1 / 35

# Assignment 1 - PowerPoint PPT Presentation

Homographies , Image Mosaics and Tracking. Assignment 1. Homography estimation from corresponding points Homographies describe image transformation of... General scene when camera motion is rotation about camera center Planar surfaces under general camera motion

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

## PowerPoint Slideshow about ' Assignment 1' - marcel

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

Image Mosaics and Tracking

### Assignment 1

• Homography estimation from corresponding points

• Homographies describe image transformation of...

• General scene when camera motion is rotation about camera center

• Planar surfaces under general camera motion

• Displaying tracking data on a map

• Image mosaic / stitch and Texture mapping

• Bilinear interpolation

• Image compositing

• Wii (optional)

Key Parts

Goal: Image Mosaics

• + + … + =

Goal: Stitch together several images into a seamless composite

• Given a coordinate transform x’ = h(x) and a source image f(x), how do we compute a transformed image g(x’)=f(h(x))?

h(x)

x

x’

f(x)

g(x’)

• Send each pixel f(x) to its corresponding location x’=h(x) in g(x’)

• What if pixel lands “between” two pixels?

h(x)

x

x’

f(x)

g(x’)

• Get each pixel g(x’) from its corresponding location x’=h(x) in f(x)

• What if pixel comes from “between” two pixels?

h(x)

x

x’

f(x)

g(x’)

• Get each pixel g(x’) from its corresponding location x’=h(x) in f(x)

• What if pixel comes from “between” two pixels?

• Answer: resample color value from interpolated (prefiltered) source image

x

x’

f(x)

g(x’)

• Possible interpolation filters:

• nearest neighbor

• bilinear

• bicubic (interpolating)

Nearest neighbor interpolation (NN)

Problem is that it can cause big aliasing effects

Why? Because the round() function causes discontinuous switches in which pixel is nearest and hence is the color drawn

NN issues

rotate 45±, scale 1.5

t controls “blend”

of two endpoints

• From parametric definition of a line segment:

p(t) = p0 + t(p1 ¡ p0), wheret2[0, 1]

= p0¡tp0 + tp1

= (1 ¡ t)p0 + tp1

Blending

from Akenine-Möller & Haines

Horizontal blend

• Idea: Blend four pixel values surrounding source, weighted by nearness

• (see MO chapter 5)

Bilinear Interpolation (BLI)

Bilinear interpolation

rotate 45±, scale 1.5

Pixel Interpolation approaches: artifactsNN vs. BLI

Pixel Interpolation approaches: artifactsNN vs. BLI

Image Stitching artifacts

Assembling the panorama artifacts

• Stitch pairs together, blend, then crop

• With homography computed, how to render combined image? artifacts

• Simply putting one image on top of the other, even with bilinear interpolation, may result in a “seam” due to different brightness levels

• Auto-iris can change overall lightness of images

• Vignetting can make image edges darker

Image Compositing Issues

courtesy of P. Haeberli

Image feathering artifacts

• Weight each image proportional to its distance from the edge (distance map [Danielsson, CVGIP 1980]

• 1. Generate weight map for each image

• 2. Sum up all of the weights and divide by sum:weights sum up to 1: wi’ = wi / ( ∑iwi)

Image Feathering artifacts

+ artifacts

=

1

0

1

0

Feathering

0 artifacts

1

0

1

Effect of window size

left

right

0 artifacts

1

0

1

Effect of window size

0 artifacts

1

Good window size

• “Optimal” window: smooth but not ghosted

• Doesn’t always work...

• Idea: Use “hat” function artifactsw indicating weight of contributions of an image to the mosaic

• w is 1 at source image center, falls linearly to 0 at image boundaries

• Combination of horizontal and vertical hat functions:

• Normalize hat weights to get blend factor in overlaping area:

Bilinear Compositing

Mosaics for Video artifactsCoding????

• Convert masked images into a background sprite for content-based coding

• + + +

=

Recognizing Panoramas artifacts

[Brown & Lowe, ICCV’03]