLOUD DETECTION

Paolo Addesso, Roberto Conte, Maurizio Longo,

Rocco Restaino and Gemine Vivone

University of Salerno, D.I.E.I.I., Fisciano, Italy;

e-mail {paddesso,rconte,longo,restaino,gvivone}@ unisa.it

Page 2: A computationally efficient method for sequential MAP-MRF cloud detection

OUTLINE

Introduction

Cloud detection

Penalty 3D Model

Cloud tracking

Region matching

Experimental results

Conclusions and future developments2

Page 3: A computationally efficient method for sequential MAP-MRF cloud detection

3

PROBLEM TACKLED

The classification consists in separating entities in a

given knowledge domain into knowledge classes.

Classification: cloud / clear sky

Sensor used: SEVIRI

Page 4: A computationally efficient method for sequential MAP-MRF cloud detection

WHY CLOUD DETECTION ?

4

The presence of clouds drastically affects

measures of optical signals

International Satellite Cloud Climatology Project

ISCCP-FD data set give a cloud cover around 66%

Many applications need a cloud masking phase

Example: fire detection, ocean color

Page 5: A computationally efficient method for sequential MAP-MRF cloud detection

STATE OF ART

Static thresholds

Methods based on spatial coherence

Markov Random Fields

Adaptive thresholds

A series of threshold tests depending on the variation

of the surface type and of the solar illumination

Machine learning tools

Fuzzy logic, artificial neural networks or kernel

methods5

Page 6: A computationally efficient method for sequential MAP-MRF cloud detection

OUTLINE

Introduction

Cloud detection

Penalty 3D Model

Cloud tracking

Region matching

Experimental results

Conclusions and future developments6

Page 7: A computationally efficient method for sequential MAP-MRF cloud detection

RANDOM FIELD AND MAP ESTIMATION

We define a random field F = {F1, … , Fm} as a

family of random variables defined on a set of

sites S in which each component Fi assumes a

value fi in the label set L

Estimator:

)}(log)|({logmaxarg

)(

)(logmaxarg

)|(maxargˆ|

fpfdp

dp

d,fp

dfpf

f

d

d,f

f

dff

MAP

7

Page 8: A computationally efficient method for sequential MAP-MRF cloud detection

MARKOV RANDOM FIELD (MRF)

F is a Markov Random Field if:Note: Ni is the neighbourhood of the pixel “i”.

)|()|( i}i{i iNS ffPffP

8

Page 9: A computationally efficient method for sequential MAP-MRF cloud detection

CLASSIFICATION WITH MRF

Given the Markovian hypothesis, the

Hammersley-Clifford theorem states that for the

a priori probability can be expressed as:

A similar likelihood form is commonly used:

Hence the a posteriori density is:

)]( exp[1

)( fUZ

fp

9

)]|(exp[)|( fdUfdp

)]()|(exp[)]|(exp[)|( fUfdUdfUdfp

Page 10: A computationally efficient method for sequential MAP-MRF cloud detection

MRF AND MAP CRITERIA

The minimum error probability is given by the

MAP estimator:

Under the hypothesis of conditional

independence among pixels, we have:

where Ni is the neighbourhood of the pixel “i”.10

)]|([ minarg)]|([ maxargˆ dfUdfpfff

Si NjSiSi

ffVfVfidU

fUfdUdfU

i

),( )( )|)((

)()|()|(

ji2i1i

Page 11: A computationally efficient method for sequential MAP-MRF cloud detection

ISING MODEL

The potential function defined on 4-neighbors1:

with

)(),( ji2ji2 ffffV

otherwise0

if1 )(

ji

ji

ffff

11

Page 12: A computationally efficient method for sequential MAP-MRF cloud detection

3D - PENALIZED ISING MODEL

Penalty function approach:

The potential function is defined as follows:

where is a penalty function and

12

)](1[)( )()](1[)( )(

i

)()(

i1

k

t

k

it

k fiλfiλfV

cloud"" 1 if0

sky"clear " 0 if1)(

)(

)(

)(

k

i

k

ik

if

ff

i

Page 13: A computationally efficient method for sequential MAP-MRF cloud detection

BOUNDING BOX PENALTY FUNCTION

EXAMPLE

13

Page 14: A computationally efficient method for sequential MAP-MRF cloud detection

OUTLINE

Introduction

Cloud detection

Penalty 3D Model

Cloud tracking

Region matching

Experimental results

Conclusions and future developments14

Page 15: A computationally efficient method for sequential MAP-MRF cloud detection

MULTI-TARGET TRACKING

Goal

Estimation of the features of an unknown number of

clouds

Typical issues

Multi-target involves at each temporal step the joint

estimation of the target number and the state vectors

The correct association between measures and

targets is needed (Data Association)15

Page 16: A computationally efficient method for sequential MAP-MRF cloud detection

TRACKING REGION MATCHING

16

X(k|k-1)

Z(k)

( x , y )

( x + dx , y + dy )

Page 17: A computationally efficient method for sequential MAP-MRF cloud detection

OUTLINE

Introduction

Cloud detection

Penalty 3D Model

Cloud tracking

Region matching

Experimental results

Conclusions and future developments17

Page 18: A computationally efficient method for sequential MAP-MRF cloud detection

GLOSSARY

Abbreviation Description

2DI 2D Ising

3DI 3D-Ising-like (also named Extended MRF)

3DP 3D-Penalized

18

Page 19: A computationally efficient method for sequential MAP-MRF cloud detection

PENALTY FUNCTIONS:SIMULATED DATA

19

Note

3DP has a lower Pe w.r.t. the 2DI and 3DI in all the test cases.

Abbreviation Pe Pfa 1-Pd

2DI 0.018 0.0012 0.16

3DI 0.038 0.0070 0.29

3DP 0.012 0.0026 0.094

Page 20: A computationally efficient method for sequential MAP-MRF cloud detection

BOUNDING BOX PENALTY FUNCTION: REAL IMAGES (SARDINIA ISLAND)

20

Note: Cloud pixel detected

by 3DP and not by 2DI (cyan),

by 3DP and not by 3DI (magenta)

by 3DP and by neither 2DI/ 3DI (red)

by 2DI and not by 3DP (blue),

by 3DI and not by 3DP (green)

Page 21: A computationally efficient method for sequential MAP-MRF cloud detection

OUTLINE

Introduction

Cloud detection

Penalty 3D Model

Cloud tracking

Region matching

Experimental results

Conclusions and future developments21

Page 22: A computationally efficient method for sequential MAP-MRF cloud detection

CONCLUSIONS

The use of the penalty function is advantageous to detect

cloud pixels (both inside cloud masses and on the edges)

22

FUTURE DEVELOPMENTS

A more detailed penalty map should be fruitful in the

presence of very rugged clouds

Include the multispectral analysis in the MAP-MRF

framework

Fusion of data collected by heterogeneous sensors


Recommended