Systems and applications for automatically identifying and verifying vehicle license plate data

Abstract

The present disclosure relates to systems and methods for automatically identifying and verifying vehicle license plate data. Specifically, the inventive system utilizes multiple automated data points to correlate a more accurate read of a license plate taken on roadways than systems that rely solely on Optical Character Recognition. The inventive system utilizes machine learning to automatically determine the make and model of the vehicle, which is then matched against motor vehicle records to provide for automation in the 80-90% range. The inventive system also utilizes analytics to determine if there are issues with the cameras and provides for near real time alerts to maintenance personnel.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS[0001]The present application claims benefit of and priority to U.S. Provisional Patent Application No. 62 / 909,210 filed Oct. 1, 2019, entitled “SYSTEMS AND APPLICATIONS FOR AUTOMATICALLY IDENTIFYING AND VERIFYING VEHICLE LICENSE PLATE DATA,” which is hereby incorporated by reference in its entirety as if fully set forth herein.BACKGROUNDField of the Art[0002]This disclosure relates to systems and methods for automatically identifying and verifying vehicle license plate data.Discussion of the State of the Art[0003]Using computing systems to identify vehicles by their license plate identifier (ID) is a difficult task for a variety of reasons. For example, identifying a vehicle's license plate ID on a toll road or other checkpoints is particularly difficult because vehicles tend to traverse relevant checkpoints at high speeds. Moreover, visibility at these checkpoints is constantly changing due to changes in weather, including inclement weather s...

AI Technical Summary

Benefits of technology

The present invention is a system and method for reviewing and scoring the results of an ALPR system, which is used to identify license plate numbers. The review process is automated and faster than human review, and it can be done using existing infrastructure. The system is less error-prone and can be easily implemented compared to a replacement system that uses a new set of source material. The technical effects of the invention are improved accuracy and efficiency in identifying license plate numbers.

Problems solved by technology

Using computing systems to identify vehicles by their license plate identifier (ID) is a difficult task for a variety of reasons.

For example, identifying a vehicle's license plate ID on a toll road or other checkpoints is particularly difficult because vehicles tend to traverse relevant checkpoints at high speeds.

Moreover, visibility at these checkpoints is constantly changing due to changes in weather, including inclement weather such as rain, fog, snow, etc., and changes in the location and position of various light sources throughout any given period of time.

These systems may be the best available solution, but they have significant limitations.

For example, OCR systems tend to have high failure rates when dealing with changing light conditions and weather conditions.

Moreover, these systems tend to have high failure rates when dealing with blurry images that may be caused by trying to capture vehicles that are moving at high speeds, especially in low-light situations when shutter speeds may be slow and / or image sensitivity (i.e. ISO sensitivity) settings may be high.

In other instances, failure rates of the OCR systems may be caused by the camera becoming out of focus, which, in at least some camera systems, may happen quite frequently.

The human review system is much more accurate than the OCR system, but it is nevertheless very expensive to maintain, comparatively very slow, and human-error prone.

Despite these significant drawbacks, toll administration agencies and other agencies tasked with identifying license plate information continue to use ALPR systems and human review systems despite it relatively high costs and slow review / confirmation process.

Images