SLIDE 1
Image Registration and Motion Estimation
Fabio Viola University of Cambridge
The Goal
- Produce mosaics from:
Image Registration and Motion Estimation Fabio Viola University of - - PowerPoint PPT Presentation
Image Registration and Motion Estimation Fabio Viola University of - - PowerPoint PPT Presentation
Image Registration and Motion Estimation Fabio Viola University of Cambridge The Goal Produce mosaics from: Sets of uncalibrated still images Videos What do we need to mosaic images? Image mosaicing integrates information from
SLIDE 2
SLIDE 3
What do we need to mosaic images?
- Image mosaicing integrates information from
different pictures (measurements) into a single support
- In order to merge data from different inputs
we need to register the input frames
SLIDE 4
What is Image Registration?
SLIDE 5
Image Registration In a Nutshell
- “...given two different views of the same scene, for
each image point in one view find the image point in the second view which has the same pre‐image, i.e. corresponds to the same actual point in the scene.”
SLIDE 6
Global transformations
- We know how to model the image formation
process
- This fact allows – under precise hypotheses ‐
for the registration task to be performed inferring global geometrical relations between pairs of input frames
SLIDE 7
Global transformations cont.
- Generalization of these properties have been
exploited to mosaic still images form tunnels, assuming they came from the same ring
- KEY POINT: images are registered locally in
pairs, approximating the captured surfaces as planes
SLIDE 8
Mosaics from videos
SLIDE 9
SLIDE 10
Images from Rav‐Acha,et al, " Minimal Aspect Distorsion (MAD) Mosaicing of Long Scenes"
SLIDE 11
Images from Rav‐Acha,et al, " Minimal Aspect Distorsion (MAD) Mosaicing of Long Scenes"
SLIDE 12
The Challenge
- Exploit the redundant information available in
video to overcome current limitations
– Introduce a global optimization over the whole video to increase coherence of registration (?) – Investigate Manifold Projection methods
- Deal with low quality of video:
– Motion blur due to hand held camera – Bad lighting conditions
SLIDE 13
SLIDE 14
Global Transformations Failures Mosaicing of Shafts
- When there is a lot of 3D structure, or motion,
in the scene simple geometrical global methods fail
- Unfortunately this is the case of Shafts
Imagery
SLIDE 15
SLIDE 16
SLIDE 17
SLIDE 18
The Idea
- Define the Mosaics as a flat representation of
the scene
- Define each frame as a map from the mosaic
to the image plane
- Given the image data learn jointly the
representation and the mapping so that the input frames can be regenerated from the mosaic
SLIDE 19
So, is this Image Registration?
SLIDE 20
Compute motion
- The registration step is performed computing
a dense motion field between the input frames
- Frames could be easily roughly aligned by
hand
- The machine will fill the gap and generate the
mosaic representation
SLIDE 21
SLIDE 22
SLIDE 23
SLIDE 24
SLIDE 25
SLIDE 26
SLIDE 27
SLIDE 28
SLIDE 29
SLIDE 30
Work Ongoing
- We are investigating the motion model and its
learning (tech report available on request)
- We are now going to start coding the
mosaicing of the provided video sequences
- Results and ICCV2009 paper expected by
march
SLIDE 31
Take‐home message
- The different data sets we have been
provided with require different techniques
- The key task to perform is registration