12 prtraffic and trofile ansport
Automatic
number
crunching
Greg Blackman investigates
upgrading the city’s analogue traffic enforcement such as Dalsa designing sensors with improved
system to a digital system. Systems Engineering sensitivity in the near-infrared region.
the applications of automatic
and Assessment, a UK-based systems integrator, On the software side, machine vision
number plate recognition,
is developing the Digital Traffic Enforcement technology can add intelligence to the images
System (DTES) using Ticket Express management captured. Automatic number plate recognition
along with other uses of
software and traffic enforcement systems from (ANPR) is a classic example, and image analysis
Danish vision technology company JAI. tools can be used to not only read the number
machine vision technology
The DTES project aims to improve the plate, but also to classify criteria such as make,
for monitoring our roads
efficiency and reduce the cost of collecting, model and colour of the vehicle.
processing and storing traffic offence evidence. ‘Adding a degree of intelligence to the images
Areas such as bus journey times, bus reliability, captured lends itself to certain traffic monitoring
Analogue video technology has long been congestion, and road safety, are targeted for applications, such as automatic tolling schemes
used for monitoring transport networks and improvement by the scheme. TfL’s current system and restricting certain vehicles from certain
is still widely used today. However, there is an uses continuously recording analogue video areas,’ notes Hearn. For instance, a restriction
increasing move towards using digital machine cameras, whereas DTES is designed to detect and might be placed on heavy vehicles in the city
vision technology in certain applications, due to record only contraventions – thus eliminating the centre during peak traffic times and ANPR can
the additional functionality it provides. ‘Vision need for reviewing hours of unnecessary footage help enforce that. Security is another example,
for traffic monitoring is currently split between and the necessity for large storage facilities. where cameras can monitor roads and flag up
CCTV and pure machine vision systems,’ states One of the challenges for machine vision stolen cars or vehicles wanted by the police.
Steve Hearn, sales manager at European imaging cameras used in traffic monitoring applications Dutch company VID provides national
technology provider Stemmer Imaging. The is producing high-resolution images in low traffic information in the Netherlands and
cameras used in a traditional, machine vision light conditions. With higher-resolution sensors has implemented Sony’s smart camera with
om
environment don’t require excessive functionality. the sensitivity is lower, so additional lighting ANPR capability for use in various applications
ope.c
However, for traffic monitoring applications a is required. However, the sensitivity of image on Dutch roads. The software involved was
eur
certain amount of pre-processing functionality is sensors is increasing rapidly, with manufacturers developed by Abstract Computing International,
.imv
required. The need to control a lens, for instance,
www means that digital cameras for traffic monitoring
are designed with similar functionality to that
 
2009 
ch
of analogue cameras and with technology, such
as FPGAs, a level of image pre-processing is
possible.
‘CCTV is low-cost and generally well
ebruary/mar
 
f
established for traffic monitoring,’ says Hearn.
ope However, he goes on to say, the cameras are
limited in resolution, and coverage of two to
three lanes of traffic with one camera is not
possible with most CCTV systems. Machine
vision cameras provide higher resolution and
also triggering capability, so systems do not need
to continuously record, as is the case with CCTV,
but can be triggered to capture specific images. A traffic scheme set up on Dutch roads advising motorists of the travelling times of different
Transport for London (TfL) is in the process of routes. Image courtesy of Sony and Abstract Computing International.
imaging and machine vision eur
IMVEfeb09 pp12-15 traffic.indd 12 17/2/09 17:08:03
Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36