Structure
from Motion - Two Frames and Multiple Frames
|
|
Structure from motion is
a technique that attempts to reconstruct the 3D
structure of a scene from a sequence of images
taken from a camera moving within the scene.
Structure from motion can be used on an Unmanned
Aerial Vehicle or Unmanned Ground Vehicle for
obstacle detection as well as for path-planning
and navigation. The 3D structure of the scene is
estimated using the optical flow values found at a
set of feature points on the image.
We developed a novel multi-frame structure from
motion algorithm in which the camera motion and
object structure are calculated from optical flow
probability distributions instead of a single
optical flow estimate at each feature point.
Optical flow distributions of the selected feature
points allow us to quantify the accuracy of the
optical flow estimate in any direction. With
this additional knowledge, a more accurate
structure from motion algorithm is created which
relies more heavily on the more accurate optical
flow data. This novel method is designed to
use the optical flow values taken from multiple
frames of video or an image sequence. It is
an optimal solution to the structure from motion
problem with respect to a chosen norm. We
demonstrated that this new method performs
significantly better than similar methods which do
not use optical flow distributions or do not use
multiple frames.
|
Graduate Students:
|
Paul Merrell and Zhaoyi Wei
|
Publications:
-
D.J. Lee, P.C. Merrell, Z.Y. Wei, and B.E.
Nelson, “Two-Frame Structure from Motion
Using Optical Flow Probability Distributions
for Unmanned Air Vehicle Obstacle Avoidance,”
Machine Vision and Applications Journal, vol.
21/3, p. 229-240, April 2010.
-
D.J.
Lee, P.C. Merrell, B.E. Nelson, and
Z.Y. Wei, “Multi-Frame Structure from
Motion using Optical Flow Probability
Distributions,” Journal of
Neurocomputing, vol. 72/4-6, p. 1032-1041,
January 2009.
-
P.C.
Merrell and D.J. Lee, ”Structure from
Motion Using Optical Flow Probability
Distributions”, SPIE International
Symposium on Defense and Security, Intelligent
Computing: Theory and Applications III, vol.
5803-6, p. 39-48, Orlando, Florida, USA, March
28-April 1, 2005.
-
P. Merrell, D.J. Lee, and R.W. Beard, “Statistical
Analysis of Multiple Optical Flow Values for
Estimation of Unmanned Air Vehicles Height
Above Ground”, SPIE Optics East,
Robotics Technologies and Architectures,
Intelligent Robots and Computer Vision XXII,
vol. 5608, p. 298-305, Philadelphia, PA, USA,
October 25-28, 2004.
|
(Click
image to view pictures and video)
|
|
|