Galkin prospecting

Information about Galkin prospecting

Published on October 30, 2007

Author: Irvette

Source: authorstream.com

Content

Data Prospecting with CORPRAL: PRE-ATTENTIVE VISION MODEL AT WORK:  Data Prospecting with CORPRAL: PRE-ATTENTIVE VISION MODEL AT WORK I. Galkin, B. W. Reinisch, G. Khmyrov, A. Kozlov, J.Grinstein University of Massachusetts Lowell, Center for Atmospheric Research, USA S. F. Fung NASA Goddard Space Flight Center, USA IN33D • Intelligent and Adaptive Systems for Data Collection, Processing, and Knowledge Discovery • December 6, 2005 Layout:  Layout Introduction Data Prospecting Concept and Applications Pre-attentive Vision vs. Attention-Driven Vision Pre-attentive Vision Algorithm (highlights) Real-life case: CORPRAL prospector for Radio Plasma Imager plasmagrams Motivation CORPRAL capabilities Study of data prospecting accuracy Summary Data Prospecting:  Data Prospecting Data Prospecting: Find useful data among data that just hold space Draw attention of human analysts to these data Optional: discard irrelevant data vs. Data Mining: Find unknown dependencies between elements constituting the dataset Extracting empirical models from data vs. Data Exploration Visualization Browsing Subsetting Imagery Data Prospecting Projects:  Imagery Data Prospecting Projects Early Warning systems Spacewatch asteriod detector (U.Arizona) Demeter space-borne earthquake detector (France) Solar event detector at BBSO Other intelligent sensors Large archives of imagery data Petabyte archives of NASA EOS and VOA High energy physics imagery archives Radio Plasma Imager (RPI) on IMAGE spacecraft Autonomous and Collaborative Systems Mars Rovers (OASIS & CLARAty by JPL) Honda Robot “ASIMO” Pre-attentive Vision:  Pre-attentive Vision Visual perception system in life organisms that constantly searches visual cues without willful attention Works best for detection of objects in the field of view No assumption about shape Looking for things that “stand out” against the background Pre-attentive vision involves directional processing “LAYMAN” APPROACH No prior knowledge of domain Pre-attentive Vision (2):  Pre-attentive Vision (2) Relatively well understood Location of oriented edgels (edge elements) Bottom-up grouping of edgels in contours under Gestalt perceptual constraints Good continuity Proximity Co-circularity CONTINUITY [Co-circularity] INPUT Oriented Edgels GROUPING Real Life Case: Radio Plasma Imager:  Real Life Case: Radio Plasma Imager 1.2 million images by Dec 2005 Multiple signatures of signal propagation No signatures 14 hours later, similar orbit radar of opportunity Data Prospecting Needs:  Data Prospecting Needs < 20% with traces How difficult is the task?:  How difficult is the task? Traces are thin and sketchy lines immersed in a textured background (noise) Smoothing destroys traces, contrast enhancements don’t help Tremendous variability of both traces and noise characteristics locally on one plasmagram globally within one orbit and from year to year FAINT TRACES TRACE MIX Perceptual Grouping Algorithm:  Perceptual Grouping Algorithm ROTOR MODEL Recurrent neural network for optimization of rotor orientations Carson Peterson (1990) INTERACTION PATTERN Bio-plausible model of rotor interaction e.g., Yen and Finkel (1998) Initial state of NN Final state of NN ANNA ANNA Grouping Example:  ANNA Grouping Example Input pattern Rotor Optimization Initial grouping Final grouping Grouping Example (2):  Grouping Example (2) Input pattern Rotor Optimization Initial grouping DEAD ZONES Example:  Example Prospecting Results:  Prospecting Results ~ 2500 plasmagrams with 5 traces or more Slide15:  http://car.uml.edu/rpi/corpral/ Intelligent Data Subsetting:  Intelligent Data Subsetting RPI Mission Database Level II CORPRAL ratings Orbital data Geospace model data Targeted queues of useful data Pin-point particular magnetospheric structures Polar cap Plasma trough Narrow down data acquired in particular operational mode Would be happy to see this subsetting used more Mission at a Glance:  Mission at a Glance 1.2 million plasmagrams processed Trace Occurrence Study:  Trace Occurrence Study Trace Occurrence 4 years of data CORPRAL Accuracy Study:  CORPRAL Accuracy Study CORPRAL Performance 2000-2001:  CORPRAL Performance 2000-2001 Sensitivity 85% - chances for “interesting” plasmagrams to be tagged Specificity 94% - chances for empty plasmagram to be ignored PPV 57% - chances that tagged plasmagram is actually interesting NPV 99% - chances that ignored plasmagram was actually empty Accuracy 94% - % of correct decisions 7.9% prevalence CORPRAL Errors:  CORPRAL Errors False negative (missed trace) False positive Attention is required Areas of Concern:  Areas of Concern Major source of false positives and negatives lies in the echo detection algorithm currently 1D version is used to label amplitudes above certain threshold level errors in echo detection propagate to the next levels of analysis uncompensated (“pre-attentive” model) grouping algorithm “hallucinates” traces, and there is no attention-driven algorithm to rule out those We are interested in 2D approaches to detection of edgels Summary:  Summary Pre-attentive vision model was created for detection of non-specific features in images (bottom-up processing) The model was applied as data prospector to 1.2 M RPI plasmagram dataset, at ~94% accuracy of prospecting Future development targets a more robust detection of the faint signatures on the textured noisy background Slide24:  BACKUP CORPRAL Errors:  CORPRAL Errors NEED ATTENTION-DRIVEN VERIFICATION OF PRE-ATTENTIVE CUES Segment Grouping:  Segment Grouping Interim steps of false positive:  Interim steps of false positive Large number of echo-like structures Texture Analysis:  Texture Analysis Direct analysis of 2D context area (no reduction to edgels) 1D analysis not working Texture Segmentation and Object-from-Texture: Search of objects with similar texture 7x7 25x25 How much can we do pre-attentively?:  How much can we do pre-attentively? IS Technology Infusion Grant:  IS Technology Infusion Grant HSEG = Hierarchical Segmentation Pre-attentive Vision (3):  Pre-attentive Vision (3) Bottom-up analysis Marr’s Pyramid of Perception RHSEG Principles:  RHSEG Principles Bottom-up strategy Combines pixels in groups using their similarity A.k.a. Constrained Region Growing Choice of constraints in RHSEG are yet to be understood Implemented in CORPRAL as a plug-in recognition step Case study 1:  Case study 1 Case Study 1 (cont.):  Case Study 1 (cont.) RAW CORPRAL V1 RHSEG (TBR) Case Study 2:  Case Study 2 RAW RHSEG (TBR) CORPRAL V1 Case Study 3:  Case Study 3 CORPRAL V1 RHSEG Pre-attentive Vision in Cats:  Pre-attentive Vision in Cats Mexican Hat Filter (1D) Kuffler (1950s): study of retina in cats excitatory center inhibitory ring Retina cells convolve image with the Mexican Hat filter. WHY? Could not understand for 30 years inhibitory center excitatory ring TWO TYPES “on-off” “off-on” Pre-attentive Vision in Cats (2):  Pre-attentive Vision in Cats (2) STEP 1. Mexican Hat filter ≈ DOG (Difference of Gaussians) STEP 2. DOG ≈ second derivative of Gaussian (using Laplacian operator ) STEP 3. “On-off” and “off-on” cells are placed next to each other, so that their output maximizes on the edge of intensity where second derivative crosses zero So, single cell blurs image with Gaussian and takes second derivative ZERO-CROSSING EDGE DETECTOR Pre-attentive Vision in ARTIST :  Pre-attentive Vision in ARTIST Second derivative crosses zero = first derivative is max = steepest slope = leading edge of echo Ionogram image is reduced to the “bright spots” of the echo leading edges Edgel Detection (ARTIST & CORPRAL):  Edgel Detection (ARTIST & CORPRAL) Edgel Detection in Dynasonde:  Edgel Detection in Dynasonde Width of echo is lost Attention-driven vision in ARTIST:  Attention-driven vision in ARTIST ARTIST (1982) Top-down considerations (from model to data, looking for image features of known shape) Hough Transform Linear Hyperbolic Arbitrary shape Trained neural networks OCR Top-down model is needed Oriented Edgels:  Oriented Edgels From Wersing (2000), Honda Robot team Pre-attentive Vision in Cats (3):  Pre-attentive Vision in Cats (3) Processing of edgel orientations takes place in the brain Hubel and Wiesel, late 1950s (Nobel Prize result) Smoothing Artifacts:  Smoothing Artifacts Current Edgel Detection:  Current Edgel Detection Classic smoothing+zero crossing No smoothing 1D Radar Echo Detection Sobel… Prewitt… Gabor… AvTrend:  AvTrend 1D Adaptive Thresholder raw all edgels thresholded selected edgels CORPRAL Rating Activity:  CORPRAL Rating Activity < 4% of all RPI data was ever looked at CORPRAL reduces amount of data to look at by at least 80% Venku 1 Bill 1 Robert 1 Alexander 2 Vance 5 Bodo 5 Cindy 12 Patrick 20 Shing 40 Gary 60 Don 62 Marie 63 Ivan 69 Maria 119 Grigori 167 Christopher 477 Qiang 506 CORPRAL V1 97733 Total 97985 Level 2 dataset, rated plasmagrams

Related presentations


Other presentations created by Irvette

Propaganda
29. 12. 2007
0 views

Propaganda

lecture3 yeast
16. 10. 2007
0 views

lecture3 yeast

Giving Bad News
28. 09. 2007
0 views

Giving Bad News

Nutrient Mobility 26
04. 10. 2007
0 views

Nutrient Mobility 26

bad honnef
05. 10. 2007
0 views

bad honnef

olsug 0402 10Hannay Nature
08. 10. 2007
0 views

olsug 0402 10Hannay Nature

Presentation Japan
09. 10. 2007
0 views

Presentation Japan

IRAN and RUSSIA Oil Gas Policies
11. 10. 2007
0 views

IRAN and RUSSIA Oil Gas Policies

present
12. 10. 2007
0 views

present

Presentation Russia
12. 10. 2007
0 views

Presentation Russia

Aula 6
15. 10. 2007
0 views

Aula 6

13 Equine Sciences
19. 10. 2007
0 views

13 Equine Sciences

Panama Canal powerpoint
22. 10. 2007
0 views

Panama Canal powerpoint

Cathia Palmer MI BANCO
22. 10. 2007
0 views

Cathia Palmer MI BANCO

MOROCCO Time Line Power Point
23. 10. 2007
0 views

MOROCCO Time Line Power Point

clim forecast
02. 10. 2007
0 views

clim forecast

5004
10. 12. 2007
0 views

5004

Quake06 template v3
29. 10. 2007
0 views

Quake06 template v3

Hendra
31. 10. 2007
0 views

Hendra

Veschetti PL
01. 11. 2007
0 views

Veschetti PL

imo bw dip con highlights
06. 11. 2007
0 views

imo bw dip con highlights

itt recruitment challenges wales
06. 11. 2007
0 views

itt recruitment challenges wales

showcase
17. 10. 2007
0 views

showcase

fuel tank safety
07. 11. 2007
0 views

fuel tank safety

CClub2 11 08 05 Part 2
19. 11. 2007
0 views

CClub2 11 08 05 Part 2

2006StatsRRTC 3 4
29. 11. 2007
0 views

2006StatsRRTC 3 4

Hospitality Industry Workforce
14. 12. 2007
0 views

Hospitality Industry Workforce

Goff
06. 12. 2007
0 views

Goff

florence1
31. 10. 2007
0 views

florence1

cindy zheng update
17. 10. 2007
0 views

cindy zheng update

Town Hall PowerPoint 6 14 04
18. 10. 2007
0 views

Town Hall PowerPoint 6 14 04

abc5fm
09. 10. 2007
0 views

abc5fm

D Baker RadBelt
30. 10. 2007
0 views

D Baker RadBelt

Thursday
19. 10. 2007
0 views

Thursday

humn presentation
17. 10. 2007
0 views

humn presentation

berkeley04r
28. 11. 2007
0 views

berkeley04r

Hybridmedia in Japan 2005 small
09. 10. 2007
0 views

Hybridmedia in Japan 2005 small

osipenko
15. 10. 2007
0 views

osipenko

Henry VIIIs Problems
05. 10. 2007
0 views

Henry VIIIs Problems

NWAV 2007
31. 10. 2007
0 views

NWAV 2007

Rhetoric AmerDream ppt
19. 02. 2008
0 views

Rhetoric AmerDream ppt

AW12
29. 10. 2007
0 views

AW12

Small Arms Marking Overview
26. 02. 2008
0 views

Small Arms Marking Overview

HazeConsult 032207
05. 10. 2007
0 views

HazeConsult 032207

09 EMI
05. 11. 2007
0 views

09 EMI

class10 22
28. 02. 2008
0 views

class10 22

L17 PT2 Splicing1
15. 10. 2007
0 views

L17 PT2 Splicing1

ES110 Hazardous Waste
10. 03. 2008
0 views

ES110 Hazardous Waste

003 Glenn Jerome
16. 03. 2008
0 views

003 Glenn Jerome

explorer
25. 03. 2008
0 views

explorer

Lect 10A Tides
03. 04. 2008
0 views

Lect 10A Tides

chap19
08. 04. 2008
0 views

chap19

leb shaw
13. 04. 2008
0 views

leb shaw

gelisim 1
16. 10. 2007
0 views

gelisim 1

rm2 lautanala
19. 10. 2007
0 views

rm2 lautanala

Kickoff Poster Italy 1
31. 10. 2007
0 views

Kickoff Poster Italy 1

Collateral Damage 9 27 06
22. 04. 2008
0 views

Collateral Damage 9 27 06

Food show Big
05. 01. 2008
0 views

Food show Big

B1 U10 A
06. 05. 2008
0 views

B1 U10 A

EC2004 ch10
07. 05. 2008
0 views

EC2004 ch10

Home Hemo dialysis Presentation
07. 05. 2008
0 views

Home Hemo dialysis Presentation

CBMB discrimination
08. 05. 2008
0 views

CBMB discrimination

Youth Program Presentation
08. 05. 2008
0 views

Youth Program Presentation

5 Hall evidence based medicine
08. 05. 2008
0 views

5 Hall evidence based medicine

Remote Learning VATAT
02. 05. 2008
0 views

Remote Learning VATAT

Heart Reports
02. 05. 2008
0 views

Heart Reports

CDC033 Presentation
02. 05. 2008
0 views

CDC033 Presentation

ProviderFraudTrainin gPartII
02. 05. 2008
0 views

ProviderFraudTrainin gPartII

TEXPEC ACP program
02. 05. 2008
0 views

TEXPEC ACP program

Presentation30
11. 10. 2007
0 views

Presentation30

raceway Jarnigan
12. 10. 2007
0 views

raceway Jarnigan

Presentation MAROC 10 2006
24. 10. 2007
0 views

Presentation MAROC 10 2006

MoscowPres2fin GK 220207
26. 10. 2007
0 views

MoscowPres2fin GK 220207

131
18. 04. 2008
0 views

131

Boeing2003
24. 10. 2007
0 views

Boeing2003

morocco1105
24. 10. 2007
0 views

morocco1105

Linux101
02. 11. 2007
0 views

Linux101

Airspace needs
09. 10. 2007
0 views

Airspace needs

JackieWilliamson Sabah
13. 03. 2008
0 views

JackieWilliamson Sabah

WVEB NCSM
08. 10. 2008
0 views

WVEB NCSM

Presentacion AIDS Helder Mario
28. 12. 2007
0 views

Presentacion AIDS Helder Mario

PURI SCAG Presentation 111601 1
10. 04. 2008
0 views

PURI SCAG Presentation 111601 1

EQ OEM Presentation Nov04
02. 05. 2008
0 views

EQ OEM Presentation Nov04

Mr Anup Banerji ppt to CII
11. 12. 2007
0 views

Mr Anup Banerji ppt to CII

AdrianaMaria2
24. 10. 2007
0 views

AdrianaMaria2

El mundo del espectaculo2
02. 11. 2007
0 views

El mundo del espectaculo2

ECS2006PresentationGB
15. 10. 2007
0 views

ECS2006PresentationGB

SURF X4L
12. 10. 2007
0 views

SURF X4L

Schulte
06. 03. 2008
0 views

Schulte

Valtio luennot
20. 11. 2007
0 views

Valtio luennot

trw vortrag 18 03 04
16. 11. 2007
0 views

trw vortrag 18 03 04

GA GTIPGTEJones2
03. 10. 2007
0 views

GA GTIPGTEJones2

interim03
10. 10. 2007
0 views

interim03

haulintr
27. 02. 2008
0 views

haulintr

pandrangi
29. 09. 2007
0 views

pandrangi

Disz
01. 05. 2008
0 views

Disz

ETW2005SeminarVIII
23. 10. 2007
0 views

ETW2005SeminarVIII

edpre040505
07. 10. 2007
0 views

edpre040505

sensor mama
03. 10. 2007
0 views

sensor mama

2nd European GIC
07. 01. 2008
0 views

2nd European GIC