License Plate Recognition License Plate Recognition License Plate - - PowerPoint PPT Presentation

Slide 1

License Plate Recognition License Plate Recognition License Plate Recognition License Plate Recognition (LPR), Car Colour & Facial (LPR), Car Colour & Facial (LPR), Car Colour & Facial (LPR), Car Colour & Facial Capture / ID or Verification, Capture / ID or Verification, Capture / ID or Verification, Capture / ID or Verification, possibly linked to Access Cards possibly linked to Access Cards possibly linked to Access Cards possibly linked to Access Cards

Barry T. Dudley

In conjunction with

Slide 2

Why I-CUBE?

• Sells service and not product
• Offers high-recognition rates and

accuracy and can be integrated into existing or new applications.

• Speed & accuracy
• Flexibility
• Integration

Slide 3

What are I-CUBE capabilities?

• License Plate Recognition up to 300 KM per hour
• LPR accurately verified to vehicle colour, shape and
• ther identifying visual characteristics
• LPR linked to driver facial ID
• Full-featured digital video recorder, so a visual

record is created for every vehicle passing the camera, allowing searching by license plate, vehicle types, makes or colours across time period

Slide 4

L License

icense P

Plate

late R

Recognition

ecognition

Slide 5

IN SOUTH AFRICA:

Access Control – 11 in SA Toll Road – 1 Secure Access Control Violation Film processing – 30 Vehicle logging; Roadblocks

Over 1 0 0 0 sites w orldw ide

Wide range of applications…

Linking vehicles to DATA (wt, size, colour, time, etc.)

Slide 6

LPR - 5 easy steps:

1 - Capture 2 – Find plate 3 – OCR 5 – Report 4 – Open gate if allowed, ALARM if BANNED

Slide 7

• Licence Plate Recognition is a non-intrusive,

computerised method of matching a Vehicle Licence Plate to a database of registration numbers.

• System includes cam era/ illum ination units, hardw are

and softw are ( application + recognition library)

• Autom atically reads License Plate num ber
• Displays, records and transm its vehicle im age and

recognition results

• Can com pare plate num ber to data base - and optionally
• pen gate or activate alarm

Slide 8

Camera/Illumination Units (Up to 4 per system) Frame Grabber LPR Software

PC Station

Included Hardware I/O Card +Terminal Block Power Supply for SCH

Slide 9

Slide 10

GATE : 1 lane IN; 1 lane OUT GATE : 1 lane IN; 1 lane OUT IN IN OUT OUT

Slide 11

Existing CCTV cameras Existing CCTV cameras

IR & CCTV cameras linked to DVR system

Frame Grabber

PC Station

LPR Software WANTED LIST Allowed Database LIST DVR HW Software

Slide 12

F Fa

acial cial R

Recognition

ecognition S

System

ystem

Slide 13

2D systems typically used for identification comparing an image captured with static images. Security personnel finds a match 3D systems typically used for verification of people or for identifying with minimal on no personnel involvement

Facial Recognition Facial Recognition 2D vs 3D

Slide 14

Deploying HNET 3D technology to verify people enrolled in the system

Facial Recognition Facial Recognition 3D System

Slide 15

FRS Network (multiple clients, one server): -

Facial Recognition Facial Recognition 3D System – How does this get connected?

Slide 16

Speed, accuracy and intelligence are among the key qualities

Facial Recognition Facial Recognition 3D System – What are the benefits?

Slide 17

Using a revolutionary core technology HNet, based on neural networks, I-CUBE facial recognition delivers cutting-edge security and split-second processing times.

Facial Recognition Facial Recognition 3D System – Speed

Slide 18

The proposed FRS was the most accurate technology tested in the International Biometric Group’s Comparative Testing for IT Security and E-Commerce

Facial Recognition Facial Recognition 3D System – Accuracy

Slide 19

The proposed FRS learns, remembers and recognises, becoming more familiar with your face each time it sees you, adjusting for difference due to aging and cosmetics.

Facial Recognition Facial Recognition 3D System – Intelligence

Fred Bloggs

Slide 20

Requirement: Vehicle Logging Requirement: Vehicle Logging The requirement is to provide Licence The requirement is to provide Licence Plate Recognition (LPR) technology, Plate Recognition (LPR) technology, possibly linked to car colour, driver possibly linked to car colour, driver Facial Capture / ID / Verification to Facial Capture / ID / Verification to facilitate secure ACCESS CONTROL. facilitate secure ACCESS CONTROL. The car and driver are linked by the The car and driver are linked by the facial biometric to an access card (if facial biometric to an access card (if present) and vehicle (colour, shape present) and vehicle (colour, shape and license plate) on enter & exit. and license plate) on enter & exit.

Slide 21

PROCEDURE:

• LPR occurs as vehicle approachs boom,
• Then driver swipes access card,
• Facial Capture / ID or Verification then
• ccurs,
• Image capture of vehicle colour occurs,
• If all captured information matches the

database, boom opens.

• If ANY information does not agree,

guard called.

• LPR of vehicle plate front and back;

Slide 22

LPR Installation for entry / exit monitoring Vehicle approaches entry

Slide 23

Entry Vehicle approaches entry

Card reader

Slide 24

Camera / Illumination unit

LPR

MKF 359 GP

Vehicle Sensor Recognize plate number and compare to data base

PC Station

LPR occurs first while vehicle moving

Card reader

Slide 25

Recognition Rate: 0.5 sec

Vehicle approaches card reader stand

Slide 26

Recognition Rate: 0.1 sec

Person presents card to card reader

Picture of driver is captured, possibly compared to database

• f allowed drivers

FACIAL

Compared

Slide 27

Recognition Rate: 0.2 sec

Person presents card to card reader

Vehicle colour captured, possibly compared to database

Car Colour

Slide 28

Total time required for an authorized driver, with the correct car (colour & license plate) and access card: 7 seconds

If Card, License Plate, Facial and Car Colour match entry in database, boom

• pens,

IF NOT, guard called to investigate

Slide 29

Matching Criteria

Office Hrs ONLY White 0987654321 123456789 NP132785 Result T&A OVERALL – After hours, hence not allowed! Allow ed Car Colour Allow ed Facial Capture Allow ed 123456789 Card Allow ed License Plate Recognition Result Captured

Criteria

Slide 30

LPR Front End

Slide 31

FRS Front End

Slide 32

FRS LOG

Slide 33

LPR LOG

LOG FOR A SINGLE EVENT

Added,1,NP192785,100,100,100,100,100,100,100,100,100 Added,2,NP132785,100,100,100,100,100,100,100,100,100 Added,4,NP12785,91,100,100,75,100,100,100,100 Best,2 Result,NP132785 Added,1,NP132785,95,100,100,100,100,100,100,100,100 Added,2,NP132785,100,100,100,100,100,100,100,100,100 Added,3,NP132785,100,100,100,100,100,100,100,100,100 Added,4,NP12785,96,100,100,75,100,100,100,100 Best,3 Deleted,4 Result,NP132785 Added,1,NU44667,99,100,100,100,100,100,100,100 Added,2,NU44667,99,100,100,100,100,100,100,100 Added,3,NU44667,99,100,100,100,100,100,100,100 Added,4,NU44667,99,100,100,100,100,100,100,100 Added,5,NU44667,99,100,100,100,100,100,100,100 Added,6,NU446M7,75,100,100,100,100,30,40,100 Best,3 Deleted,6

Result,NU44667 LICENSE PLATE, LANE, USER, DATE

HFP848GP,..........,1,Yes,Rachel Tim,Sat Aug 14 09:05:16 2004, KBW141GP,..........,2,No,,Sat Aug 14 09:05:18 2004, MKF359GP,..........,1,Yes,David Smith,Sat Aug 14 09:05:20 2004, LJD977GP,..........,3,No,,Sat Aug 14 09:05:22 2004, ND474276,..........,2,Yes,Daniel Bush,Sat Aug 14 09:05:24 2004, DYK370GP,..........,3,No,,Sat Aug 14 09:05:30 2004, LGW487GP,..........,1,Yes,Goldy Luck,Sat Aug 14 09:05:36 2004, KPR835GP,..........,3,No,,Sat Aug 14 09:05:38 2004,

All images are kept

Slide 34

Land Rover 4X4 LOG - LPR

Slide 35

VW Jetta LOG

Slide 36

Solution Proposed Solution Proposed This solution allows: -

• Multiple image capture by high resolution LPR camera’s;
• License plate finding within the image;
• License plate number reading at a high accuracy (with multiple cameras used in

stereo);

• Multiple image capture by high resolution cameras of the driver and vehicle

colour;

• Linking of license plate number and Facial ID or verification of driver with an

Access Card, so that both card, face, car colour and license plate have to match in

• rder for boom to open.
• Log of number, date, time, lane & image of all vehicles enter/exit the facility;
• Audio Alarm if a wanted / prohibited vehicle detected
• Recording vehicle load and overall view as an option.

Slide 37

“Looking forward, I believe that innovation will play a key role in the ongoing development of the

• group. Mondi invests heavily both in

excellent people and processes to ensure that it constantly improves its value

• ffering, exceeding both customer and

shareholder expectations.….”

Message from Message From David Hathorn, CEO Of The Mondi Group

In conclusion …

Slide 38

Questions

Slide 39

License Plate Recognition License Plate Recognition License Plate Recognition License Plate Recognition (LPR), Car Colour & Facial (LPR), Car Colour & Facial (LPR), Car Colour & Facial (LPR), Car Colour & Facial Capture / ID or Verification, Capture / ID or Verification, Capture / ID or Verification, Capture / ID or Verification, possibly linked to Access Cards possibly linked to Access Cards possibly linked to Access Cards possibly linked to Access Cards

Barry T. Dudley

In conjunction with