Grant Schindler Gatech Frank Dellaert Gatech Sing Bing Kang MSR Redmond Outline Problem Definition Algorithm Overview Applications Things to think about What can be done with n images What can be done with n images ID: 777245
Download The PPT/PDF document "Inferring Temporal Order of Images from ..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Inferring Temporal Order of Images from 3D Structure
Grant Schindler Gatech
Frank Dellaert Gatech
Sing Bing Kang MSR, Redmond
Slide2Outline
Problem Definition
Algorithm Overview
Applications
Things to think about
Slide3What can be done with n images?
Slide4What can be done with n images?
Feature Extraction
Correspondence
Structure from Motion
What Now?
Slide5Temporal Ordering and 4D Walkthrough
1920
1951
1966
2003
Slide6Outline
Problem Definition
Algorithm Overview
Applications
Things to think about
Slide7SFM tells us:
Camera Matrices
3D points for features
Visibility of 3D points in images
C2
F3
C1
I1
I2
F1
F2
Slide8SFM info
Image 1 (I1)
Image 2 (I2)
F1
Visible
???
F2
???
Visible
F3
Visible
???
C2
F3
C1
I1
I2
F1
F2
Slide9SFM info
Image 1 (I1)
Image 2 (I2)
F1
Visible
???
F2
Occluded
Visible
F3
Visible
Out
of View
C2
F3
C1
I1
I2
F1
F2
Slide10SFM info
Image 1 (I1)
Image 2 (I2)
F1
Visible
???
F2
Occluded
Visible
F3
Visible
Out
of View
Notion of missing at that time
C2
F3
C1
I1
I2
F1
F2
Slide11Classification of 3D point for an Image
Visible
– SFM tells us
Out of View
– Camera Matrix tells us
Missing / Occluded
- ???
for an occluded point, there must be an occluder
Slide12Point ‘F’ Missing / Occluded ?
Find out occluders
3D Triangulation of all visible points
No occluder should occlude a visible point
Visibility check for F
occluders
F1
F2
Camera centre
occluded
missing
Slide13Visibility Matrix
I1
I2
...
In
F
1
S
11
S
12
…S1n
F2S21
S22…
S2n…
…
…
…
…
F
m
S
m1
S
m2
…
S
mn
S
ij
€
{visible, occluded, missing, out of view }
Slide14Constraints of Visibility Matrix
Slide15Combinatorial Algorithm to find Best Configuration
Local search method
Starts at a random configuration
Small moves which reduce the number of constraints violated
Slide16Issues leading to Finding
Approximate Solution
Problems in feature detection
Mislabeling of points
Triangulation strategy
Inaccuracy in SFM
Features occluded by undetected occluders (fog, trees etc)
Slide17Structural Segmentation from Temporal Ordering
Clustering temporally coherent features
Separate triangulation of each cluster
Texture by projecting on images
Slide18Algorithm Overview
Slide19Possible Applications
Historic Preservation
Virtual Tourism
Urban Planning
Spatio-Temporal models as a new way
to
interact
with a vast collection of imagery
Slide20Things to Think about
Feature extraction (done manually here)
Better methods for finding occluders – problems with triangulation method
Very coarse structure
Can have triangles for no occluders
Using Goesele’s work (ICCV 2007) for structural segmentation
High number of images required (this paper used 20-30 images)
Validation
Correspondence between the best ground truth solution and best approximate solution of ordering
Increasing the scale technically and physically
Slide21An Interesting Insight….
Assume no building can be demolished once it’s built
Assume every image is a node of graph
Edge from A to B if A precedes B
(B has visible features missing in A )
Directed Graph (acyclic in ideal case)
Slide22C
A
B
Directed Graph (Acyclic in ideal case)
B1
B2
B3
B2
B2
B3
A
B
C
Input Images
Slide23C
A
B
Directed Graph (Acyclic in ideal case)
B1
B2
B3
B2
B2
B3
A
B
C
Input Images
B
C
A
Topological Sort
Solution !
Slide24More insights about Graph Model
Every edge has a confidence value based on quality of features and SFM procedure
In general, there can be back edges in this graph
Problem to find the best topological sort maximizing the confidence measure
Slide25Graph Complexity
Increases with more constraints
Modeling constraints involving more than 2 images at a time -
how??