Information Technology Journal 8 (2): 101 -113, 2009

ISSN 1812-5638
O 2009 Asian Network for Scientific Information

Car Park System: A Review of Smart Parking System and its

Technology

M.Y.I. Idris, Y. Y. Leng, E.M. Tamil, N.M. Noor and Z. Razak

Faculty of Computer Science and Information Technology, University of
Malaya, 50603 Kuala Lumpur, Malaysia

Abstract: Due to the proliferation in the number of vehicles on the road, traffic problems are bound to exist.
This is due to the fact that the current transportation infrastructure and car park facility developed are unable
to cope with the influx of vehicles on the road. To alleviate the aforementioned problems, the smart parking
system has been developed. With the implementation of the smart parking system, patrons can easily locate
and secure a vacant parking space at any car park deemed convenient to them. Vehicle ingress and egress are
also made more convenient with the implementation of hassle free payment mechanism. With vehicle detection
sensors aplenty on the market, the choices made may defer due to the different requirements in addition to the
its pros and cons. Subsequently, the various sensor systems used in developing the systems in addition to the
recent research and commercial system on the market are examined as vehicle detection plays a crucial role in
the smart parking system.

Kev words: Car park svstem. intelligent transportation svstem. parking technoloev. smart parking svstem

INTRODUCTION
technologies and researches from various academic
disciplines. With its deployment in the car park, it is
In the year 2006, 458,293 new registered vehicles hoped that it would solve the aforementioned problems
were reported compared to the year 1999 where there were faced by the patrons within the car park.
only 296,°16 new registered vehicles, which makes it a
rough estimate of 54.5% increase in a span of years
Advantages of smart parking system implementation:
(Malaysian Ministry of Transportation, 200°). Referring to The smart parking system is considered beneficial for
the aforesaid statistics provided by the Malaysian the car park operators, car park patrons as well as in
Ministry of Transportation, the current transportation environment conservation (Shaheen et al., 2005;
infrastructure and car park facilities are deemed Chinrungrueng et al., 200°). For the car park operators,
insufficient in sustaining the influx of vehicles on the the information gathered via the implementation of the
road. Smart Parking System can be exploited to predict future
Therefore, problems such as traffic congestion and parking patterns. Pricing strategies can also be
insufficient parking space inevitably crops up. In Asia, manipulated according to the information obtained to
the situation are made worse by the fact that the roads are increase the company’s profit. In terms of environment
significantly narrower compared to the West (Inaba et al., conservation, the level of pollution can be reduced by
2001). Various measures have been taken in the attempt to decreasing vehicle emission (air pollutant) in the air
overcome the traffic problems. Although, the problem can (Shaheen et al., 2005). This can be attributed to the fact
be addressed via many methods, the paper focuses on the that vehicle travel is reduced. As fuel consumption is
car park management system introduced, which is the directly related to vehicle miles travelled, it will be reduces
smart parking system. This study will review the evolution as well.
of vehicle detection technologies as well as the detection Patrons are also able to benefit from smart parking
systems developed over the years. system as parking space are able to be fully utilized
(Kurogo et al., 1995; Sakai et al., 1995) with a safer
SMART PARKING SYSTEM (Shaheen et al., 2005; Chinrungrueng et al., 200°),
optimized and more efficient system implemented
The smart parking system implemented mainly in (Sakai et al., 1995; Shaheen et al., 2005). The system is
the Europe, United States and Japan (Shaheen et al., 2005) made more efficient as vehicle travel time and search time
is developed with the incorporation of advanced are significantly reduced due to the information provided

Corresponding Author: Mohd Yamani Idna Idris, Faculty of Computer Science and Information Technology,
University of Malaya, 50603 Kuala Lumpur, Malaysia
 Inform. Technol. J., 8 (21: 101-113, 2009

by the smart parking system. With the information

2005). The PGIS in Pittsburgh, Pennsylvania also
provided, drivers are able to avoid car park that are fully
functions in directing drivers to special attraction in the
occupied and locate vacant parking spaces with ease
area. Meanwhile, in Yokohama, Japan, the city is divided
elsewhere. The number of vehicles parked illegally by the
into four zones whereby the information specificity
roadside which leads to traffic congestion is also reduced
increases with each zone that the driver cross to arrive at
as it is absorbed into the car parks (Kurog o et al., 1995).
the destination location. Additional information on
Most importantly, traffic congestion can be reduced. All
traffic flow provided by the Aichi Prefectural Police
this would eventually lead to convenience for the patrons.
Headquarters Traffic Control Center and Japan
Highway Public Corporation Nagoya Department is also
Categories of smart parking system: The smart parking
provided by the system implemented in Toyota, Japan
system can be divided into five major categories: namely,
(Sakai et al., 1995).
Parking Guidance and Information System (PGIS),
Mobile phones can also be used for guidance based
transit based information system, smart payment system,
on the research conducted by Idna and Tamil (200°)
E-parking and automated parking (Shaheen et al., 2005). which utilizes Global Positioning System (GPS) for vehicle
Further discussion on the implementation and detection. A map of the driver’s current position based on
characteristic of each of the smart parking system the GPS data along with the status of three of the nearby
category together with examples of its implementation car park are sent to their mobile phones based on the
around the world will also be provided. patron’s current location. The GPS technology used are
discussed in detail by Tamil et al. (200°). Besides that, the
Parking Guidance and Information System (PGIS): The parking guidance system developed based on web and
implementation of Parking Guidance and Information GIS technology (Liu et al., 2006) are able to disseminate
System (PGIS) encompasses two major categories. The information to the users via internet, mobile phones
PGIS can either include the entire city area or function and/or PDA. The guidance system can be with the
only within the car park facility (Shaheen et al., 2005). conventional parking management system as well. In
Setting aside the differences, both the PGIS implemented order to guide the patrons effectively, the car park map is
in many major cities in Europe, Japan, the United Kingdom printed on the parking ticket equipped with Radio
and the United States (Kurog o et al., 1995; Sakai et al., Frequency Identification (RFID) tags for guidance
1995; Shaheen et al., 2005; Mouskos et al., 200°) offer (Idna et al., 2008) so that patrons can locate the assigned
similar advantages similar to those of smart parking parking slot with ease. There are also no worries about
system as discussed earlier. Both provides information forgetting the location of the assigned parking slot during
which aids the decision making process of the drivers in exit.
reaching their destination location and aids them in Vehicle detection sensors are commonly installed at
locating a vacant parking space within the car park en tr ance z, exits and/or individual parking space to detect
facility. The city wide PGIS is indeed helpful in assisting vehicle occupancy. Indicator lights integrated with
drivers to car park with vacant parking spaces via the sensors are also sometimes installed at every individual
information occupancy status for various car parks parking space within the parking facility. The occupancy
around the city as well as other relevant information. On status detected by the sensors can either be occupancy
the other hand, guidance in locating the vacant parking of each individual parking space or in terms of vehicles
space within the car park is ultimately provided by PGIS counts in the car park depending on the installation of the
implemented within the car park. sensors. Moving on, the control center gathers and
PGI S can be summarized as consisting of 4 major
processes the traffic and occupancy information as well
components: namely, information disseminating
as controls the display of information for drivers
mechanism, information gathering mechanism, control
whereas the telecommunication network facilitates the
center and telecommunication networks similar to the
transfer of information among the other three modules
components stated by Mouskos et al. (200°).
(Mouskos et al., 200°). With the advent of advanced
Static/dynamic Variable Message Signs (VMS) have been
technologies, the implementation of devices such as
used in providing drivers with direction either on the road
microcontroller and Field Programmable Gate Array
or within the car park. For guidance on the road, various
(FPGA) are incorporated for faster information processing.
implementation methods can be adopted. For example, the
Not only that, the telecommunication network no longer
system in Shinjuku and Pittsburgh, Pennsylvania
dependent on conventional electrical wiring but wireless
segregates the city area into color coded areas for in
technologies are able to be utilized. Researchers such
providing guidance (Kurogo et al., 1995; Shaheen et al.,
as Wang and Chen (2004), Bi et al. (2006), Liu et al. (2006),
 Inform. Technol. J., 8 (21: 101-113, 2009

Tang et al. (2006), Idna et al. (2008), Lee et al. (2008) and
into account various other factors which includes:
Seong-Eun et al. (2008) have all used wireless network for
geographical, network, travel time from demand points to
data transfer in the implementation of their proposed
the location of the park-and-ride facilities and the
parking guidance system.
constraints of computershe d shapes are performed in
determining the location and commutershed area for the
Transit based information system: The functionality of park-and-ride lots.
transit based information system implemented in countries
such as France, Germany, Ireland, Japan, Switzerland, the Smart payment system: The smart payment system is
United Kingdom and the United States (Shaheen et al., implemented in the effort to overcome the limitation of the
2005) is actually similar to PGIS. The difference exist in the conventional payment methods by revamping the
fact the Transit Based Information System concentrates payment method via parking meter and introduce new
on guiding user to park-and-ride facilities. It provides real- technologies. This is because the conventional method
time information on the status of each car park and public causes delay and inconvenience for the patrons as they
transportation such as the schedules and traffic condition to have to deal with cash. It also reduces maintenance and
the public. The additional information provided enables staffing requirement for payment handling purposes as
the patrons to plan for transit in advance without getting well as traffic control (Chinrungrueng et al., 200°). In
into any inconvenience (Chinrungrueng et al., 200°). general, the Smart Payment System implemented in places
Among its benefits includes increase in the utilization of such as Finland, Italy, London and United States (Hinze,
public transportation as the primary means of 2000; Shaheen et al., 2005; Jones, 2006; Mouskos et al.,
transportation as they can leave their vehicle in the car 200°) consists of contact method, contactless method and
park and switch to public transportation with ease. This mobile devices. While the contact method involves the
will indirectly lead to an increase in the transit revenue use of smart cards, debit cards and credit cards, the
(Shaheen et al., 2005; Chinrungrueng et al., 200°). contactless method inv olves the use of contactless cards,
No doubt, for the transit based information system to mobile devices as well as Automated Vehicle
achieve success in its implementation, proper planning Identification (AVI) tag whereby RFID technologies are
must be conducted. This is especially true in selecting utilized (Mouskos et al., 200°). As contact methods
the location for the park-and-ride car parks that requires contact of the cards with parking meter or
maximizes transit whereby the concept of catchment payment machines in the facility, the latter offers more
area/commutersheds are often used such as indicated by convenience to the patrons.
Horner and Groves (200°). In the network flow-based
Parking meters have now been improvised with
technique introduced, it improves on the conventional
technologies which revolutionize the payment system via
spatial model used in determining the park-and-ride
implementing various improvements such as the
facility location by taking into consideration the traffic
acceptance of various types of cards such as credit card,
flow and works in reducing the vehicle miles travelled by
debit cards (Shaheen et al., 2005) and smart cards (Hinze,
maximizing the inter ception of vehicle during the
2000). It also incorporates other technologies such as
beginning stage of the journey.
having solar power source and wireless connectivity. The
There have been many research centered upon using
PhotoViolationMeter (Photo Violation Technologies, n.d.)
Geographic Information System (GIS). Among them are
which caters for various types of payment methods uses
the research conducted for siting park-and-ride car parks
ground sensors in detecting vehicle presence. Most
in Columbus, Ohio. Farhan and Murray (2008)
importantly, technologies such as WiFi connectivity
incorporated multi-objective spatial optimization model in
(Photo Violation Technologies, n.d.), together with its
locating the park-and-ride facilities while considering
ability in handling payment of fines and taking photos of
numerous objectives and constraints as well as taking
vehicles which violates parking regulations for evidence
into consideration the existing system. While research by
are also incorporated (Ebling and De Lara, 200°). Personal
Farhan and Murray (2008) made no assumption on user
parking meters which are essentially placed in the vehicle
demands, Horner and Grubes ie (2001) used Principal
have also been introduced in Buffalo, New York and
Component Analysis (PCA) in representing the index of
Aspen, Colorado after test studies have been conducted
user demands which will be converted to demand points
(Jones, 2006).
when coupled with information obtained via Geographic The incorporation of RFID technologies in making
Information System (GIS). Subsequently, additional payments were implemented in commercial systems such
calculation conducted by Horner and Groves (200°) takes as Mobipower Ltd., which utilized RFID-based cellular
technology and EZPass system have also developed

103
 Inform. Technol. J., 8 (21: 101-113, 2009

payment system via RFID for car parks and toll facilities You fiave a one paH rig lot
(Mouskos et al., 200°). Similarity between the two rmearved at A Your mservation
systems exists in the requirement for placement of win b‹ a;›ina can ao w
transponder unit in the vehicle. Moving on, the
implementation of mobile devices such as mobile phones
and PDA are normally seen to incorporate other devices
such as parking meters and cards. For some systems
such as those implemented in Groningen, Netherlands
(Shaheen et al., 2005) and Oulu, Finland (Jones, 2006),
prior registration via the internet is required. As mobile
phones are utilized, the system implemented in Oulu,
Finland also has the capability of sending Short
Fig. 1: Example of parking reservation system message
Message Service (SMS) notification to remind the
patrons that the time is almost due and allow them to
options of using the internet via Wireless Application
settle the payment for the additional time extension
Protocol (WAP) enabled mobile phones, Personal Digital
required (Jones, 2006).
Assistants (PDAs) and even conventional computer in
The main concern hindering the implementation of
addition to SMS service for the drivers in access ing
the Smart Payment System would have to be skepticism
the information as well as making reservations.
on the privacy and security issues. This is due to the fact
Teodorovic et al. (2006) takes the implementation a step
that confidential data of the patrons such as personal
further by incorporating fuzzy logic in decision making
information and probably account information are being
whereby the parking reservation request can either
dealt with which are highly confidential. With the
accepted or rejected. It also facilitates the enforcement of
emergence of various threats, it is justifiable to be worried.
tariff classes to enable the maximization of revenue for car
In RFID implementation alone, exploits, malwares and
park operators. The system discussed in (Idna and Tamil,
worms (Rieback et al., 2006a), as well as attacks such as 200°) is one of the systems integrating PGIS with E-
sniffing, spoofing, replay attack and denial of services are parking system, where the patrons are able to reserve
just a fraction of it. Of course, methods have been parking slots after reviewing the status of the car park and
developed in securing the data and overcoming the its proximity to the patron’s current location. An example
threats as is it discovered rang ing from the cryptography, of the message to the patrons is shown in Fig. 1.
detection and evasion as well as temporary deactivation
Thus far, numerous systems have been implemented
which are constantly improved from the conventional
online for city wide implementation, university campuses
method implemented which dates back to World War II
as well as complexes. Among the examples of companies
(Rieback et al., 2006b).
involved in the development of E-parking system are
companies such as ParkingCarma (Parking Carma, n.d.),
E-parking: E-parking provides an alternative for patrons
Click and Park (Click and Park, n.d.) and City and
to enquire the availability and/or reserve a parking space
Suburban Parking Ltd., (City and Suburban Parking Ltd.,
at their desired parking facility to ensure the availability of
n.d.). As the E-parking systems implemented online can
vacant car park space when they arrive at the parking
also be considered as E-commerce applications, it has
facility. The system can be accessed via numerous
been proposed that the Unified Modeling Language
methods such as SMS or through the internet. Some of
(UML) is employed in modeling the system’s
the additional benefits of using the E-parking system
performance. This can be achieved by converting the
aside from those collectively gained by smart parking
class diagram and sequence diagram to an execution
system are that it can be extended easily to incorporate
diagram via an intermediary actor-event graph and
the payment mechanism of smart payment system
combining it with other necessary information pertinent to
whereby payments by the patrons are made hassle free
the system (Geetha et al., 200°).
using the technologies discussed previously. Customized
As observed, there are many different implementation
information can also be provided to the patrons either
methods that can be enforced by incorporating various
before or during their trip to the car park (Shaheen et al.,
technologies. Besides the difference in reservation
2005).
method, different reservation types can also be enforced
In a study by Inaba et al. (2001), reservations can be
such as proposed by Inaba et al. (2001 ), whereby patrons
made through the utilization of mobile phones or any
can chose not to declare the exit time and park for an
reservation centers convenient to the patrons. On the
indefinite amount of time. To gain access in to the car
other hand, the study by Hodel and Cong (2004) revealed

104
 Inform. Technol. J., 8 (21: 101-113, 2009

park, printed receipts, permits or passes are utilized by the

CAR PARK OCCUPANCY DETECTION
patrons. More sophisticated implementation proposed
which requires the use of smart cards or magnetic cards
The smart parking system relies heavily on the car
(Inaba et al., 2001) and Bluetooth (Hodel and Cong, 2004)
park occupancy information as it is not only used in
are also implemented in granting access to the patrons. It
can also be implemented together with Smart Payment assisting the drivers on the road, but in the management
System payment schemes such as cards (Inaba et al., within the car park as well. There is abundance of sensor
2001 ; Hodel and Cong, 2004), pre and post paid methods system that can be installed to provide this crucial piece
as well as m-payment (Hodel and Cong, 2004) are utilized. of information. Having said that, there are many factors
which can affect the occupancy detection such as sensor
Automated parking: Automated parking involves the use chosen car park type and layout, to name a few.
of computer controlled mechanism, which allows patrons
to drive up to the bay, lock the cars and let the machines Vehicle detection technology: Vehicle sensors and
automatically place the vehicle in the allocated space. detector system can be categorized into two main
This type of car park offers maximum utilization of categories: namely, intrusive and non-intrus ive sensors
space as it is machine controlled unlike conventional car (Mimbela and Klein, 200°). Intrusive sensors are sensors
park where space is needed for navigation of vehicle
which are typically installed in holes on the road surface,
within the car park. Among its benefits are that the
by tunneling under the road surfaces or anchoring to the
implementation works great in locations, where there are
surface of the road which leads to invasive procedures of
limited room for expansion due to its structure. Besides
installation whereas the latter can be installed easily by
that, the Automated Parking System also offers
efficiency in car storage as it allows car stacking and the mounting the device on the ground or the ceiling of the
patron does not even need to go into the car park which car park. With the variety of sensors on the market,
indirectly provides extra safety measures which covers factors such as the cost, environmental condition, scale
both the vehicles and patrons (Shaheen et al., 2005). of implementation as well as the system design would
Among the automated parking system reviewed in have to be considered while selecting the sensors.
countries which includes Japan, Canada and United Examples of intrusive sensors include active infrared
States (Shaheen et al., 2005) as well as the commercial sensors, inductive loops, magnetometers, magneto-
system developed by companies such as automotion resistive sensors, pneumatic road tubes, piezoelectric
parking system (Automotion, n.d.), robotic parking cables and weigh-in-motion sensors. As denoted by its
(Robotic Parking, n.d.) and Fata SKYPARK S (Fata name, intrusive sensors typically requires pavement cut
SKYPARKS, n.d.), it generally utilizes computer controlled for installation which indirectly decreases pavement life.
mechanism in placing the vehicles in its storage bay For installation and maintenance on the road, lane closure
within the parking facility. Automated parking can also be
would have to be conducted, which would lead to
implemented in a conventional car park via additional
inconvenience of the drivers (Chinrungrueng et al., 2006;
equipments installed such as developed by Fata
Lenz and Edelste in, 2006; Mimbela and Klein, 200°;
SKYPARK S (Fata SKYPARKS, n.d.). There are many
variations whereby the automated parking system can be Mouskos et al., 200°).
implemented, from the design of the car park structure to On the other hand, non-intrus ive sensors
the workings of the computer controlled docks/lifts as encompasses microwave radar, passive acoustic array
well as the placement of vehicles whereby user sensors, passive infrared sensor, RFID, ultrasonic and
participation are sometimes required. video image processing. Non-intrus ive sensors can easily
The safety features are geared towards the vehicle be installed and maintained and does not affect the
whereby it is important to ensure that the vehicle remains surface in the process. Unlike intrusive sensors,
safe and undamaged with all the handling by the maintenance and installation for non-intrus ive sensors
computer controlled mechanisms. Research by Mathijssen can be conducted without invasive procedures and
and Pretorius (200°) introduced a three-leve1 software disruption of traffic (Kastrinaki et al., 2003; Mimbela and
design which includes: Logical Layer (LL), Safety Layer Klein, 200°). The description, strength and weaknesses of
(SL) and Hardware Abstraction Layer (HAL) to enforce
the various sensor technologies that are currently utilized
correct and efficient storage of vehicles in a safe manner.
in vehicle detection as compiled by Mimbela and Klein
As the car park facility is designed with conveyer belts,
(200°) together with other research by Kastrinaki et al.
rotatable lifts and shuttles, it has to be coordinated to
(2003), Cheung et al. (2005), Chinrungrueng et al. (2006),
ensure successful and safe placement and retrieval of the
vehicle. Lenz and Edelstein (2006), Wolff et al. (2006),
Mouskos et al. (200°) and Pala and Inane (200°) will
 Inform. Technol. J., 8 (21: 101-113, 2009

subsequently be scrutinized. Each of the sensors also has

used to transmit data in some models. Among the
the ability to provide different detection parameters which
disadvantages of using fluxgate magnetometers are the
are also discussed in the aforementioned studies.
small detection zones in some model which requires
multiple units are required for full lane detection as well as
Active infrared sensors: Active infrared sensors detects
the close proximity required for accurate detection
vehicles by emitting infrared energy and detecting the
(Cheung et al., 2005; Mimbela and Klein, 200°).
amount of energy reflected (Mimbela and Klein, 200°;
Mouskos et al., 200°). By utilizing the active infrared Magnetometer (induction or search coil magnetometer):
sensors, multiple lane operations can be conducted. For Induction or search coil magnetometer identifies vehicle
an accurate measurement of vehicle position, speed and signature by measuring the change in the magnetic flux
class, multiple beams are transmitted from the sensor. lines caused by the moving vehicle according to
However, the drawback of the sensor would be its Faraday’s Law of induction (Lenz and Edelstein, 2006;
sensitivity towards environmental conditions such as fog Mimbela and Klein, 200°). Like the fluxgate magnetometer,
or blowing snow which affects the operation of the it is insensitive to weather condition such as snow, rain
sensors. and fog. Besides that, it is less susceptible to stresses of
traffic than loops. Special sensor layouts and signal
Inductive loop detectors: Inductive Loop Detectors (ILDs)
processing software are required to identify stopped
are wire loops of various sizes which are exited with
vehicles. While it is an intrusive sensor, some models can
signals whose frequencies range from 10 to 50 kHz. The
be installed without the need for pavement cuts.
oscillation frequency of the inductive loop is directly
controlled by the inductance of the loop which changes Magnetoresistive sensor: As stated by Lenz and
with vehicle presence. The sensor system proved to be a Edelstein (2006), magnetores istive sensors encompasses:
mature and well understood technology with large Anisiotropic Magnetores istance Sensors (AMR), Giant
experience base and extensive research conducted. Magnetores istance Sensors (GMR), Magnetic Tunnel
Besides that, its flexibility also allows for the Junction Sensors, Extraordinary Magnetoresistance and
implementation in a large variety of applications. The Ballistic Magnetores istance that are simply energized by
vehicle detection zone can be easily enlarged by providing a constant current (Lenz and Edelste in, 2006).
combining the loops together. Compared with other The sensors are light and small which makes it versatile in
commonly used techniques, ILD provides the best placement (Wolff et al., 2006). Coupled with a wide range
accuracy for count data. In fact, inductive loop sensors of temperature (-55 to 200°) and low cost, it has been
became the common standard for obtaining accurate widely used for vehicle detection. Wolff et al. (2006) have
occupancy measurements. utilized the AMR sensor in their research for vehicle
While the inductive loop detector has its advantages, detection and has noted its sensitivity to position and
it is not without flaw as it is expensive to maintain orientation.
(Mouskos et al., 200°). Not only does it require multiple
detectors to monitor a specific location, the Wire loops Piezoelectric sensors: Piezoelectric sensors are made
subjected to wear and tear due to stresses of traffic and from specially processed material that is able to convert
temperature. Detection accuracy would also be kinetic energy to electrical energy when subjected to
compromised when design requires detection of a large vibration or mechanical impact. Vehicle differentiation can
variety of vehicle classes. While it is mentioned by also be conducted with extreme precision as additional
Mimbela and Klein (200°) that it is insens itive to weather information is gathered rather than the passing of vehicle
condition such as rain, fog and snow, Mouskos et al. alone. Not only that, it also provides a more accurate
(200°) has stated that the sensors are sensitive to element reading on vehicle speed and classification of vehicles
such as water, especially if the pavement is cracked. based on weight and axle spacing with almost the same
cost as ILD. Among the disadvantages would be the need
Magnetometer (fluxgate magnetometer): Fluxgate
to use multiple detectors to instrument a location. Besides
magnetometers works by detecting perturbation (magnetic
that, it is also extremely sensitive to high temperature and
anomaly) in the earth’s horizontal and vertical magnetic
traffic stress.
field. Fluxgate magnetometers provide the advantage of
being insensitive to weather condition such as snow, rain
Pneumatic road tube: Pneumatic road tube detects vehicle
and fog. It is also more accurate and less susceptible than
via the air pressure created which closes a switch,
loops to stresses of traffic. As the technologies for
producing signals when a vehicle pass or stop over the
wireless transmissions evolves, wireless RF link are also
tube. While it offers a low cost solution as well as quick

106
 Inform. Technol. J., 8 (21: 101-113, 2009

installation and easy maintenance, it has its

Passive infrared sensors: Passive infrared sensors
disadvantages. Pneumatic road sensors are temperature
identify the occupancy status of a parking space by
sensitive. Inaccuracies in axle count are also bound to
detecting changes in the energy emitted by the vehicle
happen when bus and truck numbers are high. In addition,
and the roads (Mimbela and Klein, 200°; Mouskos et al.,
the tubes are prone to vandalism.
200°). While the sensors are able to be implemented in a
multizone environment to measure vehicle speed, the
Weight-in-Motion (WIM) sensors: Weight-in-Motion
sensitivity of the sensor is reduced in heavy rain, snow
(WIM) sensors are able to detect the weight of the vehicle
and dense fog. Besides that, certain models are not
whereby the data acquired are extremely useful to
recommended for presence detection.
highway planner, designers and law enforcement
agencies. The four technologies used in WIM system are:
RFID: The utilization of RFID as a method for vehicle
bending plate, piezoelectric, load cell and capacitance mat.
detection in conducted in Mouskos et al. (200°). It is a
Each of the WIM sensors has its own advantages and
universal, useful secure and efficient technology (Pala
disadvantages. While bending plate WIM is more
and Inane, 200°) which consist of 3 units which are:
accurate and costly compared to piezoelectric WIM
transceiver, transponder and antenna. The transceiver is
system, it is less accurate compared to load cell WIM
used to send and read information from the transponder
systems and are considerable cheaper. Although
unit which contains the coded information through the
capacitance mat can be used as portable or permanent, it
antenna. Active transponders are also re-programmable
is the least accurate WIM system. For accuracy, load
through wireless connection, while passive transponders
cell WIM system would be preferable as it is the most
have an unlimited lifetime. Radio signals eliminates the
accurate WIM system, with the disadvantage of it being
need for contact, no line of sight operation and are able to
the priciest. The cheapest WIM system in use is the
penetrate opaque structures. By using RFID sensors, it
piezoelectric system, with a weakness of sensitivity
provides the means for low cost installation and
towards weather and speed variation. Its accuracy is
maintenance as well as possible detection at high speed.
behind load cell WIM and bending plate WIM system.
The complication actually lies with the need to place
Both the piezoelectric and capacitance mat WIM system
transponders in every vehicle as well as privacy issues
can be used to monitor up to 4 lanes. All the WIM system
with the patron’s personal details.
requires replacement or refurbishment every 3 to 5
years.
Ultrasonic sensors: Ultrasonic sensors transmits pulse
waveforms between 25 to 50 kHz to the road by detecting
Microwave radar: Microwave radar sensor transmits
transmitted energy which are reflected back the sensor.
energy (1-30 GHz) through an antenna and detects vehicle
Together with a signal processing module, the reflected
by the energy reflected back towards the antenna. The
ultrasonic energies are analyzed to detect occupancy in a
two type of microwave radar sensors being implemented
roadside controller. Its utilization brings the advantage of
are: Continuous Wave Radar (CW) and Frequency
Modulated Continuous Wave Radar (FMCW). detecting vehicles that exceed certain height limit as well
Microwave radar sensors provide the advantage of being as multiple lane operation. The ultrasonic sensors are also
insensitive to inclement weather. It is also able to conduct easy to install without the need for facility closure.
multiple lane traffic flow data gathering as well as provide Degraded occupancy measurement on freeways with
direct measurement of vehicle speed. Among its vehicles traveling at moderate to high speeds due to large
disadvantages is that the Doppler sensors would have to pulse repetition period are one of the shortcomings of the
be equipped with auxiliary sensors in attempt to detect sensor. Besides that, temperature changes and extreme air
stopped vehicle. turbulence affects the sensor performance, although
temperature compensation has been built into some
Acoustic sensors: The acoustic sensors detects vehicle models.
via the acoustic energy or audible sounds produced by
the vehicle through microphones installed for vehicle Video image processor: A Video image processor
detection. The advantages offered by acoustic sensors typically consists of: one or more cameras, software for
are support for multiple lane operation in certain models image interpretation and microprocessor based computer
as well as passive detection. Not only that, it is also for digitizing and processing. Careful analysis of
insensitive to precipitation. Its sensitivity towards cold continuous frames captured by the video image processor
temperature which affects data accuracy proved to be a can be used in detection of vehicles as it reveals the
drawback. Certain models are also not recommended with differences between subsequent frames. The utilization of
slow moving vehicles in stop and go traffic.
 Inform. Technol. J., 8 (21: 101-113, 2009

video image processor provides the ease of management

2005). Over in the European continent, infrared sensor
(Kastrinaki et al., 2003) and implementation as it is readily
applications have been applied in Bristol, United Kingdom
available in most car park facilities with basic surveillance
to identify vacant spaces and transmit the data to a
systems. Detection zones are also easily added and
central computer (Shaheen et al., 2005). In NJIT, inductive
modified. Besides that, it can easily adaptable to space
loops were deployed at the car park entrances and exits
of any geometric shape for coverage optimization, with
detection (Mouskos et al., 200°). It is mainly used in
the detection zones easily added and modified
keeping track of the vehicle count in the car park. In the
(Mouskos et al., 200°). With the wide-area detection
study proposed by the authors on PGIS within the car
provided when information gathered at one camera
park, CCTV cameras were used in detecting the
location are linked to another, it caters for multiple lane
occupancy status of each of the parking space
detection and reduces the number of cameras needed for
(Idna et al., 2008).
monitoring. The detection results garnered can also be
Moving on to commercial systems, industrial giants
verified offline and in real-time without the need for delay
such as CODIC (http://www.parkingireland.ie/
(Mouskos et al., 200°).
showart2.htm.), E and D (http://www.enctech
Although, it has many advantages, the CCTV
group. com/E%20&%20D/xguide.html.), IDENTIPARK
cameras are only cost-effective if many detection zones
(IDENTIPARK, n.d.) and SIEMENS (SIEMENS, n.d.) have
are required within the field of view of the camera and
developed PGIS using ultrasound sensors for vehicle
good lighting available. Inclement weather, shadows,
detection, whereas VehicleSense (Vehicle Sense, n.d.) are
vehicle projection into adjacent lanes, day-to-night
geared towards using magnetic sensors. All the
transition, vehicle/road contrast and water, salt grime,
commercial systems mentioned have the sensors
icicles and cobwebs on camera lens can affect
placement location in common whereby the sensors are
performance, even though temperature compensation and
placed at each individual parking space for occupancy
built into some models. Camera motions due to strong
detection. It is also used to guide patrons to the
winds might also affect some models. The height and
respective vacant spaces through the overhead lights
layout of the car park facility might also pose a problem as
incorporated which changes according to the occupancy
occlusion (Mimbela and Klein, 200°; Mouskos et al.,
status. On the other hand, the system developed in
200°) can occur at certain locations. While the video
Toyota guides patron through VMS to the available
cameras are unaffected by construction or maintenance of
vacant space (Sakai et al., 1995).
the car park (Mouskos et al., 200°), the camera mounting
height (in a side-mounting configuration) required for
Transit based information system: In the case of transit
optimum presence detection and speed measurement are
based information system, ultrasonic sensors and laser
about 50 to 60" would definitely be a problem in car park
scan detectors were installed in Munich whereas
facilities with low roof.
inductive loops were deployed in the city of Cologne
(Shaheen et al., 2005). The systems in Cologne and
IMPLEMENTATION OF VEHICLE DETECTION Munich, which is implemented city wide, both exploits the
TECHNOLOGIES IN SMART PARKING SYSTEM use of VMS in providing information to the patrons as
well as guidance to car parks with vacant space. The
By further examining the various smart parking guidance provided by the system in Munich proved to be
system currently deployed as well as the commercial more extensive whereby it continues to guide patrons to
system on the market, it provides a brief idea on its the vacant parking space with guidance system within the
implementation methods and sensor utilization. The car park as well (Shaheen et al., 2005).
different sensor placements as well as the implementation
method of the particular system, albeit achiev ing the same Smart payment system via REID: Commercial
end results of providing guidance to the patrons, are quite
systems such as EZPass as well as those developed by
different. Information gathered on the various systems
Mobipower Ltd are vastly different in implementation
would definitely help in improv ising and developing a
although RFID technologies are utilized. The only
better system.
similarities are the requirement for the RFID device to
be placed in the vehicle. System by Mobipower such as
PGIS: Ultrasonic sensors were employed in each described by Mouskos et al. (200°), requires the patron to
individual parking space for vehicle detection in the activate the RFID unit named Triffiq to start the
Baltimore-Washington International Airport in the United transaction and deactivate it to indicate end of
States and Blagnac Airport in France (Shaheen et al., transaction. Charges will then be displayed although the

108
 Inform. Technol. J., 8 (21: 101-113, 2009

actual payments are made when monthly bills arrive. On

the road. The sensor nodes consist of: microcontroller,
the contrary, EZPass system does not require any
magnetic sensors and radio which are powered by 2 AA
activation of the device and immediately deducts the
batteries are implemented in a (WSN) environment. Both
payments from the patron’s account although records of
are similar in the fact that the sensors are installed at
the patron’s transaction are provided periodically.
each individual parking space and implemented in a
WSN environment. Besides that, the components
IMPLEMENTATION OF VARIOUS VEHICLE
utilized are similar with the exception of FPGA device
DETECTION TECHNOLOGIES IN COMMERCIAL
utilization.
SYSTEMS AND RESEARCH
Optical sensor: In a research by Chinrungrueng et al.
Subsequent discussion focuses on the (2006, 200°), optoelectronic sensors which reacts to
implementation of various sensors vehicle detection both light are utilized in vehicle detection. Each sensor nodes
on the road and in the car park. As the sensors utilized are consist of optical sensor, a microcontroller and radio-
essentially the same, more focus will be emphasized on frequency transmitter connected in a star-based WSN
the different placements and any associated hardware topology environment (Chinrungrueng et al., 2006). Its
devices used in conjunction with the sensors. Information implementation differs depending on the power
on the different methodologies and hardware devices are constraints. The sensor nodes can either be scheduled in
provided whenever available in providing a brief overview a round robin fashion to monitor traffic and report during
on the various systems reviewed. Apart from the systems predetermined time or put to sleep and only activated
discussed a compilation of the commercial systems when performing the function of: vehicle detection or
available on the market as well as those still in communication with the server node. Two sensor heads
research is presented by Mimbela and Klein (200°) and installed at a certain distance for vehicle detection to
Kastrinaki et al. (2003). overcome the initial weakness in the system whereby it is
unable to distinguish vehicles from pedestrians and
Magnetic sensor: Various researches have been
motorcycles (Chinrungrueng et al., 200°).
conducted by utilizing the magnetic sensors which are
typically used for vehicle detection whereby the complete
RFID: The system developed by Pala and Inane (200°)
listing of the type of magnetic sensors is provided in the
relied solely on RFID technology in detecting vehicles at
research by Lenz and Edelstein (2006). In a research by the ingress and egress points. Vehicles can enter and exit
Wolff et al. (2006), passive magnetoresistive sensors were the cai park without the need stop as there is no need for
installed both along the walls and on the floor. the usage of parking tickets and payments are handled via
Microcontrollers were used to handle the communication RFID technology. The authorization on entrance to the
with a master via connectivity through a RS485 bus so car park depends on the registration of the vehicle. This
that the data can be transmitted to the PC for processing is because the system will search the database for
and displayed on the three VMS installed in the car park. registered vehicle and confirm that it does not have any
The following research involves the implementation of check-in or check-out records before updating the check-
magnetic sensors in a Wireless Sensor Network (WSN) in information into the database and lifting the barrier for
environment. In the D-Systems Project by the Mobile vehicle ingress. If the vehicle is not registered, it cannot
Internet Systems Laboratory, University College York gain entry to the car park. During egress, system updates
(Benson et al., 2006; Barton et al., 200°), the system the database with the check-out date and time.
consist of a microcontroller and antenna for
communication in the communication layer, magnetic Inductive loop and REID: In terms of vehicle detection, the
sensor in the sensing layer and lastly, 2 AA batteries in utilization of inductive loop sensors in occupancy
the power layer. As the hardware is implemented in a detections have been conceptualized whereby inductive
stackable platform whereby it can be easily combined and loop detectors are installed at each individual parking
dismantled, a processing layer consisting of FPGA device space (Shim et al., 2006). It further extends the application
were able to be added (Barton et al., 200°). by incorporating RFID technologies in the implementation
Unlike the D-Systems which concentrates on
whereby a RFID tag is used to provide the vehicle
occupancy detection, implementation by Cheung et al.
information in a WSN environment using Zigbee
(2005) explored the functionality of vehicle detection,
communication technology. This is to facilitate the
vehicle speed detection, vehicle classification and re-
information gather ing of the ingress and egress of a
identification through installation in the car park and on
particular vehicle. Implementation by Ostojic et al. (200°)
differs in the sense that it is used to perceive vehicle

109
 Inform. Technol. J., 8 (21: 101-113, 2009

presence at the ingress and egress and the RFID tag have
Vector Machine (SVM) for vehicle recognition. Conflict
to be put in front of the reader for verification at the
resolution and optimization were also implemented with
ingress and egress point.
Markov Random Field. On the other hand, Funck et al.
(2004) used PCA in reconstructing the input image via
Sensor board with multiple sensors: The sensor board
eigenspace reconstruction based on earlier obtained
for research conducted by Tang et al. (2006) is employed
model of empty car park pictures to obtain the differences
with a three-layer framework implementation. While the
between the both the images for vehicle classification.
motes are used in gathering data, the gateway in the
Subsequent discussion focuses on the use of
server layer is used to update information in the server
different segmentation techniques for vehicle detection in
which will be accessed by the client, which is the
determining occupancy status of the car park space. In
application on the client computer. It consists of three
the research by Idna et al. (2005), if a certain percentage
types of sensors: namely, light, temperature, acoustic
of the pixels are detected to belong to the floor after
sensors. The system is event driven and consists of five
segmentation via thresholding, it will be classified as
major types of events which are timer, car-in, driving
vacant. Character recognition using chain code and
status, car-out and field management which triggers the
database are implemented for character recognition of the
operation and interaction between the modules.
parking space number via the numbers painted on the
Ultrasonic sensors as well as temperature sensors
floor. A three-layer Bayes ian hierarchical detection
are available in the sensor node equipped together with a
framework which encompasses observation layer, labeling
microprocessor and wireless communication module for
layer and semantic layer has also been introduced
the system developed by Bi et al. (2006). The system also
(Huang et al., 2008). Here the entire row of car park space
provides guidance via a guiding node which also operates
is extracted as ROI that will eventually be segmented to
through WSN in obtaining information. Both the
obtain the occupancy status for each individual car park
implementation by Tang et al. (2006) and Bi et al. (2006)
space.
requires the sensor nodes to be placed at every
The Car Park Occupancy Information System (COIS)
individual parking space for detection.
uses a bi-stream (Bong et al., 2008) detection to overcome
false detection caused by shadows. Color images were
Vision based: The deployment of surveillance system
initially used (Bong et al., 2006), whereby image
generally faces the challenges of multiscale information
subtraction which was subsequently converted into
gathering, contextual event detection and the deployment
binary form. Later on, grayscale image was used from the
of large systems (Hampapur et al., 2005). Vision based
beginning (Bong et al., 2008) whereby the conversion of
system or surveillance systems have been utilized in the
the image to binary form depends solely on the bit-° of
detection of both static vehicles and also vehicles in
image pixels. Although, the methods are different,
motion. The methods proposed by Hampapur et al. (2005)
segmentation via thresholding is essentially performed on
for object detection which includes adaptive background
the image. Calculation with an accumulator is performed
subtraction and salient motion detection are some of the
next with a threshold value set to determ ine the
methods that can be implemented in vehicle detection. As
occupancy status. The second processing stream
more researches are conducted, a vast variety of image
utilizes Sobel edge detection to eliminate false reading
processing algorithms can be manipulated for vehicle
by shadows, with median filter were added later on
detection. The main difference between the vision based
(Bong et al., 2008).
systems developed is essentially the image processing
Although, SVM classification has been implemented
algorithm without regards of whether the camera is static
in Wu et al. (200°), a method incorporating image
or moving.
homography was proposed by López Sastre et al. (200°).
The manipulation of color image for detecting car
By altering the viewpoint of the car park camera to
park occupancies have been conducted using various
top- view before performing feature extraction using
image processing methods. While Principal Component
Gabor filter and classification via SVM, the region-of-
Analysis (PCA) is widely implemented in vehicle
interest extraction process will be made easier and
detection, the overall approach is vastly different.
misclass ification due to occlusion can be minimized.
Wu et al. (200°) delt with ROI region which are cropped
As noticed, different algorithm provides different
to three parking spaces per patch and uses PCA for advantages for the systems developed. PCA are often
feature extraction while incorporating it with used to overcome the problem of illumination variance in
preprocessing, color histogram analysis and Support the images captured and SVM are robust enough in
 Inform. Technol. J., 8 (21: 101-113, 2009

dealing with occlusion. But more recent techniques which

Chinrungrueng, J., U. Sunantachaikul and S. Triamlumlerd,
involve using Bayesian probability such as implemented
2006. A vehicular monitoring system with power-
by are Huang et al. (2008) robust enough to handle both
efficient wireless sensor networks. Proceedings of
the problem of occlusion and illumination invariance.
the 6th International Conference on ITS
Telecommunication, June 21 -23, Chengdu, pp:
CONCLUSION
951-954.
Chinrungrueng, J., U. Sunantachaikul and S. Triamlumlerd,
In this study, the various types of smart parking
system and has been presented. From the various 200°. Smart parking: An application of optical
examples of the implementation of the smart parking wireless sensor network. International Symposium on
system being presented, its efficiency in allev iating the Applications and the Internet Workshops
traffic problem that arises especially in the city area where (SAINTW'0°), January 15-19, Hiroshima, pp: 66-69.
traffic congestion and the insufficient parking spaces are Ebling, M. and E. De Lara, 200°. New products. IEEE
undeniable. It does so by directing patrons and optimizing Pervasive Comput., 6: 11-13.
the use of parking spaces. Farhan, B. and A.T. Murray, 2008. Siting park-and-ride
With the study on all the sensor technologies used facilities using a multi-objective spatial optimization
in detecting vehicles, which are one of the most crucial model. Comput. Operat. Res., 35: 445-456.
parts of the smart parking system, the pros and cons of Funck, S., N. Mohler and W. Oertel, 2004. Determining
each sensor technologies can be analyzed. Although, car-park occupancy from single images. IEEE
there are certain disadvantages in the implementation of Intelligent Vehicles Symposium, June 14-1°, Dresden,
visual based system in vehicle detection as described Germany, pp: 325-328.
earlier, the advantages far outweighs its disadvantages. Geetha, D.E., C.R.M. Reddy, T.V.S. Kumar and
K.R. Kanth, 200°. Performance modeling and
REFERENCES evaluation of e-commerce systems using UML 2.0.
Proceedings of the 8th ACIS International
Barton, J., J. Buckley, B. O’Flynn, S.C. O’Mathuna and Conference on Software Engineering, Artificial
J.P. Benson et al., 200°. The D-systems project- Intelligence, Networking and Parallel/Distributed
wireless sensor networks for car-park management.
Computing (SNPD 200°), July 30 200°-Aug. 1 200°,
IEEE 65th Vehicular Technology Conference,
Washington, DC, USA., pp: 1135-11 40.
April 22-25, VTC200°-Spring, pp: 1° 0-1 3.
Hampapur, A., L. Brown, J. Connell, A. Ekin and N. Haas
Benson, J., T. O’Donovan, P. O’Sullivan, U. Roedig and
et al., 2005. Smart video surveillance: Exploring the
C. Sreenan, 2006. Car park management using
concept of multiscale spatiotemporal tracking. IEEE
wireless sensor networks. Proceedings of the
31st IEEE Conference on Local Computer Networks, Signal Process. Mag., 22: 38-51.
November 14-16, Tampa, FL, pp: 588-595. Hinze, D., 2000. Italians drive for smart card parking in
Bi, Y.Z., L.M. Sun, H.S. Zhu, T.X. Yan and Z.J. Luo, 2006. major cities. Card Technol. Today, 2: 6-°.
A parking management system based on wireless Hodel, T.B. and S. Cong, 2004. PSOS, parking space
sensor network. Acta Automatica Sin., 32: 8°°-968. optimization service. Proceedings of the 4th Swiss
Bong, D.B.L., K.C. Ting and N. Rajaee, 2006. Car-park Transport Research Conference, March 25-26, Monte
occupancy information system. Third Real-Time Veritâ/Ascona, pp: 1-22.
Technology and Applications Symposium, RENTA S Horner, M.W. and T.H. Grubesic, 2001. A GIS-based
2006, Serdang, Selangor, December 2006. planning approach to locating urban rail terminals.
http://www.cs.ieeemalays ia.org/RENTAS2006/pape Transportation, 28: 55-°°.
rs/Car-Park-Occupancy.pdf. Horner, M.W. and S. Groves, 200°. Network flow-based
Bong, D.B.L., K.C. Ting and K.C. Lai, 2008. Integrated strategies for identifying rail park-and-ride facility
approach in the design of car-park occupancy locations. Soc. Econ. Plann. Sci., 41 : 255-268.
information system. IAENG Int. J. Comput. Sci., Huang, C.C., S.J. Wang, Y.J. Chang and T. Chen, 2008. A
35: 1-8. bayesian hierarchical detection framework for parking
Cheung, S.Y., S. Colen Ergen and P. Varaiya, 2005. Traffic space detection IEEE International Conference on
surveillance with wireless magnetic sensors. Acoustic, Signal and Image Processing, ICASP 2008,
Proceedings of the 12th ITS World Congress, 31 March 2008-4 April 2008, Las Vegas, NV,
November 2005, San Francisco, pp: 1-13. pp: 209° -21 00.
 Inform. Technol. J., 8 (21: 101-113, 2009

Idna, M. Y., N.M. Noor, Z. Razak and M.N. Ridzuan, 2005.

Mathijssen Aad, A. and P. Johannes, 200°. Verified
Parking system using chain code and a-star
design of an automated parking garage. Lecture
algorithm. International Conference on Intelligent
Notes Comput. Sci., 4346: 165-180.
Systems, ICIS2005, (Endorsed by the IEE), December
Mimbela, L.Y. and L.A. Klein, 200°. A summary of vehicle
1-3, Sunway Lagoon Resort Hotel, Kuala Lumpur,
detection and surveillance technologies used in
PP 5 intelligent transportation systems. New Mexico
Idna, M. Y. and E.M. Tamil, 200°. Parking information
State University, Tech. Report, 200°.
system using GPS and shortest path algorithm.
http://www.fhwa.dot.gov/ohim/tvtw/vdstits.pdf.
Proceedings of the SCORED 200°, May 14-15,
Mouskos, K.C., M. Boile and N. Parker, 200°. Technical
Univers iti Tenaga Nasional, Malaysia, pp: 1-°.
solutions to overcrowded park and ride facilities.
Idna, M. Y., Y.L. Yong, E.M. Tamil and N.Z Haron, 2008.
University Transportation Research Center-Region 2.
Parking guidance system using RFID and image
City College of New York. Final Report, FHWA-NJ-
processing techniques in WSN environment. 4th
200°-01 . http://www.nj.gov/transportation/refdata/
International Colloquium on Signal Processing and
its Applications, March -9, Royale Bintang Hotel, research/reports/FHWA-NJ-200°-011.pdf.
Kuala Lumpur, pp: 1-6. Ostojic, G., S. Stankovski, M. Lazarevic and V. Jovanov ie,
Inaba, K., M. Shibui, T. Naganawa, M. Og iwara and 200°. Implementation of RFID technology in parking
N. Yoshikai, 2001. Intelligent Parking Reservation lot access control system. 1st Annual RFID Eurasia,
Service on the Internet. SAINT-W, Symposium on Sept. 5-6, Istanbul, pp: 1-5.
Applications and the Internet-Workshops (SAINT Pala, Z. and N. Inane, 200°. Smart parking applications
2001 Workshops), Jan. 8-12, San Diego, CA, USA., using RFID technology. 1st Annual RFID Eurasia,
pp: 159-164. Sept. 5-6, Istanbul, pp: 1-3.
Jones, W.D., 2006. Parkirg 2.0. IEEE Spectrurn, 43: 20-20. Rieback, M.R., P.N.D. Simpson, B. Crispo and
Kastrinaki, V., M. Zervakis and K. Kalaitzakis, 2003. A A.S. Tanenbaum, 2006a. RFID malware: Design
survey of video processing techniques for traffic principles and examples. Pervasive Mobile Comput.,
applications. Image Vision Comput., 21 : 359-381 . 2: 405-426.
Kurogo, H., K. Takada and H. Akiyama, 1995. Concept of Rieback, M.R., B. Crispo and A.S. Tanenbaum, 2006b. The
a parking guidance system and its effects in the evolution of RFID security. IEEE Pervasive Comput.,
Shinjuku area-configuration, performance and future 5: 62-69.
improvement of system. Proceedings of Vehicle Sakai, A., K. Mizuno, T. Sugimoto and T. Okuda, 1995.
Navigation and Information Systems Conference, Parking guidance and information systems.
1995. In conjunction with the Pacific Rim TransTech Proceedings of Vehicle Navigation and Information
Conference. 6th International VNIS. 'A Ride into the Systems Conference in Conjunction with the Pacific
Future', 30 July 2 August, Seattle, WA, USA., Rim Trans Tech Conference, 6th International VNIS.
pp: 6° -° 4. A Ride into the Future, 30 Julu-Aug. 2, IEEE, Xplore,
Lee, S., D. Yoon and A. Ghosh, 2008. Intelligent parking pp: 4°8-485.
lot application using wireless sensor networks. Seong-Eun, Y., C. Poh Kit, K. Taehong, K. Jonggu and
International Symposium on Collaborative K. Daeyoung et al., 2008. PGS: Parking guidance
Technologies and Systems, CTS 2008, May 19-23, system based on wireless sensor network. 3rd
Irvine, CA, pp: 48-5°. International Symposium on Wireless Pervasive
Lenz, J.E. and A.S. Edelstein, 2006. A review of magnetic Computing, (ISWPC 2008), May -9, IEEE Xplore,
sensors. IEEE Sensors J., 6: 631-649. pp: 218-222.
Liu, Q., H. Lu, B. Zou and Q. Li, 2006. Design and Shaheen, S.A., C.J. Rodier and A.M. Eaken, 2005. Smart
development of parking guidance information system parking management field test: A bay area rapid
based on web and gis technology. Proceedings of transit (bart) district parking demonstration.
the 6th International Conference on ITS http://pubs. its. ucdavis.edu/download df.php?id=
Telecommunications, June 21-23, Cheng du, 44.
pp: 1263-1 266. Shim, S., S. Park and S. Hong, 2006. Parking management
López Sastre, R.J., P. Gil Jiménez, F.J. Acevedo and system using zigbee. Int. J. Comput. Sci. Network
S. Maldonado Bascón, 200°. Computer algebra Security, 6: 131-13°.
algorithms applied to computer vision in a parking
Tamil, E.M., D. Salleh and M. Y. Idna, 200°. CaT Sys 1. 0-a
management system. IEEE International Symposium
mobile vehicle tracking system with GPS technology.
on Industrial Electronics, ISIE 200°, June 4-°, Vig o,
Proceedings of the SCORED 200°, May 14-15,
pp: 16°5-1680.
Univers iti Tenaga Nasional, Malaysia, pp: 1-11.
 Inform. Technol. J., 8 (21: 101-113, 2009

Tang, V.W. S., Y. Zheng and J.N. Cao, 2006. An intelligent

Wolff, J., J. Heuer, T. Haibin, G. Weinmann, M. Voit and
car park management system based on wireless
S. Hartmann, 2006. Parking monitor system based on
sensor networks. 1st International Symposium on
magnetic field senso. IEEE Intelligent Transportation
Pervasive Computing and Applications, SPCA-2006,
System Conference, (ITSC'06), Toronto, Ont.,
August 3-5, Urumqi, pp: 65-° 0. pp: 12°5-12°9.
Teodorovic, D. and P. Lucie, 2006. Intelligent parking
Wu, Q., C.C. Huang, S.Y. Wang, W.C. Chiu and
systems. Eur. J. Operat. Res., 1°5: 1666-1681.
T.H. Chen, 200°. Robust parking space detection
Wang, Y.K. and S.H. Chen, 2005. A robust vehicle considering inter-space correlation. IEEE
detection approach. IEEE Conference on Advanced International Conference on Multimedia and Expo,
Video and Signal Based Surveillance, AVSS 2005,
July 2-5, Beijing, pp: 659-662.
Sept. 15-16, Taiwan, pp: 11° -122.

113