3D Reconstruction from Two 2D Images Ted Shultz and Luis A. Rodriguez

Download Report

Transcript 3D Reconstruction from Two 2D Images Ted Shultz and Luis A. Rodriguez

3D Reconstruction from Two
2D Images
Ted Shultz and Luis A. Rodriguez
ECE 533 – Image Processing
Fall 2003
Goal
Develop an algorithm to reconstruct a 3D
world scene from two static 2D images
Approach
• Acquire digital images
• Match up corresponding
points in both images
• Estimate a depth mask
• Generate an image from a
new view.
Camera
Left Image
Camera
Right Image
Original left image of room
Original right image of room
Depth mask overlaid on left image
to show depth of various objects
Left image with dots
showing 150
locations that were
found in both images
Depth mask made
from two images
(brighter is closer)
10 frames from included “Room
Slide.mov” file.
Original left image of Computer
Depth mask made from two images
(brighter is closer)
Original right image of Computer
Depth mask overlaid on left image
to show depth of various objects
10 frames from included “Computer
roll.mov” file (animation must be
seen to appreciate)
Movies
Low resolution movies are currently online at:
http://www.cae.wisc.edu/~shultz/movie
High resolution copies are on CD and available by
request
Conclusion
• Movies are convincing
• Masks are not perfect, but adequate to
fool the eye
• Currently manually intensive, point
matching process could be automated.
• Could be modified to incorporate multiple
views.