Vision: Scene Labelling

1
Vision Scene Labelling
Structure in the world allows us to interpret
complex situations by propagating
constraints. This is conveniently demonstrated
in computer vision, using a technique known as
Guzman labelling.
2
Blocks-World Vision Problem
Given A 2-D line drawing representing a
collection of polyhedral blocks on a
table. Determine Which faces (bounded regions
in the drawing) go together as parts of the same
objects. Which edges (line segments) are
internal to objects and which are occluding
edges.
3
Example Scene Analysis Problem
4
Guzmans Vertex Labels
Ell Arrow Fork Tee Arrow There is an
angle of more than 180 deg. Fork Each of the 3
angles is of less than 180 deg. Tee There is
one angle of exactly 180 deg., and 2 smaller ones.
5
Guzmans Labelling Technique
1. Classify each vertex into one of the
categories ell, arrow, fork, tee, or other. 2.
At each vertex, mark each incoming edge according
to the role it plays at the vertex (e.g., shank
of an arrow, stem of a tee). 3. Create single
links between neighboring regions each time
a. they are divided by a line segment at a fork,
b. they are divided by the shank of an arrow,
c. they are in corresponding positions of a
configuration of two opposing tees with colinear
stems. 4. Create a node for each region.
Whenever two regions are doubly linked, connect
their nodes with a same object link.
6
Example with Vertex Labels
L
L
A
A
A
T
T
F
L
T
A
T
F
T
L
L
L
A
A
7
Example with Region Links
8
Example with Object Links
9
Example with Internal and Occluding Edges
Identified
internal
occluding
10
Discussion
The work of Guzman was refined by D. Huffman, M.
Clowes, and D. Waltz to take into account
additional kinds of edges, including crack edges,
oriented occluding edges, and concave and convex
internal edges. A key point of this research was
to show that constraints imposed by the real
world could make seemingly intractable
combinatorial interpretation problems actually
solvable.