SlideShare une entreprise Scribd logo
1  sur  27
Recent Advances in Crop
Classification
Raju Vatsavai

(vatsavairr@ornl.gov)

Computational Sciences and
Engineering Division
ORNL, Oak Ridge, TN, USA
Collaborators:

B. Bhaduri, V. Chandola, G. Jun, J.
Ghosh, S. Shekhar, T. Burk
Remote Sensing – Beyond Images
Workshop, Mexico
th December, 2013.
City, Mexico, 14
Managed by UT-Battelle
for the Department of Energy
Outline
Better spectral and spatial resolution
– Fine-grained (species) classification
– Complex (compound) object recognition

Challenges
– Limited ground-truth: Semi-supervised learning (SSL)
– Spatial homogeneity: SSL + Markov Random Fields
– Spatial heterogeneity: Gaussian Process (GP) learning
– Aggregate vs. Subclasses: Fine-grained classification
– Phenology: Multi-view learning

Conclusions
2

Managed by UT-Battelle
for the Department of Energy
Challenge 1: Limited Training Data
Increasing spectral resolution: 4 to 224 Bands
Challenges
– #of training samples ~ (10 to 30) * (number of dimensions)
– Costly ~ $500-$800 per plot (depends on geographic area)
– Accessibility – Private/Privacy issues (e.g., USFS may average 5%
denied access)
– Real-time – Emergency situations, such as, forest fires, floods

Solutions
– Reduce number of dimensions
– (Artificially) Increase number of samples
– By incorporating unlabeled samples
Naïve semi-supervised (Nigam et al. [JML-2000])
– Bagging [Breiman, ML-96]
3

Managed by UT-Battelle
for the Department of Energy
True Distribution

Estimated Distribution
(Small Samples; MLE
are good asymptotically)

4

Managed by UT-Battelle
for the Department of Energy
Initial Estimates +
Unlabeled Samples

5

Managed by UT-Battelle
for the Department of Energy
Iteratively Update Parameters
Using Unlabeled Samples

6

Managed by UT-Battelle
for the Department of Energy
Iteratively Update Parameters
Using Unlabeled Samples

7

Managed by UT-Battelle
for the Department of Energy
Iteratively Update Parameters
Using Unlabeled Samples

8

Managed by UT-Battelle
for the Department of Energy
Final parameters
after convergence

9

Managed by UT-Battelle
for the Department of Energy
Solution: Semi-supervised Learning
Assume Samples are generated by a
Gaussian Mixture Model (GMM)
• Estimate Parameters with
Expectation Maximization (EM)
E-Step

{

}

T
1
ˆj ˆ j
ˆj
xi - m k ) S-1,k ( xi - m k )
(
2
eij =
-1/2
T
M
1
ˆ
ˆ
ˆ
ˆ
Slk
exp - ( xi - mlk ) S-1,k ( xi - mlk )
ål=1
l
2

ˆ
Skj

-1/2

exp -

{

M-Step
aj

å
=

N
i=1

N

eij

N

ˆj
m k+1

,

i=1 ij i
N
i=1 ij

å
ˆ
Sk+1 = i=1
j
N

and

å ex,
=
å e

ˆj
ˆj
eij ( xi - m k+1 ) ( xi - m k+1 )

å

N

e

i=1 ij

ithdata vector, jth class
10 Managed by UT-Battelle
for the Department of Energy

T

}
Results

Small Subset of 20
Training Samples

10 Classes, 100 Training Samples
(10-30) x No of dimensions / class

20 labeled + 80
unlabeled samples

S u p e rvise d (B C ) vs. S e m i-su p e rvise d (B C -E M )
80

Ranga Raju Vatsavai, Shashi Shekhar, Thomas E. Burk: A SemiSupervised Learning Method for Remote Sensing Data Mining.
ICTAI 2005: 207-211

A c c u ra c y

70

60

50
B C - W o rs t
B C - B est
B C (E M ) - B e s t

40

30
0

20

40

60

80

100

F ixe d U n la b e le d (8 5 ) a n d V a ryin g (In c re a s in g ) L a b e le d

11 Managed by UT-Battelle
for the Department of Energy

120
Challenge 2: Spatial Homogeneity
Spatial Homogeneity
Bayes Theorem: p(c|x) = p(x|c)p(c)/p(x)
For Markov random field , the conditional
distribution of a point in the field given all other Prior Distribution Model:
points is only dependent on its neighbors.
p{ ( s ) |
Where

(S

s )}

p{ ( s ) |

( s )}
For a first - order neighborhood system

S is an image lattice
S

s denotes a set of points in S excluding s

p( )

1
z

c

t (

e

C

)

e.q.1

c

x
x s x
x
12 Managed by UT-Battelle
for the Department of Energy

x x x
x s x
x x x

x
x x x
x x s x x
x x x
x

t ( ) is the total number of horizantally
and vertially neighboring points of different
value in

in clique c .

e.q.1 is Gibbs distribution and therefore,
an MRF.
is emphirically determined weight.
c

t ( )

1 if
( i, j )
otherwise.

{ 0,

( k ,l )
Solution: Spatial Classification
•

•

BC (60%)

BC-EM (68%)

BC-MRF (65%)

BC-EM-MRF (72%)

•

13 Managed by UT-Battelle
for the Department of Energy

Shashi Shekhar, Paul R.
Schrater, Ranga Raju Vatsavai,
Weili Wu, Sanjay Chawla:
Spatial contextual classification
and prediction models for mining
geospatial data. IEEE
Transactions on Multimedia 4(2):
174-188 (2002)
Baris M. Kazar, Shashi Shekhar,
David J. Lilja, Ranga Raju
Vatsavai, R. Kelley Pace:
Comparing Exact and
Approximate Spatial Autoregression Model Solutions for
Spatial Data Analysis. GIScience
2004: 140-161
Ranga Raju Vatsavai, Shashi
Shekhar, Thomas E. Burk: An
efficient spatial semi-supervised
learning algorithm. IJPEDS
22(6): 427-437 (2007)
Challenge 3: Spatial Heterogeneity
Going From Local to Global
– Signature continuity is a problem in classifying large
geographic regions

Solutions
– Assume constant variance structure over space, that is, train
one model, use it on other regions – poor performance
– Train separate model for each region – needs lot of data
– Train one model covering samples from all regions – needs
an adaptive model to capture spatial heterogeneity

14 Managed by UT-Battelle
for the Department of Energy
Solution: Gaussian Process (GP)
Classification
Change of distribution over space is modeled by
p(x | y) ~ N ( ,

)

p ( x ( s ) | y ) ~ N ( ( s ),

( s ))

Goo Jun, Ranga Raju Vatsavai, Joydeep Ghosh: Spatially Adaptive Classification and Active
Learning of Multispectral Data with Gaussian Processes. SSTDM 2009: 597-603
15 Managed by UT-Battelle
for the Department of Energy
Challenge 4: Aggregate Vs. Subclasses
Spectral Classes vs. Thematic Classes

Insufficient Ground-truth
Subjective/domain-dependent
Parametric – assumption violations
16 Managed by UT-Battelle
for the Department of Energy
Solution: Sub-class Classification
Coarse-to-fine Resolution Information Extraction
– Characterizing the nature of the change
Fallow to Switch grass, Wheat to Corn, or crop damage
Coarse Classes (MODIS)
Each class is Gaussian

Sub-Classes (AWiFS)
Each class is MoG
Model Selection (BIC,AIC)
How many components?
Parameter Estimation

Semi-supervised Learning

Characterize Changes
17 Managed by UT-Battelle
for the Department of Energy
Results: Sub-class
Classification

Dataset:
LandSat ETM+ Data (Cloquet, Carleton,
MN, May 31, 2000)
1.
•6 Bands, 4 Classes, 60 plots
•Independent test data: 205 plots
•Forest (4 Subclasses; 2 subclasses are
combined into 1)
2.
•2 Labeled plots per sub-class
18 Managed by UT-Battelle
for the Department of Energy

Ranga Raju Vatsavai, Shashi Shekhar,
Budhendra L. Bhaduri: A Learning Scheme for
Recognizing Sub-classes from Model Trained on
Aggregate Classes. SSPR/SPR 2008: 967-976
Ranga Raju Vatsavai, Shashi Shekhar,
Budhendra L. Bhaduri: A Semi-supervised
Learning Algorithm for Recognizing Sub-classes.
SSTDM 2008: 458-467
Crop (Opium) Classification

Helmand accounts for 75% of the world’s opium
production
GeoEye 4-Band Image, 13th May 2011
19 Managed by UT-Battelle
for the Department of Energy
Ground-truth (Aggregate Classes)

Ground-truth collected for 4 classes
1-Other Crops (Yellow), 2-Poppy (Red), 3-Soils
(Cyan), 4-Water (Blue)
20 Managed by UT-Battelle
for the Department of Energy
Classified (Aggregate) Image

Maximum Likelihood Classification (Widely used)
Also did lot of other standard classification schemes
– Decision Trees, Random Forest, Neural Nets, …
21 Managed by UT-Battelle
for the Department of Energy
Classified (Sub-classes) Image

Sub-class classification – Identifying finer classes from
aggregate class – new scheme
– 1 -> 11,12,13; 2 -> 21,22,23, 3->31,32, 4->41
(Overall Accuracy Improved by ~10%)
22 Managed by UT-Battelle
for the Department of Energy
Challenge 5: Phenology

AWiFS (May 3, 2008;
FCC (4,3,2))
23 Managed by UT-Battelle
for the Department of Energy

AWiFS (July 14, 2008;
FCC (4,3,2))

Thematic Classes: C-Corn, S-Soy
More Formally

24 Managed by UT-Battelle
for the Department of Energy
Solution: Multi-view
Learning
Multi-temporal images are different
views of same phenomena
– Learn single classifier on different views, chose
the best one through empirical evaluation
– Combine different views into a single view, train
classifier on single combined view – stacked
vector approach
– Learn classifier on single view and combine
predictions of individual classifiers – multiple
classifier systems
Bayesian Model Averaging

– Co-training
Learn a classifier independently on each view
Use predictions of each classifier on unlabeled
data instances to augment training dataset for
other classifier
Varun Chandola, Ranga Raju Vatsavai: Multi-temporal remote sensing
image classification - A multi-view approach. CIDU 2010: 258-270
25 Managed by UT-Battelle
for the Department of Energy
Conclusions
We developed several innovative solutions that
address big spatiotemporal data challenges
–
–
–
–

Semi-supervised learning
Spatial classification (homogeneity and heterogeneity)
Temporal classification
Sub-class classification

Ongoing
– Transfer learning: Adopt model learned in area to the
other with very little additional ground-truth
– Compound object classification (multiple instance
learning)
– Semantic classification (beyond pixels and objects)
– Scaling
Heterogeneous (OpenMP + MPI + CUDA)
Cloud computing (MapReduce)
26 Managed by UT-Battelle
for the Department of Energy
Acknowledgements
Prepared by Oak Ridge National Laboratory,
P.O. Box 2008, Oak Ridge, Tennessee 378316285, managed by UT-Battelle, LLC for the U. S.
Department of Energy under contract no.
DEAC05-00OR22725.
Collaborators and Sponsors

27 Managed by UT-Battelle
for the Department of Energy

Contenu connexe

Similaire à Recent Advances in Crop Classification

NIST-JARVIS infrastructure for Improved Materials Design
NIST-JARVIS infrastructure for Improved Materials DesignNIST-JARVIS infrastructure for Improved Materials Design
NIST-JARVIS infrastructure for Improved Materials DesignKAMAL CHOUDHARY
 
AUTOMATIC SPECTRAL CLASSIFICATION OF STARS USING MACHINE LEARNING: AN APPROAC...
AUTOMATIC SPECTRAL CLASSIFICATION OF STARS USING MACHINE LEARNING: AN APPROAC...AUTOMATIC SPECTRAL CLASSIFICATION OF STARS USING MACHINE LEARNING: AN APPROAC...
AUTOMATIC SPECTRAL CLASSIFICATION OF STARS USING MACHINE LEARNING: AN APPROAC...mlaij
 
Molinier - Feature Selection for Tree Species Identification in Very High res...
Molinier - Feature Selection for Tree Species Identification in Very High res...Molinier - Feature Selection for Tree Species Identification in Very High res...
Molinier - Feature Selection for Tree Species Identification in Very High res...grssieee
 
Autonomous experimental phase diagram acquisition
Autonomous experimental phase diagram acquisitionAutonomous experimental phase diagram acquisition
Autonomous experimental phase diagram acquisitionaimsnist
 
3D Scene Analysis via Sequenced Predictions over Points and Regions
3D Scene Analysis via Sequenced Predictions over Points and Regions3D Scene Analysis via Sequenced Predictions over Points and Regions
3D Scene Analysis via Sequenced Predictions over Points and RegionsFlavia Grosan
 
Crystallization classification semisupervised
Crystallization classification semisupervisedCrystallization classification semisupervised
Crystallization classification semisupervisedMadhav Sigdel
 
Chapter5.pdf
Chapter5.pdfChapter5.pdf
Chapter5.pdfsravan66
 
Monitoring Biomass Dynamics at Scale: Emerging Trends and Recent Successes
Monitoring Biomass Dynamics at Scale: Emerging Trends and Recent SuccessesMonitoring Biomass Dynamics at Scale: Emerging Trends and Recent Successes
Monitoring Biomass Dynamics at Scale: Emerging Trends and Recent SuccessesCIMMYT
 
Lecture: Ensembles and free energy in Monte Carlo simulations
Lecture: Ensembles and free energy in Monte Carlo simulationsLecture: Ensembles and free energy in Monte Carlo simulations
Lecture: Ensembles and free energy in Monte Carlo simulationsNikolai Priezjev
 
Instance Based Learning in Machine Learning
Instance Based Learning in Machine LearningInstance Based Learning in Machine Learning
Instance Based Learning in Machine LearningPavithra Thippanaik
 
Data Science Education: Needs & Opportunities in Astronomy
Data Science Education: Needs & Opportunities in AstronomyData Science Education: Needs & Opportunities in Astronomy
Data Science Education: Needs & Opportunities in AstronomyJoshua Bloom
 
Lecture: Interatomic Potentials Enabled by Machine Learning
Lecture: Interatomic Potentials Enabled by Machine LearningLecture: Interatomic Potentials Enabled by Machine Learning
Lecture: Interatomic Potentials Enabled by Machine LearningDanielSchwalbeKoda
 
Mathematical Modelling and Computer Simulation Assist in Designing Non-tradit...
Mathematical Modelling and Computer Simulation Assist in Designing Non-tradit...Mathematical Modelling and Computer Simulation Assist in Designing Non-tradit...
Mathematical Modelling and Computer Simulation Assist in Designing Non-tradit...IJECEIAES
 
Chiral Particle/Photon emission from heavy-light mesons
Chiral Particle/Photon emission from heavy-light mesonsChiral Particle/Photon emission from heavy-light mesons
Chiral Particle/Photon emission from heavy-light mesonsTakayuki Matsuki
 

Similaire à Recent Advances in Crop Classification (20)

NIST-JARVIS infrastructure for Improved Materials Design
NIST-JARVIS infrastructure for Improved Materials DesignNIST-JARVIS infrastructure for Improved Materials Design
NIST-JARVIS infrastructure for Improved Materials Design
 
AUTOMATIC SPECTRAL CLASSIFICATION OF STARS USING MACHINE LEARNING: AN APPROAC...
AUTOMATIC SPECTRAL CLASSIFICATION OF STARS USING MACHINE LEARNING: AN APPROAC...AUTOMATIC SPECTRAL CLASSIFICATION OF STARS USING MACHINE LEARNING: AN APPROAC...
AUTOMATIC SPECTRAL CLASSIFICATION OF STARS USING MACHINE LEARNING: AN APPROAC...
 
Biehl hanze-2021
Biehl hanze-2021Biehl hanze-2021
Biehl hanze-2021
 
An Introduction to Metric Learning for Clustering
An Introduction to Metric Learning for ClusteringAn Introduction to Metric Learning for Clustering
An Introduction to Metric Learning for Clustering
 
Molinier - Feature Selection for Tree Species Identification in Very High res...
Molinier - Feature Selection for Tree Species Identification in Very High res...Molinier - Feature Selection for Tree Species Identification in Very High res...
Molinier - Feature Selection for Tree Species Identification in Very High res...
 
Autonomous experimental phase diagram acquisition
Autonomous experimental phase diagram acquisitionAutonomous experimental phase diagram acquisition
Autonomous experimental phase diagram acquisition
 
3D Scene Analysis via Sequenced Predictions over Points and Regions
3D Scene Analysis via Sequenced Predictions over Points and Regions3D Scene Analysis via Sequenced Predictions over Points and Regions
3D Scene Analysis via Sequenced Predictions over Points and Regions
 
JaroslavHQL2016_final
JaroslavHQL2016_finalJaroslavHQL2016_final
JaroslavHQL2016_final
 
Crystallization classification semisupervised
Crystallization classification semisupervisedCrystallization classification semisupervised
Crystallization classification semisupervised
 
Undergraduate Modeling Workshop - Hierarchical Models for Sparsely Sampled Hi...
Undergraduate Modeling Workshop - Hierarchical Models for Sparsely Sampled Hi...Undergraduate Modeling Workshop - Hierarchical Models for Sparsely Sampled Hi...
Undergraduate Modeling Workshop - Hierarchical Models for Sparsely Sampled Hi...
 
Chapter5.pdf
Chapter5.pdfChapter5.pdf
Chapter5.pdf
 
CLIM: Transition Workshop - Accounting for Model Errors Due to Sub-Grid Scale...
CLIM: Transition Workshop - Accounting for Model Errors Due to Sub-Grid Scale...CLIM: Transition Workshop - Accounting for Model Errors Due to Sub-Grid Scale...
CLIM: Transition Workshop - Accounting for Model Errors Due to Sub-Grid Scale...
 
MCCS
MCCSMCCS
MCCS
 
Monitoring Biomass Dynamics at Scale: Emerging Trends and Recent Successes
Monitoring Biomass Dynamics at Scale: Emerging Trends and Recent SuccessesMonitoring Biomass Dynamics at Scale: Emerging Trends and Recent Successes
Monitoring Biomass Dynamics at Scale: Emerging Trends and Recent Successes
 
Lecture: Ensembles and free energy in Monte Carlo simulations
Lecture: Ensembles and free energy in Monte Carlo simulationsLecture: Ensembles and free energy in Monte Carlo simulations
Lecture: Ensembles and free energy in Monte Carlo simulations
 
Instance Based Learning in Machine Learning
Instance Based Learning in Machine LearningInstance Based Learning in Machine Learning
Instance Based Learning in Machine Learning
 
Data Science Education: Needs & Opportunities in Astronomy
Data Science Education: Needs & Opportunities in AstronomyData Science Education: Needs & Opportunities in Astronomy
Data Science Education: Needs & Opportunities in Astronomy
 
Lecture: Interatomic Potentials Enabled by Machine Learning
Lecture: Interatomic Potentials Enabled by Machine LearningLecture: Interatomic Potentials Enabled by Machine Learning
Lecture: Interatomic Potentials Enabled by Machine Learning
 
Mathematical Modelling and Computer Simulation Assist in Designing Non-tradit...
Mathematical Modelling and Computer Simulation Assist in Designing Non-tradit...Mathematical Modelling and Computer Simulation Assist in Designing Non-tradit...
Mathematical Modelling and Computer Simulation Assist in Designing Non-tradit...
 
Chiral Particle/Photon emission from heavy-light mesons
Chiral Particle/Photon emission from heavy-light mesonsChiral Particle/Photon emission from heavy-light mesons
Chiral Particle/Photon emission from heavy-light mesons
 

Plus de CIMMYT

What do women and men farmers want in their maize varieties
What do women and men farmers want in their maize varietiesWhat do women and men farmers want in their maize varieties
What do women and men farmers want in their maize varietiesCIMMYT
 
Transforming Maize-legume Value Chains – A Business Case for Climate-Smart Ag...
Transforming Maize-legume Value Chains –A Business Case for Climate-Smart Ag...Transforming Maize-legume Value Chains –A Business Case for Climate-Smart Ag...
Transforming Maize-legume Value Chains – A Business Case for Climate-Smart Ag...CIMMYT
 
Maize for Asian tropics: Chasing the moving target
Maize for Asian tropics: Chasing the moving targetMaize for Asian tropics: Chasing the moving target
Maize for Asian tropics: Chasing the moving targetCIMMYT
 
Tropical maize genome: what do we know so far and how to use that information
Tropical maize genome: what do we know so far and how to use that informationTropical maize genome: what do we know so far and how to use that information
Tropical maize genome: what do we know so far and how to use that informationCIMMYT
 
Social inclusion of young people and site-specific nutrient management (SSNM)...
Social inclusion of young people and site-specific nutrient management (SSNM)...Social inclusion of young people and site-specific nutrient management (SSNM)...
Social inclusion of young people and site-specific nutrient management (SSNM)...CIMMYT
 
Identification of quantitative trait loci for resistance to shoot fly in maize
Identification of quantitative trait loci for resistance to shoot fly in maizeIdentification of quantitative trait loci for resistance to shoot fly in maize
Identification of quantitative trait loci for resistance to shoot fly in maizeCIMMYT
 
The development of two sweet corn populations resistance to northern corn lea...
The development of two sweet corn populations resistance to northern corn lea...The development of two sweet corn populations resistance to northern corn lea...
The development of two sweet corn populations resistance to northern corn lea...CIMMYT
 
Outbreak of Fusarium ear rot on Maize in Thailand
Outbreak of Fusarium ear rot on Maize in ThailandOutbreak of Fusarium ear rot on Maize in Thailand
Outbreak of Fusarium ear rot on Maize in ThailandCIMMYT
 
Next Generation Phenotyping Technologies in Breeding for Abiotic Stress Toler...
Next Generation Phenotyping Technologies in Breeding for Abiotic Stress Toler...Next Generation Phenotyping Technologies in Breeding for Abiotic Stress Toler...
Next Generation Phenotyping Technologies in Breeding for Abiotic Stress Toler...CIMMYT
 
Marker-assisted introgression of waxy1 gene into elite inbreds for enhancemen...
Marker-assisted introgression of waxy1 gene into elite inbreds for enhancemen...Marker-assisted introgression of waxy1 gene into elite inbreds for enhancemen...
Marker-assisted introgression of waxy1 gene into elite inbreds for enhancemen...CIMMYT
 
Comparative Analysis of Biochemical & Physiological Responses of Maize Genoty...
Comparative Analysis of Biochemical & Physiological Responses of Maize Genoty...Comparative Analysis of Biochemical & Physiological Responses of Maize Genoty...
Comparative Analysis of Biochemical & Physiological Responses of Maize Genoty...CIMMYT
 
Maize intensification in major production regions of the world
Maize intensification in major production regions of the worldMaize intensification in major production regions of the world
Maize intensification in major production regions of the worldCIMMYT
 
Genomic and enabling technologies in maize breeding for enhanced genetic gain...
Genomic and enabling technologies in maize breeding for enhanced genetic gain...Genomic and enabling technologies in maize breeding for enhanced genetic gain...
Genomic and enabling technologies in maize breeding for enhanced genetic gain...CIMMYT
 
Defense Response boost Through Cu-chitosan Nanoparticles and Plant Growth enh...
Defense Response boost Through Cu-chitosan Nanoparticles and Plant Growth enh...Defense Response boost Through Cu-chitosan Nanoparticles and Plant Growth enh...
Defense Response boost Through Cu-chitosan Nanoparticles and Plant Growth enh...CIMMYT
 
Institutional and Policy Innovations for Food and Nutrition Security in Asia ...
Institutional and Policy Innovations for Food and Nutrition Security in Asia ...Institutional and Policy Innovations for Food and Nutrition Security in Asia ...
Institutional and Policy Innovations for Food and Nutrition Security in Asia ...CIMMYT
 
New agricultural technologies and gender dynamics at house holds in rural Ba...
 New agricultural technologies and gender dynamics at house holds in rural Ba... New agricultural technologies and gender dynamics at house holds in rural Ba...
New agricultural technologies and gender dynamics at house holds in rural Ba...CIMMYT
 
Effects of QPM and PVA maize on chicken
Effects of QPM and PVA maize on chickenEffects of QPM and PVA maize on chicken
Effects of QPM and PVA maize on chickenCIMMYT
 
Seeds of Discovery
Seeds of DiscoverySeeds of Discovery
Seeds of DiscoveryCIMMYT
 
Soil and nitrogen management in maize
Soil and nitrogen management in maizeSoil and nitrogen management in maize
Soil and nitrogen management in maizeCIMMYT
 
Technologies to drive maize yield improvement
Technologies to drive maize yield improvementTechnologies to drive maize yield improvement
Technologies to drive maize yield improvementCIMMYT
 

Plus de CIMMYT (20)

What do women and men farmers want in their maize varieties
What do women and men farmers want in their maize varietiesWhat do women and men farmers want in their maize varieties
What do women and men farmers want in their maize varieties
 
Transforming Maize-legume Value Chains – A Business Case for Climate-Smart Ag...
Transforming Maize-legume Value Chains –A Business Case for Climate-Smart Ag...Transforming Maize-legume Value Chains –A Business Case for Climate-Smart Ag...
Transforming Maize-legume Value Chains – A Business Case for Climate-Smart Ag...
 
Maize for Asian tropics: Chasing the moving target
Maize for Asian tropics: Chasing the moving targetMaize for Asian tropics: Chasing the moving target
Maize for Asian tropics: Chasing the moving target
 
Tropical maize genome: what do we know so far and how to use that information
Tropical maize genome: what do we know so far and how to use that informationTropical maize genome: what do we know so far and how to use that information
Tropical maize genome: what do we know so far and how to use that information
 
Social inclusion of young people and site-specific nutrient management (SSNM)...
Social inclusion of young people and site-specific nutrient management (SSNM)...Social inclusion of young people and site-specific nutrient management (SSNM)...
Social inclusion of young people and site-specific nutrient management (SSNM)...
 
Identification of quantitative trait loci for resistance to shoot fly in maize
Identification of quantitative trait loci for resistance to shoot fly in maizeIdentification of quantitative trait loci for resistance to shoot fly in maize
Identification of quantitative trait loci for resistance to shoot fly in maize
 
The development of two sweet corn populations resistance to northern corn lea...
The development of two sweet corn populations resistance to northern corn lea...The development of two sweet corn populations resistance to northern corn lea...
The development of two sweet corn populations resistance to northern corn lea...
 
Outbreak of Fusarium ear rot on Maize in Thailand
Outbreak of Fusarium ear rot on Maize in ThailandOutbreak of Fusarium ear rot on Maize in Thailand
Outbreak of Fusarium ear rot on Maize in Thailand
 
Next Generation Phenotyping Technologies in Breeding for Abiotic Stress Toler...
Next Generation Phenotyping Technologies in Breeding for Abiotic Stress Toler...Next Generation Phenotyping Technologies in Breeding for Abiotic Stress Toler...
Next Generation Phenotyping Technologies in Breeding for Abiotic Stress Toler...
 
Marker-assisted introgression of waxy1 gene into elite inbreds for enhancemen...
Marker-assisted introgression of waxy1 gene into elite inbreds for enhancemen...Marker-assisted introgression of waxy1 gene into elite inbreds for enhancemen...
Marker-assisted introgression of waxy1 gene into elite inbreds for enhancemen...
 
Comparative Analysis of Biochemical & Physiological Responses of Maize Genoty...
Comparative Analysis of Biochemical & Physiological Responses of Maize Genoty...Comparative Analysis of Biochemical & Physiological Responses of Maize Genoty...
Comparative Analysis of Biochemical & Physiological Responses of Maize Genoty...
 
Maize intensification in major production regions of the world
Maize intensification in major production regions of the worldMaize intensification in major production regions of the world
Maize intensification in major production regions of the world
 
Genomic and enabling technologies in maize breeding for enhanced genetic gain...
Genomic and enabling technologies in maize breeding for enhanced genetic gain...Genomic and enabling technologies in maize breeding for enhanced genetic gain...
Genomic and enabling technologies in maize breeding for enhanced genetic gain...
 
Defense Response boost Through Cu-chitosan Nanoparticles and Plant Growth enh...
Defense Response boost Through Cu-chitosan Nanoparticles and Plant Growth enh...Defense Response boost Through Cu-chitosan Nanoparticles and Plant Growth enh...
Defense Response boost Through Cu-chitosan Nanoparticles and Plant Growth enh...
 
Institutional and Policy Innovations for Food and Nutrition Security in Asia ...
Institutional and Policy Innovations for Food and Nutrition Security in Asia ...Institutional and Policy Innovations for Food and Nutrition Security in Asia ...
Institutional and Policy Innovations for Food and Nutrition Security in Asia ...
 
New agricultural technologies and gender dynamics at house holds in rural Ba...
 New agricultural technologies and gender dynamics at house holds in rural Ba... New agricultural technologies and gender dynamics at house holds in rural Ba...
New agricultural technologies and gender dynamics at house holds in rural Ba...
 
Effects of QPM and PVA maize on chicken
Effects of QPM and PVA maize on chickenEffects of QPM and PVA maize on chicken
Effects of QPM and PVA maize on chicken
 
Seeds of Discovery
Seeds of DiscoverySeeds of Discovery
Seeds of Discovery
 
Soil and nitrogen management in maize
Soil and nitrogen management in maizeSoil and nitrogen management in maize
Soil and nitrogen management in maize
 
Technologies to drive maize yield improvement
Technologies to drive maize yield improvementTechnologies to drive maize yield improvement
Technologies to drive maize yield improvement
 

Dernier

Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhikauryashika82
 
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxBasic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxDenish Jangid
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxVishalSingh1417
 
Unit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxUnit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxVishalSingh1417
 
Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104misteraugie
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphThiyagu K
 
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17  How to Extend Models Using Mixin ClassesMixin Classes in Odoo 17  How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17 How to Extend Models Using Mixin ClassesCeline George
 
Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfagholdier
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactdawncurless
 
fourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writingfourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writingTeacherCyreneCayanan
 
Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..Disha Kariya
 
microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introductionMaksud Ahmed
 
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...Shubhangi Sonawane
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfJayanti Pande
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactPECB
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingTechSoup
 
Gardella_PRCampaignConclusion Pitch Letter
Gardella_PRCampaignConclusion Pitch LetterGardella_PRCampaignConclusion Pitch Letter
Gardella_PRCampaignConclusion Pitch LetterMateoGardella
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsTechSoup
 
An Overview of Mutual Funds Bcom Project.pdf
An Overview of Mutual Funds Bcom Project.pdfAn Overview of Mutual Funds Bcom Project.pdf
An Overview of Mutual Funds Bcom Project.pdfSanaAli374401
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeThiyagu K
 

Dernier (20)

Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in DelhiRussian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
Russian Escort Service in Delhi 11k Hotel Foreigner Russian Call Girls in Delhi
 
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxBasic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptx
 
Unit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxUnit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptx
 
Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot Graph
 
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17  How to Extend Models Using Mixin ClassesMixin Classes in Odoo 17  How to Extend Models Using Mixin Classes
Mixin Classes in Odoo 17 How to Extend Models Using Mixin Classes
 
Holdier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdfHoldier Curriculum Vitae (April 2024).pdf
Holdier Curriculum Vitae (April 2024).pdf
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impact
 
fourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writingfourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writing
 
Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..
 
microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introduction
 
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdf
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global Impact
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy Consulting
 
Gardella_PRCampaignConclusion Pitch Letter
Gardella_PRCampaignConclusion Pitch LetterGardella_PRCampaignConclusion Pitch Letter
Gardella_PRCampaignConclusion Pitch Letter
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The Basics
 
An Overview of Mutual Funds Bcom Project.pdf
An Overview of Mutual Funds Bcom Project.pdfAn Overview of Mutual Funds Bcom Project.pdf
An Overview of Mutual Funds Bcom Project.pdf
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and Mode
 

Recent Advances in Crop Classification

  • 1. Recent Advances in Crop Classification Raju Vatsavai (vatsavairr@ornl.gov) Computational Sciences and Engineering Division ORNL, Oak Ridge, TN, USA Collaborators: B. Bhaduri, V. Chandola, G. Jun, J. Ghosh, S. Shekhar, T. Burk Remote Sensing – Beyond Images Workshop, Mexico th December, 2013. City, Mexico, 14 Managed by UT-Battelle for the Department of Energy
  • 2. Outline Better spectral and spatial resolution – Fine-grained (species) classification – Complex (compound) object recognition Challenges – Limited ground-truth: Semi-supervised learning (SSL) – Spatial homogeneity: SSL + Markov Random Fields – Spatial heterogeneity: Gaussian Process (GP) learning – Aggregate vs. Subclasses: Fine-grained classification – Phenology: Multi-view learning Conclusions 2 Managed by UT-Battelle for the Department of Energy
  • 3. Challenge 1: Limited Training Data Increasing spectral resolution: 4 to 224 Bands Challenges – #of training samples ~ (10 to 30) * (number of dimensions) – Costly ~ $500-$800 per plot (depends on geographic area) – Accessibility – Private/Privacy issues (e.g., USFS may average 5% denied access) – Real-time – Emergency situations, such as, forest fires, floods Solutions – Reduce number of dimensions – (Artificially) Increase number of samples – By incorporating unlabeled samples Naïve semi-supervised (Nigam et al. [JML-2000]) – Bagging [Breiman, ML-96] 3 Managed by UT-Battelle for the Department of Energy
  • 4. True Distribution Estimated Distribution (Small Samples; MLE are good asymptotically) 4 Managed by UT-Battelle for the Department of Energy
  • 5. Initial Estimates + Unlabeled Samples 5 Managed by UT-Battelle for the Department of Energy
  • 6. Iteratively Update Parameters Using Unlabeled Samples 6 Managed by UT-Battelle for the Department of Energy
  • 7. Iteratively Update Parameters Using Unlabeled Samples 7 Managed by UT-Battelle for the Department of Energy
  • 8. Iteratively Update Parameters Using Unlabeled Samples 8 Managed by UT-Battelle for the Department of Energy
  • 9. Final parameters after convergence 9 Managed by UT-Battelle for the Department of Energy
  • 10. Solution: Semi-supervised Learning Assume Samples are generated by a Gaussian Mixture Model (GMM) • Estimate Parameters with Expectation Maximization (EM) E-Step { } T 1 ˆj ˆ j ˆj xi - m k ) S-1,k ( xi - m k ) ( 2 eij = -1/2 T M 1 ˆ ˆ ˆ ˆ Slk exp - ( xi - mlk ) S-1,k ( xi - mlk ) ål=1 l 2 ˆ Skj -1/2 exp - { M-Step aj å = N i=1 N eij N ˆj m k+1 , i=1 ij i N i=1 ij å ˆ Sk+1 = i=1 j N and å ex, = å e ˆj ˆj eij ( xi - m k+1 ) ( xi - m k+1 ) å N e i=1 ij ithdata vector, jth class 10 Managed by UT-Battelle for the Department of Energy T }
  • 11. Results Small Subset of 20 Training Samples 10 Classes, 100 Training Samples (10-30) x No of dimensions / class 20 labeled + 80 unlabeled samples S u p e rvise d (B C ) vs. S e m i-su p e rvise d (B C -E M ) 80 Ranga Raju Vatsavai, Shashi Shekhar, Thomas E. Burk: A SemiSupervised Learning Method for Remote Sensing Data Mining. ICTAI 2005: 207-211 A c c u ra c y 70 60 50 B C - W o rs t B C - B est B C (E M ) - B e s t 40 30 0 20 40 60 80 100 F ixe d U n la b e le d (8 5 ) a n d V a ryin g (In c re a s in g ) L a b e le d 11 Managed by UT-Battelle for the Department of Energy 120
  • 12. Challenge 2: Spatial Homogeneity Spatial Homogeneity Bayes Theorem: p(c|x) = p(x|c)p(c)/p(x) For Markov random field , the conditional distribution of a point in the field given all other Prior Distribution Model: points is only dependent on its neighbors. p{ ( s ) | Where (S s )} p{ ( s ) | ( s )} For a first - order neighborhood system S is an image lattice S s denotes a set of points in S excluding s p( ) 1 z c t ( e C ) e.q.1 c x x s x x 12 Managed by UT-Battelle for the Department of Energy x x x x s x x x x x x x x x x s x x x x x x t ( ) is the total number of horizantally and vertially neighboring points of different value in in clique c . e.q.1 is Gibbs distribution and therefore, an MRF. is emphirically determined weight. c t ( ) 1 if ( i, j ) otherwise. { 0, ( k ,l )
  • 13. Solution: Spatial Classification • • BC (60%) BC-EM (68%) BC-MRF (65%) BC-EM-MRF (72%) • 13 Managed by UT-Battelle for the Department of Energy Shashi Shekhar, Paul R. Schrater, Ranga Raju Vatsavai, Weili Wu, Sanjay Chawla: Spatial contextual classification and prediction models for mining geospatial data. IEEE Transactions on Multimedia 4(2): 174-188 (2002) Baris M. Kazar, Shashi Shekhar, David J. Lilja, Ranga Raju Vatsavai, R. Kelley Pace: Comparing Exact and Approximate Spatial Autoregression Model Solutions for Spatial Data Analysis. GIScience 2004: 140-161 Ranga Raju Vatsavai, Shashi Shekhar, Thomas E. Burk: An efficient spatial semi-supervised learning algorithm. IJPEDS 22(6): 427-437 (2007)
  • 14. Challenge 3: Spatial Heterogeneity Going From Local to Global – Signature continuity is a problem in classifying large geographic regions Solutions – Assume constant variance structure over space, that is, train one model, use it on other regions – poor performance – Train separate model for each region – needs lot of data – Train one model covering samples from all regions – needs an adaptive model to capture spatial heterogeneity 14 Managed by UT-Battelle for the Department of Energy
  • 15. Solution: Gaussian Process (GP) Classification Change of distribution over space is modeled by p(x | y) ~ N ( , ) p ( x ( s ) | y ) ~ N ( ( s ), ( s )) Goo Jun, Ranga Raju Vatsavai, Joydeep Ghosh: Spatially Adaptive Classification and Active Learning of Multispectral Data with Gaussian Processes. SSTDM 2009: 597-603 15 Managed by UT-Battelle for the Department of Energy
  • 16. Challenge 4: Aggregate Vs. Subclasses Spectral Classes vs. Thematic Classes Insufficient Ground-truth Subjective/domain-dependent Parametric – assumption violations 16 Managed by UT-Battelle for the Department of Energy
  • 17. Solution: Sub-class Classification Coarse-to-fine Resolution Information Extraction – Characterizing the nature of the change Fallow to Switch grass, Wheat to Corn, or crop damage Coarse Classes (MODIS) Each class is Gaussian Sub-Classes (AWiFS) Each class is MoG Model Selection (BIC,AIC) How many components? Parameter Estimation Semi-supervised Learning Characterize Changes 17 Managed by UT-Battelle for the Department of Energy
  • 18. Results: Sub-class Classification Dataset: LandSat ETM+ Data (Cloquet, Carleton, MN, May 31, 2000) 1. •6 Bands, 4 Classes, 60 plots •Independent test data: 205 plots •Forest (4 Subclasses; 2 subclasses are combined into 1) 2. •2 Labeled plots per sub-class 18 Managed by UT-Battelle for the Department of Energy Ranga Raju Vatsavai, Shashi Shekhar, Budhendra L. Bhaduri: A Learning Scheme for Recognizing Sub-classes from Model Trained on Aggregate Classes. SSPR/SPR 2008: 967-976 Ranga Raju Vatsavai, Shashi Shekhar, Budhendra L. Bhaduri: A Semi-supervised Learning Algorithm for Recognizing Sub-classes. SSTDM 2008: 458-467
  • 19. Crop (Opium) Classification Helmand accounts for 75% of the world’s opium production GeoEye 4-Band Image, 13th May 2011 19 Managed by UT-Battelle for the Department of Energy
  • 20. Ground-truth (Aggregate Classes) Ground-truth collected for 4 classes 1-Other Crops (Yellow), 2-Poppy (Red), 3-Soils (Cyan), 4-Water (Blue) 20 Managed by UT-Battelle for the Department of Energy
  • 21. Classified (Aggregate) Image Maximum Likelihood Classification (Widely used) Also did lot of other standard classification schemes – Decision Trees, Random Forest, Neural Nets, … 21 Managed by UT-Battelle for the Department of Energy
  • 22. Classified (Sub-classes) Image Sub-class classification – Identifying finer classes from aggregate class – new scheme – 1 -> 11,12,13; 2 -> 21,22,23, 3->31,32, 4->41 (Overall Accuracy Improved by ~10%) 22 Managed by UT-Battelle for the Department of Energy
  • 23. Challenge 5: Phenology AWiFS (May 3, 2008; FCC (4,3,2)) 23 Managed by UT-Battelle for the Department of Energy AWiFS (July 14, 2008; FCC (4,3,2)) Thematic Classes: C-Corn, S-Soy
  • 24. More Formally 24 Managed by UT-Battelle for the Department of Energy
  • 25. Solution: Multi-view Learning Multi-temporal images are different views of same phenomena – Learn single classifier on different views, chose the best one through empirical evaluation – Combine different views into a single view, train classifier on single combined view – stacked vector approach – Learn classifier on single view and combine predictions of individual classifiers – multiple classifier systems Bayesian Model Averaging – Co-training Learn a classifier independently on each view Use predictions of each classifier on unlabeled data instances to augment training dataset for other classifier Varun Chandola, Ranga Raju Vatsavai: Multi-temporal remote sensing image classification - A multi-view approach. CIDU 2010: 258-270 25 Managed by UT-Battelle for the Department of Energy
  • 26. Conclusions We developed several innovative solutions that address big spatiotemporal data challenges – – – – Semi-supervised learning Spatial classification (homogeneity and heterogeneity) Temporal classification Sub-class classification Ongoing – Transfer learning: Adopt model learned in area to the other with very little additional ground-truth – Compound object classification (multiple instance learning) – Semantic classification (beyond pixels and objects) – Scaling Heterogeneous (OpenMP + MPI + CUDA) Cloud computing (MapReduce) 26 Managed by UT-Battelle for the Department of Energy
  • 27. Acknowledgements Prepared by Oak Ridge National Laboratory, P.O. Box 2008, Oak Ridge, Tennessee 378316285, managed by UT-Battelle, LLC for the U. S. Department of Energy under contract no. DEAC05-00OR22725. Collaborators and Sponsors 27 Managed by UT-Battelle for the Department of Energy