homographies image mosaics and tracking
Download
Skip this Video
Download Presentation
Assignment 1

Loading in 2 Seconds...

play fullscreen
1 / 35

Assignment 1 - PowerPoint PPT Presentation


  • 153 Views
  • Uploaded on

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

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 ' Assignment 1' - marcel


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
homographies image mosaics and tracking
Homographies,

Image Mosaics and Tracking

Assignment 1

key parts

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: Image Mosaics
  • + + … + =

Goal: Stitch together several images into a seamless composite

image warping
Image Warping
  • 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))?
  • What about holes?

h(x)

x

x’

f(x)

g(x’)

forward warping
Forward Warping
  • Send each pixel f(x) to its corresponding location x’=h(x) in g(x’)
  • What if pixel lands “between” two pixels?
  • Answer: add “contribution” to several pixels, normalize later (splatting)

h(x)

x

x’

f(x)

g(x’)

inverse warping
Inverse Warping
  • 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’)

inverse warping1
Inverse Warping
  • 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’)

interpolation
Interpolation
  • Possible interpolation filters:
    • nearest neighbor
    • bilinear
    • bicubic (interpolating)
nn issues

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
nn aliasing
NN aliasing

rotate 45±, scale 1.5

blending

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

bilinear interpolation bli

Vertical blend

Horizontal blend

  • Idea: Blend four pixel values surrounding source, weighted by nearness
  • (see MO chapter 5)
Bilinear Interpolation (BLI)
assembling the panorama
Assembling the panorama
  • Stitch pairs together, blend, then crop
image compositing issues

With homography computed, how to render combined image?

  • 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
Image feathering
  • 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)
good window size

0

1

Good window size
  • “Optimal” window: smooth but not ghosted
    • Doesn’t always work...
bilinear compositing

Idea: Use “hat” function w 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 coding
Mosaics for Video Coding????
  • Convert masked images into a background sprite for content-based coding
  • + + +

=

recognizing panoramas
Recognizing Panoramas

[Brown & Lowe, ICCV’03]

ad