Electronic toll management and vehicle identification

• US 8,265,988 B2
• Filed: 05/23/2011
• Issued: 09/11/2012
• Est. Priority Date: 02/21/2003
• Status: Expired due to Term

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture Global Services Limited (Accenture PLC)
• Inventors: Hedley, Jay E., Thornburg, Neal Patrick
• Primary Examiner(s): Wu, Rutao
• Application Number:
  US13/113,125
• Publication Number:
  US 20110288909A1
• Time in Patent Office: 477 Days
• Field of Search: None
• US Class Current: 705/13
• CPC Class Codes: G06Q 30/0283 Price estimation or determination
• CPC Class Codes: G06Q 50/40 Business processes related to the transportation industry shipping G06Q10/083
• CPC Class Codes: G06V 20/62 Text, e.g. of license plates, overlay texts or captions on TV images
• CPC Class Codes: G07B 15/06 Arrangements for road pricing or congestion charging of vehicles or vehicle users, e.g. automatic toll systems
• CPC Class Codes: G08G 1/017 identifying vehicles G08G1/015, G08G1/054 take precedence

Abstract

Identifying a vehicle in a toll system includes accessing image data for a first vehicle and obtaining license plate data from the accessed image data for the first vehicle. A set of records is accessed. Each record includes license plate data for a vehicle. The license plate data for the first vehicle is compared with the license plate data for vehicles in the set of records. Based on the results of the comparison of the license plate data, a set of vehicles is identified from the vehicles having records in the set of records. Vehicle fingerprint data is accessed for the first vehicle. The vehicle fingerprint data for the first vehicle is based on the image data for the first vehicle. Vehicle fingerprint data for a vehicle in the set of vehicles is accessed. Using a processing device, the vehicle fingerprint data for the first vehicle is compared with the vehicle fingerprint data for the vehicle in the set of vehicles. The vehicle in the set of vehicles is identified as the first vehicle based on results of the comparison of vehicle fingerprint data.

Claims

1. A computer-implemented method of identifying a vehicle in a toll system, the method comprising:

accessing image data for a first vehicle;

obtaining license plate data from the accessed image data for the first vehicle;

accessing a set of records, each record including license plate data for a vehicle;

executing, using at least one processing device, a loosened license plate reading algorithm to;

compare the license plate data for the first vehicle with the license plate data for vehicles in the set of records, and

identify a set of vehicle candidates from the vehicles having records in the set of records, the set of vehicle candidates being identified based on results of the comparison of the license plate data, wherein the loosened license plate reading algorithm includes loosened license plate matching criteria or a lowered license plate read confidence threshold to enable generation of a larger set of matching vehicle candidates relative to a license plate reading algorithm designed to identify a single and best vehicle candidate match; and

selecting, from the set of vehicle candidates, a vehicle candidate as corresponding to the first vehicle by;

accessing vehicle fingerprint data for the first vehicle, the vehicle fingerprint data for the first vehicle being based on the accessed image data for the first vehicle,

accessing vehicle fingerprint data for the vehicle candidate in the set of vehicle candidates,

comparing, using the at least one processing device, the vehicle fingerprint data for the first vehicle with the vehicle fingerprint data for the vehicle candidate in the set of vehicle candidates, and

identifying the vehicle candidate in the set of vehicle candidates as the first vehicle based on results of the comparison of vehicle fingerprint data.

2. The method of claim 1, wherein the loosened license plate reading algorithm is optimized to identify at least two vehicle candidates as corresponding to the first vehicle to thereby enable selection from among the identified at least two vehicle candidates through use of vehicle fingerprint data.

3. The method of claim 1, wherein the loosened license plate reading algorithm comprises an algorithm that reads a license plate number of a target vehicle from an image of the target vehicle and compares the license plate number read from the image to known license plate numbers of vehicles to identify a set of matching vehicle candidates for the target vehicle.

4. The method of claim 1, wherein the loosened license plate reading algorithm is configured to generate a larger set of matching vehicle candidates by lowering the read confidence threshold used by the algorithm to determine whether a read result is designated as corresponding to a matching vehicle candidate.

5. The method of claim 1, wherein the loosened license plate reading algorithm is configured to generate a larger set of matching vehicle candidates by requiring a license plate number of a candidate vehicle to match only a subset or a lesser number of characters in the license plate number of a target vehicle for the candidate vehicle to be included in the set of matching vehicle candidates.

6. The method of claim 1, further comprising accessing laser signature data or inductive signature data for the first vehicle.

7. The method of claim 6, wherein the laser signature data includes one or more of an overhead electronic profile of the first vehicle, an axle count of the first vehicle, and a 3D image of the first vehicle.

8. The method of claim 6, wherein the inductive signature data includes one or more of an axle count of the first vehicle, a type of engine of the first vehicle, and a vehicle type or class for the first vehicle.

9. The method of claim 6, wherein each record in the set of records includes laser signature data or inductive signature data for a vehicle.

10. The method of claim 9, further comprising comparing laser signature data or inductive signature data for the first vehicle with laser signature data or inductive signature data for vehicles in the set of records.

11. The method of claim 10, wherein identifying a set of vehicle candidates from the vehicles having records in the set of records includes identifying the set of vehicle candidates based on the results of the comparison of the license plate data and the results of the comparison of the laser signature data or the inductive signature data.

12. The method of claim 11, wherein identifying the set of vehicle candidates based on the results of the comparison of the license plate data and the results of the comparison of the laser signature data or inductive signature data includes determining a combined equivalent matching score for each vehicle having a record in the set of records and identifying the set of vehicle candidates as a set of vehicles having combined equivalent matching scores above a predetermined threshold.

13. The method of claim 12, wherein each combined equivalent matching score comprises a weighted combination of a laser or inductive signature matching score and a license plate matching score.

14. The method of claim 10, wherein identifying the vehicle candidate in the set of vehicle candidates as the first vehicle includes identifying the vehicle candidate as the first vehicle based on the results of the comparison of the vehicle fingerprint data and the results of the comparison of the laser signature data or inductive signature data.

15. The method of claim 14, wherein identifying the vehicle candidate in the set of vehicle candidates as the first vehicle based on the results of the comparison of the vehicle fingerprint data and the results of the comparison of the laser signature data or inductive signature data includes determining a combined equivalent matching score for the vehicle candidate in the set of vehicle candidates and determining that the combined equivalent matching score is higher than a predetermined threshold.

16. The method of claim 15, wherein the combined equivalent matching score comprises a weighted combination of a laser or inductive signature matching score and a vehicle fingerprint matching score.

17. The method of claim 1, wherein identifying the vehicle candidate in the set of vehicle candidates as the first vehicle includes identifying the vehicle candidate as the first vehicle if the comparison of the vehicle fingerprint data for the first vehicle with the vehicle fingerprint data for the vehicle candidate in the set of vehicle candidates indicates a match having a confidence level that exceeds a confidence threshold.

18. The method of claim 17, wherein identifying the vehicle candidate in the set of vehicle candidates as the first vehicle includes identifying the vehicle candidate in the set of vehicle candidates as the first vehicle without human intervention if the confidence level of the match exceeds a first confidence threshold.

19. The method of claim 18, wherein identifying the vehicle candidate in the set of vehicle candidates as the first vehicle includes identifying the vehicle candidate in the set of vehicle candidates as the first vehicle if the confidence level of the match is less than the first confidence threshold but greater than a second confidence threshold and a human operator confirms the match.

20. The method of claim 19, further comprising enabling the human operator to confirm or reject the match by:

enabling the human operator to perceive the accessed image data for the first vehicle, and

enabling the human operator to interact with a user interface to indicate rejection or confirmation of the match.

21. The method of claim 19, wherein identifying the vehicle candidate in the set of vehicle candidates as the first vehicle includes identifying the vehicle candidate as the first vehicle if the confidence level of the match is less than the first and second confidence thresholds and a human operator manually identifies the vehicle candidate as the first vehicle by accessing the image data for the first vehicle and the record for the vehicle in the set of records.

22. The method of claim 1, wherein identifying the vehicle candidate in the set of vehicle candidates as the first vehicle includes identifying the vehicle candidate by combining vehicle identification number (VIN), laser signature, inductive signature, and image data.

23. An apparatus for identifying a vehicle in a toll system, the apparatus comprising:

means for accessing image data for a first vehicle;

means for obtaining license plate data from the accessed image data for the first vehicle;

means for accessing a set of records, each record including license plate data for a vehicle;

means for executing a loosened license plate reading algorithm to;

compare the license plate data for the first vehicle with the license plate data for vehicles in the set of records, and

identify a set of vehicle candidates from the vehicles having records in the set of records, the set of vehicle candidates being identified based on results of the comparison of the license plate data, wherein the loosened license plate reading algorithm includes loosened license plate matching criteria or a lowered license plate read confidence threshold to enable generation of a larger set of matching vehicle candidates relative to a license plate reading algorithm designed to identify a single and best vehicle candidate match; and

means for selecting, from the set of vehicle candidates, a vehicle candidate as corresponding to the first vehicle by;

accessing vehicle fingerprint data for the first vehicle, the vehicle fingerprint data for the first vehicle being based on the accessed image data for the first vehicle,

accessing vehicle fingerprint data for the vehicle candidate in the set of vehicle candidates,

comparing, using the at least one processing device, the vehicle fingerprint data for the first vehicle with the vehicle fingerprint data for the vehicle candidate in the set of vehicle candidates, and

identifying the vehicle candidate in the set of vehicle candidates as the first vehicle based on results of the comparison of vehicle fingerprint data.

24. An apparatus for identifying a vehicle in a toll system, the apparatus comprising:

an image capture device configured to capture image data for a first vehicle; and

one or more processing devices communicatively coupled to each other and to the image capture device and configured to;

access the image data for the first vehicle;

obtain license plate data from the image data for the first vehicle;

access a set of records, each record including license plate data for a vehicle;

execute, using at least one processing device, a loosened license plate reading algorithm to;

compare the license plate data for the first vehicle with the license plate data for vehicles in the set of records, and

identify a set of vehicle candidates from the vehicles having records in the set of records, the set of vehicle candidates being identified based on results of the comparison of the license plate data, wherein the loosened license plate reading algorithm includes loosened license plate matching criteria or a lowered license plate read confidence threshold to enable generation of a larger set of matching vehicle candidates relative to a license plate reading algorithm designed to identify a single and best vehicle candidate match; and

select, from the set of vehicle candidates, a vehicle candidate as corresponding to the first vehicle by;

accessing vehicle fingerprint data for the first vehicle, the vehicle fingerprint data for the first vehicle being based on the image data for the first vehicle,

accessing vehicle fingerprint data for the vehicle candidate in the set of vehicle candidates,

comparing the vehicle fingerprint data for the first vehicle with the vehicle fingerprint data for the vehicle candidate in the set of vehicle candidates, and

identifying the vehicle candidate in the set of vehicle candidates as the first vehicle based on results of the comparison of vehicle fingerprint data.

25. A computer-implemented method of identifying a vehicle in a toll system, the method comprising:

accessing image data for a first vehicle;

obtaining license plate data from the accessed image data for the first vehicle;

accessing a set of records, each record including license plate data for a vehicle;

executing, using at least one processing device, a loosened license plate reading algorithm to;

compare the license plate data for the first vehicle with the license plate data for vehicles in the set of records, and

identify a set of vehicle candidates from the vehicles having records in the set of records, the set of vehicle candidates being identified based on results of the comparison of the license plate data, wherein the loosened license plate reading algorithm includes loosened license plate matching criteria or a lowered license plate read confidence threshold to enable generation of a larger set of matching vehicle candidates relative to a license plate reading algorithm designed to identify a single and best vehicle candidate match; and

selecting, from the set of vehicle candidates, a vehicle candidate as corresponding to the first vehicle based on an additional vehicle identifier that is distinct from license plate data.

26. The method of claim 25, wherein the loosened license plate reading algorithm is optimized to identify at least two vehicle candidates as corresponding to the first vehicle to thereby enable selection from among the identified at least two vehicle candidates through use of the additional vehicle identifier.

27. The method of claim 25, wherein the loosened license plate reading algorithm comprises an algorithm that reads a license plate number of a target vehicle from an image of the target vehicle and compares the license plate number read from the image to known license plate numbers of vehicles to identify a set of matching vehicle candidates for the target vehicle.

28. The method of claim 25, wherein the loosened license plate reading algorithm is configured to generate a larger set of matching vehicle candidates by lowering the read confidence threshold used by the algorithm to determine whether a read result is designated as corresponding to a matching vehicle candidate.

29. The method of claim 25, wherein the loosened license plate reading algorithm is configured to generate a larger set of matching vehicle candidates by requiring a license plate number of a candidate vehicle to match only a subset or a lesser number of characters in the license plate number of a target vehicle for the candidate vehicle to be included in the set of matching vehicle candidates.

30. The method of claim 25, wherein the additional vehicle identifier comprises sensor data distinct from image data that is obtained from sensors of the toll facility detecting the first vehicle.

31. The method of claim 30, wherein the sensor data comprises laser signature data or inductive signature data for the first vehicle.

32. The method of claim 25, further comprising electronically determining the additional vehicle identifier by processing the accessed image data for the first vehicle.

33. The method of claim 32, wherein the additional vehicle identifier comprises vehicle fingerprint data.