IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, VOL. 1, NO. 2, JUNE 2000
A Vehicle Occupant Counting System Based on
Near-Infrared Phenomenology and Fuzzy Neural
, Senior Member, IEEE
, Vassilios Morellas
, Member, IEEE
, Member, IEEE
We undertook a study to determine if the automatic
detection and counting of vehicle occupants is feasible. An auto-
mated vehicle occupant counting system would greatly facilitate
the operation of freeway lanes reserved for buses, car-pools, and
emergency vehicles (HOV lanes). In the present paper, we report
our findings regarding the appropriate sensor phenomenology and
arrangement for the task. We propose a novel system based on fu-
sion of near-infrared imaging signals and we demonstrate its ade-
quacy with theoretical and experimental arguments. We also pro-
pose a fuzzy neural network classifier to operate upon the fused
near-infrared imagery and perform the occupant detection and
counting function. We demonstrate experimentally that the com-
bination of fused near-infrared phenomenology and fuzzy neural
classification produces a robust solution to the problem of auto-
matic vehicle occupant counting. We substantiate our argument by
providing comparative experimental results for vehicle occupant
counters based on visible, single near-infrared, and fused near-in-
frared bands. Interestingly, our proposed solution can find a more
general applicability as the basis for a reliable face detector both
indoors and outdoors.
Fuzzy neural network, near-infrared fusion, ve-
hicle occupant detection.
HERE are compelling reasons for the existence of an auto-
matic vehicle occupant counting system in the HOV lane.
In particular, such a system will be useful in the following re-
1) It will facilitate the gathering of statistical data for road
construction planning. The gathering of usage statistics in
the HOV lane is mandated by the U.S. Federal Highway
Administration. Currently, the gathering of data is per-
formed manually. This is obviously laborious, inefficient,
and prone to error.
2) It will facilitate law enforcement in the HOV lane. Cur-
rently, HOV lane enforcement requires substantial com-
mitments of State Highway Patrol personnel and equip-
ment. HOV lane enforcement has other costs as well.
Manuscript received March 6, 2000; revised August 29, 2000. This work
was supported by the Minnesota Department of Transportation under Contract
Q5216211101.The Guest Editor for this paper was Dr. Katsushi Ikeuchi.
I. Pavlidis and V. Morellas are with the Honeywell Technology Center, Min-
neapolis, MN 55418 USA (e-mail: email@example.com; vassilios.