License Plate Recognition, a Twenty-First Century Fact of Life

Terrorists were the intended targets for the first license plate readers deployed by New York City.  It was 2006 and the NYPD was involved in what was known as the Lower Manhattan Security Initiative, a counter-terrorism plan that involved setting up movable, random roadblocks in the Financial District. Thousands of cameras provided ancillary surveillance in the area south of Canal Street but the program revolved around special ones equipped with license plate reading technology.

Thank goodness the NYPD has been successful so far in quelling terrorist plots. They have expanded their use of license readers to attack everyday crime wherever it may be happening. According to an article in the New York Times, as of April 2011, New York was using 238 license plate readers. Of these 130 are mobile, mounted on the backs of police cars that might be patrolling any street in the city’s five boroughs. The other 108 are fixed posts at city bridges and tunnels, as well as above other thoroughfares. License plate reading cameras differ from other surveillance IP cameras that monitor broad areas in that they are designed to focus on a small area, and are aimed low to the ground.

Police tracked down 3,659 stolen vehicles, and issued traffic tickets for 34,969 un-registered ones. In the period from 2010 to 2011 alone, they identified and recovered 248 vehicles bearing stolen license plates.

Divisions dealing with felonies have used the technology to their advantage as well. In 2011 a bank robber was apprehended after high-jacking a livery cab in New Jersey and driving it through the Lincoln tunnel to New York. Somewhere along the route, the license plate was detected and the car traced to a specific block in Queens. FBI agents, alerted by the NYPD, surveyed the block and the next morning apprehended the suspect who had a loaded pistol in his possession. 

In another case of violent crime, a murder suspect was arrested after several cameras spotted his plates in various locations. The police had but to connect the dots to find him sequestered in a closet in a relative’s home. 

How does this work in a city measuring 304.8 square miles (or 468.9 square miles if one counts the 165.6 square miles of water)? The data captured on the cameras are continuously checked against specific databases containing information on stolen vehicles, stolen license plates, and unregistered vehicles. In addition, the cameras’ files are downloaded twice daily to central computers where personnel update the databases each time. Investigators are then able to retrieve new information such as the license plate of a new suspect or the stolen license plate of one they’ve lost track of.

Technology Highlights:

This technology is gaining popularity in security and traffic installations. The technology concept assumes that all vehicles already have the identity displayed (the plate!) so no additional transmitter or responder is required to be installed on the car.

The system uses illumination (such as Infra-red) and a camera to take the image of the front or rear of the vehicle, then an image-processing software analyzes the images and extracts the plate information. This data is used for enforcement, data collection, and (as in the access-control system featured above) can be used to open a gate if the car is authorized or keep a time record on the entry or exit for automatic payment calculations.

The LPR system significant advantage is that the system can keep an image record of the vehicle which is useful in order to fight crime and fraud ("an image is worth a thousand words"). An additional camera can focus on the driver face and save the image for security reasons. Additionally, this technology does not need any installation per car (such as in all the other technologies that require a transmitter added on each car or carried by the driver).

LPR is also called in different references as:

• Automatic Vehicle Identification (AVI)
• Car Plate Recognition (CPR)
• Automatic Number Plate Recognition (ANPR)
• Car Plate Reader (CPR)
• Optical Character Recognition (OCR) for Cars

Does it Work?

Early LPR systems sufferred from a low recognition rate, lower than required by practical systems. The external effects (sun and headlights, bad plates, wide number of plates types) and the limited level of the recognition software and vision hardware yielded low quality systems.

However, 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 number 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 to the existing facility.
Even if the recognition is not absolute, the application that depends on the recognition results can compensate 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 some of the LPR flaws and yield dependable and fully automatic systems.

Some license plate recognition system uses special software who automatically reading license plates.   

·         Image collection

·         Image analysis

·         Image and data storage

·         Data transmission

Image Collection

License plate capture cameras with CCD image sensor works with a pulsed infra-red light source to monitor a target area of passing vehicles. The illumination device contains up to 190 LEDs in the near infrared range and is capable of providing a high contrast black and white image similar to the image below.

Notice how the use of infra-red light suppresses most of the surrounding detail and allows the reflective license plate properties to make it dominant in the field.  In addition the TruViewLPR license plate capture camera lets the user alter the contrast by changing each video field up to sixty times per second, on a cycle of three different levels of brightness  - low, medium, and high. Taken together, these allow for optimal plate image processing no matter what the time of day or the condition the license plate in question.

Image Analysis

The captured images are processed by a set of algorithms that extract only the license plate portion of the frame and send it to two different Optical Character Recognition engines for processing.  It takes 200 milliseconds or less for the LPR Software to analyze and come up with an ALPR result. It then reports one of two reads: The read that provides the highest confidence score level of all the captured images for that particular license plate or the read that meets a pre-determined minimum level of confidence.

Data Storage

The image with the best results is now saved and linked with the results data. The data might consist of the plate number, the date and time, the lane number.

Overview Camera

In addition another camera may be used to furnish a scene overview showing a full view of the vehicle which will be linked to the plate data and image, all to be stored to be made available for subsequent  queries. You can also add many IP cameras for multiple overviews when using VMS software.

Data and Image Management and Display

Stored data can be forwarded to a central server over a standard TCP/IP connection or using a wireless connection.

The LPR information can be displayed using Ocularis VMS software or using the Central Management console which will allow an operator to bring up ALPR events based on license plate number, date, time, lane, or other desired characteristics.

Applications

There are a number of applications where automated License plate recognition can be used.  Image collection can take place in a triggered or non-triggered environment.

·         A non-triggered installation needs no detection device. In this mode, software, known as Virtual Vehicle Detector, analyzes each image at a rate of sixty images per second for the presence of a license plate. This image, and additional images containing the vehicle’s license plate data is captured and processed to extract the license plate characteristics

·         A triggered mode requires a detection device and can be used in a number of applications. The trigger could be an in-ground loop or an optical trigger and is called for when several systems are to be tied together to a single event. Such parallel systems might be a vehicle classification system, a transponder system, a parking lot ticket dispenser, a weigh-in motion system , and so on.

The LPR Software device can act as a lane controller, hosting a database that will permit or deny vehicle access into or out of a parking facility, gated community, or high-security compound. This can be done with the optional Universal Interface Controller (UIC) to provide contact closure outputs to open or close a gate or arm in response to queries of the database.

And so in this day and age, a license plate serves as more than just a way to determine if that’s your buddy in the silver Honda up ahead.

Elements of typical LPR systems

LPR systems normally consist of the following units:

• Camera(s) - that take the images of the car (front or rear side)
• Illumination - a controlled light that can bright up the plate, and allow day and night operation. In most cases the illumination is Infra-Red (IR) which is invisible to the driver.
• Frame grabber - an interface board between the camera and the PC, allows the software to read the image information
• Computer - normally a PC running Windows or Linux. It runs the LPR application which controls the system, reads the images, analyzes and identifies the plate, and interfaces with other applications and systems.
• Software - the application and the recognition package. Usually the recognition package is supplied as a DLL (Dynamic Link Library).
• Hardware - various input/output boards used to interface the external world (such as control boards and networking boards)
• Database - the events are recorded on a local database or transmitted over the network. The data includes the recognition results and (optionally) the vehicle or drver-face image file

The following illustration shows a typical configuration of a LPR system (for example, for 2-lanes-in and 2-lanes-out access control system). The system ("SeeLane") is a typical example of such system.
The SeeLane application runs as a background Windows application in the PC (shown in the center), and interfaces to a set of SeeCarHead camera/illumination units (one for each vehicle) which are interfaced by the frame grabber. The application controls the sensors and controls via an I/O card that is connected thru a terminal block to the inputs and outputs.
The application displays the results and can also send them via serial communication and via DDE messages to other application(s). It writes the information to local database or to optional remote databases (via the network). 

Typical applications

LPR applications have a wide range of applications, which use the extracted plate number and optional images to create automated solutions for various problems. These include the following sample applications

Parking - the plate number is used to automatically enter pre-paid members and calculate parking fee for non-members (by comparing the exit and entry times). The optional driver face image can be used to prevent car hijacking.

In this example, a car is entering a car park in a busy shopping center. The car plate is recognized and stored. When the car will later exit (through the gate on the right side) the car plate will be read again. The driver will be charged for the duration of the parking. The gate will automatically open after payment - or if the vehicle has a monthly permit.

Access Control - a gate automatically opens for authorized members in a secured area, thus replacing or assisting the security gaurd. The events are logged on a database and could be used to search the history of events.

In this example, the gate has just been automatically raised for the authorized vehicle, after being recognized by the system. A large outdoor display greets the driver. The event (result, time and image) is logged in the database.

Tolling - the car number is used to calculate the travel fee in a toll-road, or used to double-check the ticket.

In this installation, the plate is read when the vehicle enters the toll lane and presents a pass card. The information of the vehicle is retrieved from the database and compared against the pass information. In case of fraud the operator is notified.

Border Control - the car number is registered in the entry or exits to the Country, and used to monitor the border crossings. It can short the border crossing turnaround time and cut short the typical long lines.

This installation covers the borders of the entire Country. Each vehicle is registered into a central database and linked to additional information such as the passport data. This is used to track all border crossings.

Stolen cars - a list of stolen cars or unpaid fines is used to alert on a passing 'hot' cars. The 'black list' can be updated in real time and provide immediate alarm to the police force. The LPR system is deployed on the roadside, and performs a real-time match between the passing cars and the list. When a match is found a siren or display is activated and the police officer is notified with the detected car and the reasons for stopping the car.

Enforcement - the plate number is used to produce a violation fine on speed or red-light systems The manual process of preparing a violation fine is replaced by an automated process which reduces the overhead and turnaround time. The fines can be viewed and paid on-line.

The photo is an example of a speeding car caught by the traffic camera. The rear vehicle plate is automatically extracted off the scanned film image, replacing a tedious manual operation and the need to develope and print the violation. The datablock on the top-right side is additional speeding information that is automatically extracted from the developed film and used to complete the fine notice and inserted to a database. The violators can pay the fine on-line and are presented with this photo as a proof with the speeding information.

Traffic control - the vehicles can be directed to different lanes according to their entry permits (such as in University complex projects). The system effectively reduces traffic congestions and the number of attendents.

In this installation the LPR based system classifies the cars on a congested entrance to 3 types (authorized, known visitors, and unknown cars for inquiry) and guides them to the appropriate lane. This system reduced the long waiting lines and simplified the security officers work load.

Marketing Tool - the car plates may be used to compile a list of frequent visitors for marketing purposes, or to build a traffic profile (such as the frequency of entry verses the hour or day).

Travel - A number of LPR units are installed in different locations in city routes and the passing vehicle plate numbers are matched between the points. The average speed and travel time between these points can be calculated and presented in order to monitor municipal traffic loads. Additionally, the average speed may be used to issue a speeding ticket.

In this example the car is recognized at two points, and the violation shows the photos of both locations which were taken on bridges on top of the highway. The average speed of the car is calculated from both points, and displayed if the speed passed a violation threshold, and optionally printed.

Airport Parking - In order to reduce ticket fraud or mistakes, the LPR unit is used to capture the plate number and image of the cars. The information may be used to calculate the parking time or provide a proof of parking in case of a lost ticket - a typical problem in airport parking which have relatively long (and expensive) parking durations.

This photo shows the gate of a long term airport parking. The car is recognzied on entry and the data is later used to track the real entry time in case of a lost ticket.