<p>IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, VOL. 8, NO. 2, JUNE 2007
Vehicle Classification Based on the Radar
Measurement of Height Profiles
Ildar Urazghildiiev, Rolf Ragnarsson, Pierre Ridderström, Anders Rydberg, Member, IEEE, Eric Öjefors,
Kjell Wallin, Per Enochsson, Magnus Ericson, and Göran Löfqvist
Abstract—The problem of classifying road vehicles according
to vehicle type is considered. The proposed solution is based on
using vehicle height and length and height profiles obtained by a
microwave (MW) radar sensor. We show that if the radar sensor
satisfies certain requirements, then a precise feature vector can be
extracted, and simple deterministic algorithms can be applied to
determine the vehicle class. Field trials using a spread-spectrum
MW radar sensor system operating on these principles have been
carried out. They confirm that accurate classification of a large
number of vehicle classes can be reached.
Index Terms—Classification, feature extraction, height profile,
road vehicles, spread-spectrum radar.
THE PROBLEM of the classification of road vehicles arises
in many areas such as truck volume estimating, traffic
planning, roadway tolling, etc.; see e.g., – and references
therein. To solve this problem, a number of solutions have
been proposed. The known methods of vehicle classification are
based on using such kinds of sensors as pneumatic road tubes,
inductive loops, magnetic sensors, piezoelectric sensors, video
cameras, infrared lasers sensors, microwave (MW) radars, and
ultrasonic sensors –. Any kind of sensor will provide a
specific mechanism of classifying vehicles and has its own ad-
vantages and disadvantages. Since user needs and classification
conditions can differ, no sensors and corresponding techniques
have proven to be the best for all possible applications , .
Therefore, any new classification technique providing specific
advantages can be of great interest for the highway agencies.
Manuscript received February 23, 2006; revised