seeplane i-cube presented by barry t. fryer dudley (mba {it}; msc {image analysis}
TRANSCRIPT
SeePLANE
I-Cube
Presented byBarry T. Fryer
Dudley(MBA {IT};
MSc {Image Analysis}
Frame Work of Presentation
Introduction to IA / LPR (Theory)
SeePlane
Value proposition (3 options)
Over 1,000 OCR Systems in 30 CountriesOver 1,000 OCR Systems in 30 Countries
USA
Mexico
Colombia
Brazil
Portugal Spain UK Holland Italy Hungary Poland Kazakhstan Litha Israel
China
Hong Kong
Korea
Taiwan
Thailand
Singapore
Argentina South Africa (over 100 solutions) Australia
SeePlane: System descriptionThe system consists of cameras monitoring the
weigh bridge lane. All planes passing the cameras will be recorded in terms of the time, lane, direction, plane license number (if present), if allowed to use the lane (white list) and an alarm if the plane is either not allowed to take off or over weight (black list).
SeePlane: System operationThe OCR software allows PLANES to be enrolled
into a WHITE LIST, which are listed per trip. If an unauthorised OR OVER WEIGHT plane is detected this is recorded. If a plane in the BLACK LIST is detected, an alarm will be generated.
If TWO SYSTEMS ARE INSTALLED, the plane average speed will be determined, with an alarm for those above the set average speed.
Neural networksOperating in real time, are beingutilised extensively world wide.Here I-CUBE uses NEURALNETWORKS illustrates theconcept to automatically identify a plane. The ability to automatically predictand identify planes which are overweight orspeeding saves lives.
A Word About Our EyesEyes are very good contrast adjusters, but not good for distinguishing subtle variations in colorEyes can discern about 30 continuous levels of gray or color in a field of viewEyes are not good judges of distanceEyes cannot accurately reproduce measurementsEyes can not work in the dark or 24/7
SAME SIZE???
Why do Image Analysis?Improved Precision /Accuracy in MeasurementsReproducibility of ResultsHigher Throughput than Manual MethodsBetter Definition of Contrasting AreasMore Measurements / FasterReal Time Link to Databases
Vehicle:
• Size
• Colour
• Shape
• Texture
• Grey level
1 - Capture2 – Find plane number
3 – OCR4 – Report
OCR - 5 easy steps:
5 – Alarm if overweight or speeding !
Camera/IlluminationUnits
(Up to 6 per system)
IP orFrame Grabber
PLANE Software + DLL+Sample Client Program
PC Station
Included HardwareI/O Card +Terminal Block
Power Supply for SCH
Point A
Point B
PLANE SPEEDING SYSTEM
Configuration
Possible to have
multiple cameras to cover both
sides of the planes
Database remotely updated: Planes to
be expected
Automatic Database search
(local)
Recognition Rate: 0.2 sec
PLANE
• Size
• Colour
• Shape
• No of trips per day
• Etc
Additional items possibly captured:
Adapting Gigabit Ethernet for VisionStandard packet: 1440 Bytes (56 Bytes header)
”Jumbo” packet: Max. 16224 Bytes (one 56 Bytes header)
96.1% efficiency*
99,7% efficiency*
In combination with a High Performance Driver, based on TCP/IP offload-engine, it provides higher transmission efficiency and drastically reduces CPU usage.
(High CPU overhead for sending many small packets)
(Very low CPU overhead as only one packet)
*) Comparison based on sending 16224 bytes of data
Lens
Image sensor
Digitizing Pre-processing
Timing Interface
PLC
Cat-5eEthernet cableup to 100 m
Local I/Os:-Trigger input-Results output
Illumination control
Image Processing in
PC
Illumination
(Lens IrisVideo)
Power
Acquire
100110001010001110001010011100100100011101100011001010001000
PC
PC
Possible system configurations
Point-to-point(One camera, one PC)
GigESwitch
Many-to-one(Multiple cameras, one PC)
One-to-many (broadcast)(One or several cameras, with several PCs)
Control room monitoringControl room monitoring
Additional value for the airportAdditional value for the airport
OPTIONS?OPTIONS?Capital amount @ R390, 680.67
(Install and train on how to use)
Rental option @ R9, 761.16
(5 year period)
Cost per PLANE @ R39.04
(based on 250 planes a day)
ReferencesB.T. Dudley. "Image Analysis and Waste Technology in Africa", Binary - Computers in Microbiology, 5, 3-4. (1993) B.T. Dudley, A.R. Howgrave-Graham, A.G. Bruton and F.M. Wallis. "The application of digital image analysis to quantifying and measuring UASB digester granules", Biotechnology & Bioengineering. 42, 279 - 283. (1993) Castleman, K. R. 1998. Concepts in Imaging and Microscopy: Color ImageProcessing for Microscopy. The Biological Bulletin. 194 (2): 100-107.Russ, J.C. 1995. The Image Processing Handbook. 2nd ed. CRC Press. BocaRaton, FL.Inoue, S. (1986). Video Microscopy. Plenum Press Internet: www.I-Cube.co.za
Thanks to:
Barry T. DUDLEY(MBA {IT}; MSc {Image Analysis}; BSc {Brewing}; BSc Hons {Waste Technology})
ASD (Average Speed Determination) http://www.i-cube.co.za Cell: +27 (0) 82 562 8225MADADENI PH +27 (0) 31 764-3077
82 Kloof Falls Rd Fax 0866539659Kloof, Durban, Kwa-Zulu Natal, 3610, South Africa E-mail: [email protected]
“..any sufficiently advanced technology is indistinguishable from magic.” Arthur C. Clark
Technical QUESTIONS: