Tolling System Reducing Manual Review via Mobile Device Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current toll systems require extensive manual review of license plate images due to high error rates in automated image recognition, especially with diverse specialty plate designs, resulting in substantial costs and inefficiencies.
Innovation Solution
A method where a vehicle's mobile device reports its location and time of passing through a tolling location to a tolling server, allowing for accurate correlation of license plate images with vehicle accounts, reducing the need for manual review by using geofencing and inertial measurements to determine lane changes and crossing times.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated optical character recognition is used to identify license plate numbers, then processing speed increases, but recognition accuracy decreases due to diverse specialty plate designs
Solution Approach 1:
The patent introduces an intermediary verification process where human operators review a subset of license plate images to verify automated recognition accuracy. This intermediary layer allows the system to maintain high processing speed through automation while correcting errors through selective human verification, resolving the contradiction between speed and accuracy.
Solution Approach 2:
The system dynamically adjusts the verification threshold and sampling rate based on confidence levels. When automated recognition confidence is high, the system processes images quickly without human review. When confidence is low or plate designs are complex, the system increases human verification intensity, thereby adapting the balance between processing speed and accuracy to specific conditions.
2Measurement precision
If manual review of all license plate images is performed, then recognition accuracy is maintained, but operational costs and time consumption increase substantially
Solution Approach 1:
Instead of requiring complete manual review of all license plate images, the system implements partial review by selecting only a representative sample for human verification. This partial action approach maintains sufficient accuracy for toll assessment while dramatically reducing the time and resources required compared to full manual review.
Solution Approach 2:
The automated recognition system performs the primary function of identifying license plate numbers independently. Human operators are only involved when the automated system encounters uncertainty or edge cases, allowing the system to serve itself in the majority of routine situations and eliminating the need for extensive manual intervention.
3Loss of energy
If selective manual review is implemented, then operational costs are reduced, but the complexity of the review process increases
Solution Approach 1:
The system incorporates feedback mechanisms where human reviewers provide corrections and confidence assessments that feed back into the automated recognition system. This feedback loop allows the system to learn from human expertise and improve its automated decision-making, reducing the need for complex review processes while maintaining accuracy.
Solution Approach 2:
The system performs preliminary automated recognition and classification of license plate images before human review is required. By pre-processing images to identify clear, unambiguous cases that can be automatically processed, the system reduces the complexity of human review by presenting operators only with challenging cases that require their expertise.
Data Source
AI summary
A tolling system is operable to reduce the number of manual reviews of a toll point images needed to process toll fee charges by separately reporting from both toll points and mobile device in vehicles running a tolling application program the lane and crossing time when traversing a toll point. A tolling service can match records produced by the toll points with records providing by the mobile device when the toll point cannot immediately determine the identity of the toll customer passing through the toll point.