19
www.nr.no earthobs.nr.no Retraining maximum likelihood classifiers using a low-rank model Arnt-Børre Salberg Norwegian Computing Center Oslo, Norway IGARSS July 25, 2011

Retraining maximum likelihood classifiers using low-rank model.ppt

Embed Size (px)

Citation preview

Page 1: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Retraining maximum likelihood classifiers using a low-rank model

Arnt-Børre Salberg

Norwegian Computing Center

Oslo, Norway

IGARSS July 25, 2011

Page 2: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Introduction► Challenge: Dataset shift problem:

▪ Training data match the test data poorly due to atmospherical, geographical, botanical and phenological variations in the image data→ reduced classification performance

▪ Class-dependent data distribution varies ◦ between training images◦ between test and training images

► Goal: Develop a method that re-estimates the parameters such that classifier possess a good fit to the test data

Page 3: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Introduction

► Many surface reflectance algorithms often requires data from external sources▪ LEDAPS (Landsat):

◦ ozone and water vapor measurements

► Phenological, botanical and geographical variation in addition to atmospherical makes the calibration problem even harder

Page 4: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

An existing method…

► Models the test image as a mixture distribution and estimates all parameters using the EM-algorithm, with estimated parameters from training data as initial values

► To many degrees of freedom. Statistic fit is excellent, but class labels get mixed.

( )

−+=

∑∑∑== =

C

iiii

PPC

C

C

Pf

PPC

C

C 1

N

1n

C

1ini

,...,,...,,...

1

1

1

1 ,|Plogmaxarg

,...,

,...,

,...

1

1

1

λΣμxΣΣ

μμ

ΣΣμμ

Page 5: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Low-rank parameter modeling► Training image k:

▪ Class mean vector and covariance matrix (class i)

► Class mean vector and covariance matrix model for the test image

α and β are unknown parameter vectors to be estimated from the data

)( and 1 ,, DD) (D kiki ×× Σμ

Page 6: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Low-rank data modeling

► The proposed method for modeling the test data is a low-rank approach since the number of parameters in α is L<D. ▪ This is much less than estimating all C·D

parameters i µ i, i=1,…,C

► By using a low-rank estimation of the class mean vectors of the test data, the spectral differences between the classes is in larger degree maintained

Page 7: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Parameter estimation► Procedure for estimating α

and β:▪ Select N random

samples {y1, y2,… yN} from the test image

Page 8: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Parameter estimation► Procedure for estimating α and β:

▪ Select N random samples {y1, y2,… yN} from the test image

▪ Model them using a Gaussian mixture distribution

► Estimate the parameters by solving the likelihood

Page 9: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Experiment 1:Cloud detection in optical images

► 15 different QuickBird and WorldView-2 images covering 7 different scenes in Norway

► Features▪ Band 2 (green)▪ Band 3 (red)

► Classes▪ clouds, cloud shadows, vegetation,

concrete/asphalt/etc., haze and water

► Resolution down-sampled to 19.2 m (16.0 m)

► 4 different training (sub)images

Page 10: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Experiment 1:Cloud detection in optical images

► Model

δ i is the eigenvector corresponding to the largest eigenvalue νi of the matrix

average

Test

eigenvector

Page 11: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Experiment 1:Cloud detection in optical images

► Parameter estimation. At iteration l+1:

where

Page 12: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Results:Cloud detection in optical images

Without retraining With retraining

Page 13: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Results:Cloud detection in optical images

Page 14: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Results:Cloud detection in optical images

Page 15: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Experiment 2:Tree cover mapping of tropical forest

► 13 different Landsat TM images covering an area nearby Amani, Tanzania (path/row 166/063)

► Features▪ Band 1-5 and 7

► Classes▪ Forest, spares forest, grass and soil

► Two training images (1986-10-06 and 2010-02-10)

Page 16: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Experiment 2:Tree cover mapping of tropical forest

► Model

α constrained to contain only positive elements

► Solution found using non-negative least-squares in combination with iterative maximum-likelihood estimation

Page 17: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Experiment 2:Tree cover mapping of tropical forest

► Parameter estimation: At iteration l+1

where

Page 18: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Results:Tree cover mapping of tropical forest

► *

Without retraining With retraining

February 2010 July 2009

Page 19: Retraining maximum likelihood classifiers using low-rank model.ppt

www.nr.noearthobs.nr.no

Summary and conclusion

► Proposed a simple method for handling the dataset shift between training and test data

► Cloud detection: Evaluated successfully on a many different Quickbird and WorldView-2 images. ▪ Haze versus clouds▪ Confuses snow and clouds

► Guidelines on how to select the low-rank modeling functions is needed

► EM-algorithm and local minima problem

► More testing and evalidation of the method is necessary