Parking Network is the leading online platform for Parking Professionals worldwide

What else is on Parking Network?

What is Parking Network?

License Plate Recognition

License Plate Recognition (LPR) is an image-processing technology used to identify vehicles by
their license plate only. Since every vehicle carries a unique license plate, no external cards, tags or transmitters need be issued to vehicle owners in order for their vehicle to be recognizable. LPR is a viable option to transponder technology.

LPR might also be called:

  • ANPR - Automatic Number Plate Recognition

  • AVI - Automatic Vehicle Identification

  • CPR- Car Plate Recognition / Car Plate Reader

  • OCR - Optical Character Recognition
  • Computer-based plate recognition started emerged in the 1980's. In 1990's, LPR technology made a successful transition from the research bench and military applications to the commercial marketplace. In the last five years off-the-shelf components star­ted to become available from a greater number of vendors and the technology became mainstream. Now, with over 40 suppliers offering commercial LPR products, the technology is finding its way into all aspects of traffic solutions.
    Closed circuit television (CCTV) cameras can be used to take the images used by automatic number plate recognition software's. In most parking facilities the gates are already covered by cameras and often these same cameras can be utilized for LPR to save cost. Though dedicated IP cameras will in most cases yield a better result.
    Since the vehicle plates are based on different
    Country standards, they usually differ in form, shape and material. Therefore theLPR systems are Country specific and are adapted to tbe Country where they are installed and used. A high end LPR system can usually handle sImultaneously several different kinds of plates of the doze[ls that a LPR vendor may support. LPR systelJls are based on images of the front and/or rear plates. Especially in very dark con­ditions infrared cameras are used to take pictures any time of the day.
    Early LPR systems suffered from a low recognition rate, lower than required by practical systems. They came also at a very high installation cost. The exter­nal effects and the limited level of the recognition software and vision hardware yielded low quality systems. Concerns about these systems have also centered on privacy fears of government tracking citizens' movements and media reports of misiden­tification and high error rates. This has cast a bad reputation to LPR systems that still surfaces today. However most of these concerns are history, as recent improvements in the software and hardware have made the LPR systems much more reliable and wide spread. You can now find these systems in numerous installations and the numbers of systems are growing exponentially, efficiently automating more and more tasks in different market segments. In many cases the LPR unit is added as retrofit in addition to existing solutions, such as a magnetic card reader or ticket dispenser/reader, in order to add more functionality and enhance the level of security to the existi ng facility.
    Even if the recognition is not absolute, the highly developed software's can cowpensate the errors and produce a virtually flawless system. For examp­le, when comparing the recognition of the entry time of a car to the exit time in order to establish the parking time, the match (of entry verses exit) can allow some small degree of error without making a mistake.
    This intelligent integration can overcome most of the LPR flaws and yield dependable and fully automatic systems. Today's technology can reach over 99.5 % success rate and read plates at speeds over 250 km/h.

    LPR are also in wide use in several fields other than parking:

  • Law enforcement - searching for stolen cars and wanted criminals

  • Customs - vehicles entering and exiting coun­try borders.

  • Traffic violations - speed cameras which work by tracking vehicles' travel time between two fixed points, and calculating the average speed.

  • Tolls - London congestion charge is a good
    example with over 200 cameras

  • Traffic flow - possible to monitor the travel of individual vehicles, automatically providing information about the speed and flow of various routes. These details can highlight pro­blem areas as and when they occur and help the centre to make informed management decisions

  • Airport / Harbor logistics - taxi and heavy traffic flow control

  • Gas station payment control - quick identifica­tion of a customer that leaves without paying
  • scan01.jpg
    1, Parking
    arrives to gat~.
    2. Parking
    loop or infrared
    the camera to record. tion can be used,
    3. The software grabs can be more thai'loN veh icle, which increases stores the information
    4. Pictures are transferred server that inter­
    prets the LP informatiqn Jro.m t~epictWres.The licen­se plate is extracted fror)'1t~e image, and the digits are separated and recognizec:f,
    5.The license platenLfmber, together withthe image a nd event i nformation,is sent back to the recording server where it is storedln the database. The infor­mation can also be sent to a third party and/or activate dry contact (for ba~ders, alarms etc).
    6. Parking equipment receives information accor­ding to particular event
    7. Parking Equipment system decides how the vehicle is treated: open gate, block gate, etc Total time for the complete flow varies between 0.5 to 4 seconds depending on the system and the variables.
    vehicle

    There are benefits of a LPR systems for both subscription and short term users.

    PRO's of LPR:
  • No need for cards or transponder. Access can be controlled by a license plate combined with a subscription. The process is quick and easy and is completely automated.

  • The subscription is linked to a vehicle, not to a card. This makes the exchange of cards impos­sible, thereby reducing fraud. A customer can have several cars in his LPR account.

  • New subscriptions are easily issued in seconds
    and can be billed afterwards.

  • Division of the park facility in multiple areas,
    with the possibility to define user groups. The parking capacity can be monitored per section.

  • Several reports of vehicle activity at the parking site can be generated for a given period.

  • Archived images can be used to solve quickly disputes on parking duration or lost tickets.

  • Car theft prevention by pairing the ticket to a specific car.

  • Identification of vehicles through a black list with several programmable responses. This allows exclusion of unwanted vehicles.

  • Accurate estimates of vehicles present in the parking facility or in one of its sections.

  • No more open parking tickets, track vehicle movement

  • Gives customers a sense of security, verifying vehicle details. License plate can be printed on ticket.

  • Easily find cars that are staying suspiciously long by subtracting the cars that have exited from the ones hat have entered.

  • Remote surveillance and control even over the
    internet.

  • Flexible car pool management. A customer with 10 cars has 5 subscriptions. Automatically if the sixth enters it will be charged separately or denied access.

  • Easy access to pictures of cars at entrance and exit (for example in solving was the dent there already when entering the facility)

  • Customer loyalty programs (special rates etc) Dividing a car park into sections with LPR can also help customers find their car


  • CON's of LPR
  • Recognition rate may drop for various reason like:

  • . Weather
    . Dirty/muddy/snowy plates
    . plate tilt, rotation, skew
    . presence of a trailer hitch or other obscuring
    factors
    . ambient illumination
  • Not 100 % recognition. Still advisable to use simultaneously other systems like chip cards in case of regognition failure for subscription users.

  • For locked pedestrian accesses there is a need of some other form of identification
  • A word of caution - with many vendors supplying LPR systems, the quality of these systems can vary greatly. Determining the accuracy of an LPR system is complex and depends on the application, operating conditions, and assumptions made during testing. When evalua­ting a system, it is important to use those criteria to examine manufacturers' claims carefully.


    The supplier should clearly and precisely define the conditions under which the system achieved the stated accuracy rate. A system may correctly identify plates ninety-nine percent of the time under controlled conditions, but only fifty percent of the time under less ideal conditions. The supplier should also explicitly state the definition of failure: a failure could signify a missed plate (no recognition at all) or an error in the interpretation (identification) of one or more characters, which can still be usable.
    European plates are in general simple to read. On the contrary for example some US states have very difficult vanity plates with colorful backgrounds. Many countries are also taking LPR into consideration when making new plates, for example changing the font to improve plate recognition as the Dutch did in 2002.
    Many countries now use license plates that are retro­flective. This returns the light back to the source and thus improves the contrast of the image. In some countries again the characters on the plate are not reflective, giving a high level of contrast with the reflective background in any lighting conditions. A camera that makes use of infrared imaging (with a normal color filter over the lens and an infrared


    light-source next to it) benefits greatly from this as the infrared waves are reflected back from the plate. This is only possible on dedicated day&night cameras, however, and so cameras used for other purposes must rely more heavily on the software capabilities.
    Most off street parking garages has the advantage that they are under a roof in controlled conditions. This means that the circumstances are constant as the car moves slowly and the lighting is good and even.


    Vehicle owners have used a variety of techniques in an attempt to evade LPR systems and traffic enforce­ment cameras in general. One method is to increase the reflective properties of the lettering that makes it more likely that the system will be unable to locate the plate or produce a high enough level of contrast to be able to read it. This is typically done by using a plate cover or a spray, though claims regarding the effectiveness of the latter are disputed. In most countries, the covers are illegal and covered under existing laws, while in most countries there is no law to disallow the use of the sprays. Only flash cameras a re affected by these methods.
    In order to avoid surveillance or penalty charges, there has been an upsurge in car cloning, particu­larly in London. This is usually achieved by copying registration plates from another car of a similar model and age. This can be difficult to detect, espe­cially as those who clone may change the registrati­on plates and travel behavior to hinder investigati­ons. However most of these frauds are not targeted at pa rki ng faci I ities.
    LPR raises also some legal and privacy issues. Countries seem to take quite different approaches to LPR. Spain seems to be most aggressive for LPR in already requiring some parking facilities to print the customer's I icense plate on the ticket.