Sunday, July 29, 2012

The tripods are coming!

When I learn that the military want to deploy “tripod operators” I can’t help but think of that brilliant book by H.G. Wells, “War of the Worlds”’. Fortunately, that’s not quite what the Naval Research Laboratory (NRL) is up to.


Their Technology Transfer Office has details of a “tripod operator” technology of interest to those working with vision guided robotics (VGR) and meshing of 3D point clouds. The movie below provides an overview.


Despite viewing the movie a couple of times, I’m still not sure just what a “tripod operator” actually does. It looks almost as though it compares the relative heights of three nearby points and tries to infer something about the geometry.

The write-up says the NRL has a patent on this technology, but I’ve been unable to find it. If anyone out there has more luck perhaps you’d be kind enough to share.

2 comments:

Anonymous said...

http://www.dtic.mil/cgi-bin/GetTRDoc?AD=ADA293983

from the above - "The tripod operator is a class of feature extraction operators for range images which
facilitate the recognition and localization of objects. It consists of three points in 3-space
fixed at the vertices of an equilateral triangle and a procedure for making several scalar
measurements in the coordinate frame of the triangle. The triangle is then moved as a
rigid body until the three vertices lie on the surface of some range image or modeled
object. The resulting measurements are local shape features which are invariant under
rigid motions. These features can be used to automatically find distinctive regions at
which to begin recognition, to rapidly screen candidate objects for a match, and to speed
pruning in the generation of interpretation trees. Tripod operators are applicable to all
3-D shapes, and reduce the need for specialized feature detectors. A key property is that they can be moved on the surface of an object in only three DOF (like a surveyor's tripod
on the ground)."

Anonymous said...

see here
http://www.dtic.mil/cgi-bin/GetTRDoc?AD=ADA293983

"The tripod operator is a class of feature extraction operators for range images which
facilitate the recognition and localization of objects. It consists of three points in 3-space
fixed at the vertices of an equilateral triangle and a procedure for making several scalar
measurements in the coordinate frame of the triangle. The triangle is then moved as a
rigid body until the three vertices lie on the surface of some range image or modeled
object. The resulting measurements are local shape features which are invariant under
rigid motions. These features can be used to automatically find distinctive regions at
which to begin recognition, to rapidly screen candidate objects for a match, and to speed
pruning in the generation of interpretation trees. Tripod operators are applicable to all
3-D shapes, and reduce the need for specialized feature detectors. A key property is that
they can be moved on the surface of an object in only three DOF (like a surveyor's tripod
on the ground). Consequently, only a 3-dimensional manifold of feature space points can
be generated, for any dimensionality of feature vector. Thus, objects can be represented
compactly, and in a form allowing fast matching."