Robust localization classification and temporal evolution tracking in auroral data
Download
1 / 23

Robust Localization, Classification, and Temporal Evolution Tracking in Auroral Data - PowerPoint PPT Presentation


  • 63 Views
  • Uploaded on

Robust Localization, Classification, and Temporal Evolution Tracking in Auroral Data. G. Germany * C.C. Hung † T. Newman * J. Spann ‡ * Univ. of Alabama in Huntsville † S. Polytechnic State Univ. ‡ MSFC. AISR Meeting, April 4-6, 2005. Visual Perception I. What do you see?.

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about ' Robust Localization, Classification, and Temporal Evolution Tracking in Auroral Data' - mayes


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
Robust localization classification and temporal evolution tracking in auroral data

Robust Localization, Classification, and Temporal Evolution Tracking in Auroral Data

G. Germany * C.C. Hung †

T. Newman * J. Spann ‡

* Univ. of Alabama in Huntsville

† S. Polytechnic State Univ.

‡ MSFC

AISR Meeting, April 4-6, 2005


Visual perception i
Visual Perception I Tracking in Auroral Data

  • What do you see?

from Torrans 99 (GMU)

from Schiffman’s Sensation and Perception, 2000,

as presented by Loken et al., Macalester Coll.


Visual perception i1
Visual Perception I Tracking in Auroral Data

  • What do you see?

from Torrans 99 (GMU)

from Schiffman’s Sensation and Perception, 2000,

as presented by Loken et al., Macalester Coll.

Gestalt = Form, a unit of perception

Note: Avoid strict Gestaltism!


Visual perception ii some gestalt
Visual Perception II: Some Gestalt Tracking in Auroral Data

  • Continuity

  • Closure

  • Proximity

  • Similarity

H ppy Birthday

EEEEEEEEEEFEEEEEEEEEE


A problem finding auroral oval
A Problem: Finding Auroral Oval Tracking in Auroral Data

UVI Image

Region-Based Seg.


A problem finding auroral oval1
A Problem: Finding Auroral Oval Tracking in Auroral Data

UVI Image

Region-Based Seg.

* Incomplete


Toward a better solution
Toward a Better Solution? Tracking in Auroral Data

  • Exploit:

    • Continuity

    • Closure

    • Proximity

    • Similarity


Toward a better solution1
Toward a Better Solution? Tracking in Auroral Data

  • Exploit:

    • Continuity

    • Closure

    • Proximity

    • Similarity


General goal support study of aurora
General Goal: Support Study of Aurora Tracking in Auroral Data

  • UVI Polar Datasets

    • 9M+ images!

      • Exploitation Challenge

    • OST (Germany Talk @ AISR05)

      • Queries based on:

        • Sensor Location

        • Some Image Features:

          • Integrated Intensity

          • Boundary Position

          • Image Quality

      • Popular:

        • 1000/100


Specific goal effective retrieval
Specific Goal: Effective Retrieval Tracking in Auroral Data

  • UVI OST: Mining Pre-Processing

    • Removes Non-Auroral Features

    • Extracts Auroral Oval

      • Inefficient

      • Often fails

  • Support Auroral Feature Search

    • Shape-Based Processing to Localize Oval

    • Better-support Auroral Feature Retrieval


Shape recovery
Shape Recovery Tracking in Auroral Data

  • Our prior work:

    • Spheres

    • Cylinders

    • Cones

    • Ellipsoids

    • Paraboloids

    • Hyperboloids

    • Compound Structures


Exploiting shape i
Exploiting Shape I Tracking in Auroral Data

  • Exploiting Shape: Preliminaries

    • What Shape?

    • Shape Invariant Descriptors


Exploiting shape ii experiments
Exploiting Shape II: Experiments Tracking in Auroral Data

  • Shape Testing

    • Manual Tracing

    • Linear Least Squares Fitting

    • Shape Invariant Extraction


Some fitting results
Some Fitting Results Tracking in Auroral Data

Colorized Image

Manually traced boundary

Fittings

Invar.

∆ = 2E-10

J = 1E-9

I = -8E-5

∆/I < 0

97/011/053422

∆ = 9E-9

J = 2E-8

I = -3E-4

∆/I < 0

97/011/094246


Initial work localization
Initial Work: Localization Tracking in Auroral Data

  • Hough-Based Processing

    • Democratic:

      • Pixels Vote

    • Example

      • y = mx + b

y=px+q

y=ax+c

y=dx+e

y=fx+g

PixelA


Approx auroral oval boundary
Approx. Auroral Oval Boundary Tracking in Auroral Data

  • Thresholding with density examination

    • Thresholding value:  (mean of the pixel intensities)

  • LoG edge detection

99/006/093006

Thresholded image

Dense part

Boundary


Shape based detection
Shape-based Detection Tracking in Auroral Data

  • Mod. Randomized Hough Transf. (MRHT) for ellipse:

    • Randomly Select Eedgels

    • Fit General Quadratic

    • Determine Shape

    • Ellipse Parameter Recovery (next page)

    • Parameter Space Decomposition

      • 2D accumulate array for center

      • 2D accumulate array for axes

      • 1D accumulate array for orientation


Shape based detection cont
Shape-based Detection (cont.) Tracking in Auroral Data

  • MRHT for ellipse

    • Recover:

  • center

orientation

axes

  • where


Shape based detection cont1
Shape-based Detection (cont.) Tracking in Auroral Data

  • Separation of inner and outer boundary

    • Based on distance to center of detected ellipse from boundary pixels

Green = detected ellipse from boundary pixels. Red = inner boundary. Blue = outer boundary

99/006/093006


Shape based detection cont2
Shape-based Detection (cont.) Tracking in Auroral Data

  • Shape detection of inner and outer boundary.

99/006/093006

Green = RHT ellipses. Red = Inner. Blue= outer boundaries of the aurora arc.

99/006/070027


More experimental results
More Experimental Results Tracking in Auroral Data

97/011/094246

96/344/233133

97/010/150934

99/006/213123


Experimental configuration
Experimental Configuration Tracking in Auroral Data

  • Machine:

    • CPU: 2.3 GHz

    • Memory: 512 MB

    • OS: Windows XP

  • Run time (wall clock)

    • 3 MRHT runs each with 100,000 fittings

      • One run for center estimation, two runs for inner and outer boundary detection

    •  45 seconds for each image


Conclusion
Conclusion Tracking in Auroral Data

  • Shape-Based Fitting

    • Goal: Better-Localizing Auroral Oval

    • Upcoming:

      • Couple w/ k-means (Hung and Germany, 2003)

      • Longer Term:

        • Auroral Classification

        • Temporal Evolution Tracking


ad