robust localization classification and temporal evolution tracking in auroral data n.
Download
Skip this Video
Download Presentation
Robust Localization, Classification, and Temporal Evolution Tracking in Auroral Data

Loading in 2 Seconds...

play fullscreen
1 / 23

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


  • 64 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


Download Now 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
  • 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
  • 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
  • Continuity
  • Closure
  • Proximity
  • Similarity

H ppy Birthday

EEEEEEEEEEFEEEEEEEEEE

a problem finding auroral oval
A Problem: Finding Auroral Oval

UVI Image

Region-Based Seg.

a problem finding auroral oval1
A Problem: Finding Auroral Oval

UVI Image

Region-Based Seg.

* Incomplete

toward a better solution
Toward a Better Solution?
  • Exploit:
    • Continuity
    • Closure
    • Proximity
    • Similarity
toward a better solution1
Toward a Better Solution?
  • Exploit:
    • Continuity
    • Closure
    • Proximity
    • Similarity
general goal support study of aurora
General Goal: Support Study of Aurora
  • 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
  • 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
  • Our prior work:
    • Spheres
    • Cylinders
    • Cones
    • Ellipsoids
    • Paraboloids
    • Hyperboloids
    • Compound Structures
exploiting shape i
Exploiting Shape I
  • Exploiting Shape: Preliminaries
    • What Shape?
    • Shape Invariant Descriptors
exploiting shape ii experiments
Exploiting Shape II: Experiments
  • Shape Testing
    • Manual Tracing
    • Linear Least Squares Fitting
    • Shape Invariant Extraction
some fitting results
Some Fitting Results

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
  • 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
  • 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
  • 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.)
  • MRHT for ellipse
    • Recover:
  • center

orientation

axes

  • where
shape based detection cont1
Shape-based Detection (cont.)
  • 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.)
  • 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

97/011/094246

96/344/233133

97/010/150934

99/006/213123

experimental configuration
Experimental Configuration
  • 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
  • Shape-Based Fitting
    • Goal: Better-Localizing Auroral Oval
    • Upcoming:
      • Couple w/ k-means (Hung and Germany, 2003)
      • Longer Term:
        • Auroral Classification
        • Temporal Evolution Tracking