Electronic toll management and vehicle identification

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.

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.

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.