Intensity and Edge-Based Symmetry Detection
Applied to Car-Following *
Thomas Zielke, Michael Brauckmann, and Werner yon Seelen
Instltut ffir Neurolnformatik, ltuhr-UniversitKt, 4630 Boehum, Germany.
Abstract. We present two methods for detecting symmetry in images,
one based directly on the intensity values and another one based on a dis-
crete representation of local orientation. A
s~lmmetr~l finder
has been devel-
oped which uses the intensity-based method to search an image for compact
regions which display some degree of mirror symmetry due to intensity sim-
ilarities across a straight axis. In a different approach, we look at symmetry
as a bilateral relationship between local orientations. A
s~mmet~y-enl~ancing
edge detector is
presented which indicates edges dependent on the orienta-
tions at two different image positions. SEED, as we call it, is a detector
element implemented by a feedforward network that holds the symmetry
conditions. We use SEED to find the contours of symmetric objects of which
we know the axis of symmetry from the intensity-based symmetry finder.
The methods presented have been applied to the problem of visually guided
car-foilowing. Real-time experiments with a system for automatic headway
control on motorways have been successful.
1 Introduction
Our interest in symmetry detection originates from the problem of car-following by Com-
puter Vision, i.e. the problem of how an automobile equipped with a camera and control
computers can be programmed to automatically keep a safe driving distance to a car in
front. There are three major visual tasks the system has to cope with:
i. Detecting leading cars. This means repeated visual scanning of the road in front of
the car until an object appears which can be identified as another vehicle.
2. Visual tracking of a car's rear while its image position and size may vary greatly.
3. Accurate measuring of the car's dynamic image size needed for the speed control.
The methods presented here exploit the symmetry property of the rear view of most
vehicles on normal roads. Mirror symmetry with respect to a vertical axis is one of the
most striking generic shape features available for object recognition in a car-following
situation. Initially, we use an intensity-based symmetry finder to detect image regions that
are candidates for a leading car. The vertical axis of symmetry obtained from this step
is also an excellent feature for measuring the leading car's relative lateral displacement
in consecutive images because it is invariant under (vertical)
nodding
movements of the
camera and under changes of object size. To exactly measure the image size of the car
in front, a novel edge detector has been developed which enhances edges that have a
symmetric counterpart with respect to a given axis.
* This work has been supported by the German Federal Ministry of Research and Technology
(BMFT) and by the Volkswagen AG (VW). PROMETHEUS PRO-ART Project: ITM8900/2
Lecture Notes in Computer Science, Vol. 588
G. Sandini (Ed.)
Computer Vision - ECCV '92
9 Springer-Verlag Berlin Heidelberg 1992