detecting & modeling change in time-varying...

49
Detecting & Modeling Change in Time-Varying Imagery Peggy Agouris Dept. of Spatial Information Engineering University of Maine

Upload: others

Post on 04-Oct-2020

5 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Detecting & Modeling Change in

Time-Varying Imagery

Peggy Agouris

Dept. of Spatial Information Engineering University of Maine

Page 2: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Overview

Problem(s)

Change Detection in Time-Varying Aerial Imagery

Tracking Positional Change and Modeling Spatiotemporal Behavior in Motion Imagery (incl. Video Sequences)

Examples

Page 3: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Problem

Change detection: one component of successful conflation of geospatial information

Page 4: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Integrated Environment

Translation onto new image

Object shape information (from GIS)

Shape accuracy estimates (from GIS)

Differential Snakes

Change detection

Versioning

GIS Updating

Page 5: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Traditional Snakes

Semi-automatic tool for object extraction

Based on the optimization of a model of

curve contrast and smoothness using

content-derived forces and an elastodynamic

model

Page 6: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

edgecurvcontsnake EEEE ⋅+⋅+⋅= γβα

)( iedge vIE −∇=

211 2 +− +−= iiicurv vvvE

1−−−= iicont vvdE

Traditional Snakes Model

Total energy:

Continuity term:

Curvature term:

Edge term:

Page 7: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Optimization

Greedy algorithm : current point location is optimized, while previous and next points are fixed Stop criteria : number of points moved, change of total energy

vi

vi+1vi-1

Page 8: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Quality Evaluation of Extracted Road Network

Need a posteriori evaluation of object extractionResults are useful input for spatiotemporal change detectionAssumption: known energy function valuesFor sample points along an extracted object, values of uncertainty are generated using fuzzy rules

Page 9: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Quality Evaluation Rules

High Medium Low

Low High Low Low

High High Medium High

DEE

Points of interest are determined based on statistical properties of energy

Fuzzy rules of the form :

• If Et is LOW and DEt is LOW then U is LOW

Page 10: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

d

Fin

Fout

vi

v0i

uncedgecurvcontsnake EEEEE ⋅+⋅+⋅+⋅= δγβα

Additional energy term (uncertainty)

Action is similar to an elastic spring force

Differential Snake Model

Page 11: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Uncertainty Energy

dvUncD

Eii

unc ⋅⋅

=)0(

1

dDi

1/Unc(v0i)

0

Eunc

Page 12: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Change Detection vs. Versioning

Change is detected if a road segment has moved beyond the stochastic range of older information

Versioning identifies road segments that can be delineated in the new image with better accuracy than their current database record

Page 13: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Example

Prior (red) and current (blue) road shape information

Page 14: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Change Detection & Versioning Experiments

Buffer zones of influence of prior

information

Result of change detection (blue line)

Result of versioning (purple line)

Page 15: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Change Detection & Versioning Experiments (cont.)

Prior and current road shape information

Buffer zones of influence of prior

information

After change detection (blue)

and versioning (purple)

1

2

3

4

5

6

1

2

3

4

5

6

Page 16: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Differential Snakes GUI (Change Detection & Versioning)

QuickTime™ and aMicrosoft Video 1 decompressorare needed to see this picture.

Page 17: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Performance and Accuracy Issues

Typical Performance Metrics

Average values for a road segment spanning

a 512x512 image window:

• Change Detection: 2.095 sec

• Versioning: 0.561 sec

Page 18: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Change Detection for

Closed Contour Objects

Important tool for dynamic scene analysis

Applications: surveillance, environmental, transportation, biomedical, etc.

Quick and efficient, requires proper initialization, assumes frequent monitoring (small movement of object between frames)

Page 19: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Differential Snakes for Tracking Object Contours

Extracted Object Contour from

Previous Frame

New Frame Information

Differential Snakes

New Object Contour

Page 20: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Estimation of Translation and Rotation

Translation: difference of positions of two geometric centersRotation: difference of direction of principal axes

Δϕ

Page 21: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Estimation of Uniform Expansion

Ratio of areas = (ratio of perimeters)2

Page 22: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Estimation of Radial Deformation

Use of polygon clipping techniques: - calculate the intersections between two input polygons- label edges as inside, outside, or shared- find the minimal polygons which are created by intersection- classify all minimal polygons into the output sets A∩B, A/B, and A\B

Page 23: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Experiments with Moving Objects

Track changes in the shape of an object

Example: a liquid that deforms non-uniformly

We show five distinct frames and the detected

change between them (frames n, n+1)

Area threshold to ignore small polygon changes

Integration of spatiotemporal tracking process in

a GUI (in Matlab)

Page 24: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Experiment with a Moving Object

100 150 200 250 300 350 400 450 500

100

150

200

250

300

350

400100 150 200 250 300 350 400 450 500

100

150

200

250

300

350

400100 150 200 250 300 350 400 450 500

100

150

200

250

300

350

400100 150 200 250 300 350 400 450 500

100

150

200

250

300

350

400

Page 25: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

GUI for Spatiotemporal Change Detection

QuickTime™ and aMicrosoft Video 1 decompressorare needed to see this picture.

Page 26: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Remarks

Integration of object extraction and change detection

Introduction of uncertainty as external energy in a deformable modelChange detection using the uncertainty of the extraction

Framework for spatiotemporal tracking of object deformations

Estimate translation, rotation, radial deformations using geometric properties

Page 27: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Positional Change Detection & Modeling

in Motion Imagery

Page 28: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Problem

Detecting change in position and shape/extent of objects or events across time and space Modeling their spatiotemporal behavior

Page 29: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Trends in imagery collection: from static to motion and from single to multiple sensors.

Tremendous amounts of data.

Bottleneck in the analyst workforce.

Rationale

Page 30: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Automated motion imagery analysis solutions

Automation at various levels of the analysisprocess:

automated identification of trajectories in single video feeds (i.e. tracking positional change over time)automated content analysis to identify interesting spatiotemporal activities and support queries

Needs

Page 31: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Motion Trajectory Identification

Nodal Representation of Trajectories

Spatiotemporal Helix Modeling

Essential Issues

Page 32: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

QuickTime™ and aMPEG-4 Video decompressor

are needed to see this picture.

Page 33: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

0

200

400

801001201401601802002202400

10

20

30

40

50

60

70

80

90

x (column pixels)

1

3

2

55

1

3

2

5

2

3

1

5

2

5

3

5

1

3

7

2

5

1

7

3

5

2

6

7

1

3

4

2

6

1

7

3

4

2

6

8

3

4

1

2

6

8

3

4

6

2

1

8

3

4

6

2

1

Moving Object Trajectories

8

3

4

6

2

1

4

2

y (row pixels)

6

1

66

6

fram

e (t

ime)

Page 34: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Modeling Spatiotemporal Change

Over time objects/events may change their:

location (movement)

outline (deformation)

Need:

an integrated representation of movement

and deformation

Page 35: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Trajectories of moving objects:

3-d collections of points evolving through S-T space

•Generalization

•Summarization

•Behavior Analysis

QuickTime™ and a decompressor

are needed to see this picture.

QuickTime™ and a decompressor

are needed to see this picture.QuickTime™ and a

decompressorare needed to see this picture.

QuickTime™ and a decompressor

are needed to see this picture.

Moving Objects in the SpatioTemporal Domain

YUV420 codec decompressorare needed to see this picture.

YUV420 codec decompressorare needed to see this picture.

Page 36: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

x

y

t

x

y

t

Summarization

Page 37: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

The SpatioTemporal HelixAn integrated representation of movement and

deformation, and

A signature of an object’s spatiotemporal behavior.

Comprises a spine and prongsSpine models trajectory• Nodes: acceleration, deceleration, rotation

Prongs express deformation• Changes of a predefined magnitude• Recorded as time, percent change, azimuth

Page 38: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Helix RepresentationSpine:Spine: expresses spatioexpresses spatio--

temporal 3temporal 3--D movement of D movement of

the center of mass.the center of mass.

Prongs:Prongs: express expansion or express expansion or

collapse of the objectcollapse of the object’’s outline s outline

Page 39: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

The Helix as a Spatiotemporal Database Index

Helixobjidt1,t2={node1,…noden; prong1,..prongm}

•• Node:Node: nnii(x,y,t,q(x,y,t,q))

•• Prong: Prong: ppjj(t,r,a(t,r,a11,a,a22))

Page 40: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Collecting Spine & Prong Information

Two novel image analysis techniques:

SOM with geometric analysis (g-SOM)•Describes ST trajectory of center of mass

Differential snakes•Allows calculation of percent change in

outline

Page 41: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

QuickTime™ and aMicrosoft Video 1 decompressorare needed to see this picture.

Page 42: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Generalization

Page 43: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Hurricane Frances

Page 44: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Hurricane Charley

Page 45: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Hurricane Helixes

Page 46: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Hurricane Helixes: Charlie

QuickTime™ and aCinepak decompressor

are needed to see this picture.

QuickTime™ and aCinepak decompressor

are needed to see this picture.

Page 47: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Hurricane Helixes: Frances

QuickTime™ and aCinepak decompressor

are needed to see this picture.

QuickTime™ and aCinepak decompressor

are needed to see this picture.

Page 48: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

Concluding Remarks

Incorporating uncertainty in change detection improves conflation and eliminates false positivesDetection of positional and shape change in motion imagery contributes to a better understanding of behavior of evolving events

Page 49: Detecting & Modeling Change in Time-Varying Imageryncgia.ucsb.edu/projects/nga/docs/pdf/agouris.pdfOverview Problem(s) Change Detection in Time-Varying Aerial Imagery Tracking Positional

For more information:

Peggy AgourisAnthony Stefanidis

{peggy, tony}@spatial.maine.edu

http://dipa.spatial.maine.edu