overview
issues
Australia
related
Guides:
Privacy
Security
& InfoCrime
related
Profiles
& Notes:
Australian
Privacy
regimes
Surveillance
Travel
Assembly
ID Theft
& Fraud
|
overview
This page considers automatic number plate recognition
(ANPR) systems.
It covers -
The
following page of this note considers uptake of ANPR in
Australia, issues and salient studies about use/misuse
of the technology.
introduction
ANPR systems use optical character recognition software
to convert images of vehicle registration numbers into
information for real time or retrospective matching with
law enforcement and other databases.
They have been hailed as mechanisms for "denying
criminals the use of the road" and "intelligence-led
policing". They have also been described as a foundation
for intelligent transport systems (ITS) and congestion
management regimes.
As of early 2007 their use has not resulted in major expressions
of disquiet from communities and civil society advocates
in Australia and overseas. However in isolation and in
conjunction with other technologies, including biometrics
and RFIDs, they pose significant challenges regarding
personal privacy and community-wide surveillance.
They are also known as Licence Plate Recognition (LPR),
Car Plate Recognition (CPR) and Automatic Licence Plate
Recognition (ALPR) systems.
technology
ANPR systems essentially comprise two components -
- data
capture
- data
exchange and analysis
Data
capture involves mechanisms to gain and
read an image of a vehicle number plate (aka registration
plate).
Most jurisdictions require that motor vehicles be identified
through an alphanumeric sign at the front and rear of
that vehicle, with the sign generally being of a standard
size and a common font. The identification 'numbers' on
that plate are drawn from a register maintained by the
particular jurisdiction. That database typically features
information about ownership of the vehicle and may be
tied to a discrete database of registered drivers, ie
those people with a drivers' licence.
The Australian registers are highlighted here.
data capture
Given that most plates are in roughly the same position
and format it is feasible to use an automated or manual
camera (eg hand-held, in a fixed position on a building
or bridge, in a police van) to take a digital image of
a selected vehicle or vehicles in a stream of traffic.
Selection might be manually determined by an operator
or automatic, for example of every vehicle passing a particular
point or every heavy vehicle (with size triggering the
camera).
Many ANPR systems feature dual cameras: an infra-red device
that captures multiple images of the specific number plate
and a conventional colour device that records an image
of the plate in context, ie takes a snap of the car.
Because much capture concerns speeding vehicles and may
take place in adverse conditions such as rain and smog,
multiple images from the infra-red are 'resolved' to provide
a 'best fit' image that is not blurred and that can be
quickly interrogated using optical character recognition
(OCR) software.
That software, a more powerful form of the tool used in
many domestic and business desktop scanners, parses the
image in seeking to recognise shapes in the pixels as
characters on a number plate. Although there is disagreement
about the effectiveness of such recognition, it is common
to encounter claims that the accuracy of interpretation
is between 95% and 98% (with best results in regimes where
equipment is properly maintained and there is little variation
in plates, for example few 'vanity' or 'celebration' plates).
Data analysis is automatic but is often independent of
the device, ie takes place on a server or other machine
at a remote location linked to the
camera via a high speed line.
In isolation, taking snaps of passing cars would not be
particularly meaningful. ANPR systems are significant
because of the data exchange and analysis component.
data analysis and exchange
The shape of ANPR data analysis and exchange depends on
how the ANPR system was set up and how it is being used.
Some applications are highlighted below.
In essence, capture can provide a one-off or ongoing list
of number plates at a particular location, specific time
and direction.
That list can be matched with other databases, which might
include lists of expired number plates, plates on vehicles
that have been reported as stolen or involved in accidents
and on vehicles that are likely to be driven by someone
of interest to law enforcement personnel.
Checking may be almost instantaneous. Proponents of the
UK National ANPR Data Centre for example note that automated
searches of several 'hotlists' by police using mobile
ANPR devices typically returns results within 5 seconds,
quick enough for decisions on whether investigation is
required (and whether particular vehicles should be approached
with extra caution).
The list might instead feed a new database, for example
one that automatically bills the owners of all vehicles
entering a particular precinct during a period of traffic
congestion or that compares matches data from cameras
at two locations and thereby determines that the vehicle
has broken speed limits.
In practice it is a potentially rich source of information
for a wide range of users. One of the issues discussed
in the following page of this note is accordingly that
information collected for 'innocent' purposes on a short
term basis will be shared with other agencies (including
national and provincial law enforcement bodies, welfare
and tax agencies), will be analysed by those bodies through
matching with their data sets and will be stored by them.
The effect of that analysis may be to establish a regime
of pervasive surveillance, one from which individuals
cannot opt out (and indeed of which they are only partly
aware) and in which there is little recourse against abuse
or ineptitude.
applications
In principle, ANPR provides a basis for any scheme that
is restricted to or that leverages vehicle registration
information.
Applications in Europe and Australia have thus included
-
- traffic
congestion management (differential pricing for use
of roads in a precinct)
- traffic
speed restrictions
- offender
identification (unregistered, uninsured, stolen vehicles,
fake number plates)
- criminal
intelligence (location of terrorism suspects and 'persons
of interest to the police')
Congestion
Management
Traffic congestion schemes, of increasing significance
in urban centres where there are concerns about pollution
or the capacity of streets to accommodate a large number
of vehicles during peak hours, seek to exclude classes
of motor vehicles (for example cars owned by non-residents)
or to allow entry of vehicles on a selective basis (eg
at a particular time or subject to a financial penalty).
In essence most schemes involve charging for use of public
streets and have thus proved to be controversial, although
sometimes supported by residents of the particular precinct.
ANPR has been used in such schemes to identify what vehicles
are traversing a location, on the basis that the technology
is less "invasive" than electronic tagging systems
that require users to gain a RFID tag for the particular
driver or vehicle. The registration database is typically
linked to a billing system, with ANPR being used to identify
'authorised' vehicles (which have usually paid for the
privilege of using the local road network) and non-authorised
vehicles, which are automatically issued with a fine.
The London congestion pricing scheme (centred on a standard
charge for private cars and commercial vehicles entering
the zone during particular periods, with a 90% discount
for residents and exemption for buses, taxis and disabled
individuals) envisages that the penalty will be around
£80 per instance. Jonathan Leape notes that
while
the current level of accuracy would not support an account-based
charging system (for which a vehicle would have to be
detected in order to be charged), it is sufficient for
the enforcement of the current pre-pay system; individuals
must pay the charge without knowing whether they have been detected, and even the
reduced penalty charge (if paid within 14 days) is more
than six times the daily charge.
Given the speed of processing and sufficient cameras it
is possible to develop highly granular, time-specific
and dynamic charging, eg different charges at various
times of the day, higher charges when pollution reaches
particular levels.
Speed Restrictions
ANPR can also be used for automated enforcement of speed
restrictions and associated traffic codes, such as prohibitions
on particular classes of vehicles (such as those carrying
explosives or chemicals) using specific routes.
Speed restriction is mechanistic, with the ANPR system
'logging' the vehicle at two or more locations and determining
whether transit between those points and times breached
speed limits. A billing database can then automatically
issue a fine and/or alert traffic police that a breach
is underway.
Attitudes to use of ANPR for speed restrictions appear
to vary considerable, with for example little disquiet
in Australia compared to the UK.
Network management
There is academic and official interest, although apparently
few implementations, in use of ANPR to identify how road
networks are being used and thereby better model future
traffic flows or underpin intelligent transport systems
(eg dynamic signage and traffic signals that reflect loads
on parts of the network).
Offender Identification
Law enforcement officials appear to have been more enthusiastic
about the scope for using ANPR in 'offender identification'.
That encompasses such things as identification of -
- unregistered
vehicles, ie vehicles with an expired number plate (significant
because most regimes prohibit driving of an unregistered
vehicle but do not require that 'unused' vehicles have
a current plate)
- uninsured
vehicles (primarily in regimes where it is mandatory
to insure a vehicle through a government-controlled
insurer)
- stolen
vehicles (ie where the thief takes the vehicle but does
not change the number plates)
- vehicles
with cloned plates (eg the same plates are identified
on separate vehicles in different locations at much
the same time) or with bogus numbers (eg there is no
match with the vehicle register)
- vehicles
engaged in activity such as unauthorised use of bus-only
lanes.
Such
identification can be tied to automated issue of a fine
or summons to appear before a magistrate. It can also
be used in real time to alert law enforcement personnel
to intercept the suspect vehicle, for example to find
and pull over a car that has been reported as stolen.
Criminal Intelligence
Police, customs and other law enforcement officials are
reluctant to tightly circumscribe use of ANPR. As the
following page notes there appears to be considerable
sharing of information by agencies and real time checking
of plates against multiple hotlists.
Such lists include vehicles -
-
reported to have been involved in hit and run incidents,
petrol thefts, drive by shootings, burglaries and abductions
- reported
as having been at the scene of a crime
-
registered to suspected terrorists, family and associates
-
rented using 'flagged' credit cards
-
registered to suspected drug traffickers or child sex
offenders
- registered
to suspected stalkers
In
practice a wide range of people may be 'of interest to
the police' (and their peers); the major limit on realtime
large scale ad hoc sorting based on ANPR is the difficulty
of linking different databases.
next page (ANPR issues)
|
|
