Title:
3D Obstacle Detection Using a Single Camera
3D Obstacle Detection Using a Single Camera
Author(s)
Shah, Syed Irtiza Ali
Johnson, Eric N.
Johnson, Eric N.
Advisor(s)
Editor(s)
Collections
Supplementary to
Permanent Link
Abstract
This paper aims at detecting obstacles using a single camera in an unknown
three dimensional world, for 3D motion of an unmanned air vehicle. Obstacle
detection is a pre-requisite for collision-free motion of a UAV through 3D space.
Most research towards vision based obstacle detection and avoidance has been done
for 2D planar motion of ground robots and using active sensors like laser range
finders, sonar, radar etc. Passive camera based research has mostly been done,
either using stereo vision (multiple cameras) or, by developing a prior expectation
map of the world and its comparison with the new image data. In this paper, an
attempt has been made to find a 3D solution of the obstacle detection problem using
a single camera in an unknown world. The equations developed and the simulations
results presented here, show that a 3D model of the scene can be generated from 2D
image information from a single camera flying through a very small arc of lateral
flight around the object, without the need of capturing images from all sides as in a typical 'structures from motion' problem. The forward flight simulation results
show that the depth extracted from forward motion is in fact usable for large part of
the image, which is a significant contribution of this work.
Sponsor
Date Issued
2009-08
Extent
Resource Type
Text
Resource Subtype
Proceedings