# US 2019/0378347 A1 · Architectures for vehicle tolling

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0378347 A1
- Document ID: US20190378347A1
- Status: Published application
- Kind: A1
- Application number: 16/437,315
- Filed: 2019-06-11
- Published: 2019-12-12
- Earliest claimed: 2018-06-11
- Assignees: Raytheon Company
- Applicants: Raytheon Company
- Inventors: Jacob W. Gallaway; Nathan D. Davis; Jeremy J. Gerhart
- Web page: https://patentgrep.com/patent/US20190378347A1

## CPC

- G07B 15/06: Arrangements for road pricing or congestion charging of vehicles or vehicle users, e.g. automatic toll systems
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06Q 20/102: {Bill distribution or payments}
- G06V 20/62: Text, e.g. of license plates, overlay texts or captions on TV images
- G08G 1/015: with provision for distinguishing between two or more types of vehicles, e.g. between motor-cars and cycles
- G08G 1/0175: {by photographing vehicles, e.g. when violating traffic rules}
- G07B: TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93})

## Abstract

Generally discussed herein are systems, devices, and methods for improved automatic toll generation. A system can include one or more cameras positioned to capture images of vehicles passing through a toll station, vehicle detection and classification circuitry to receive an image of a vehicle from the one or more cameras and execute a first machine learning (ML) model to classify the vehicle, axle count circuitry to, in response to receiving data from the vehicle detection and classification circuitry that a vehicle was detected, execute a second ML model to classify a number of axles of the vehicle for determining a toll charge, and toll circuitry to issue the toll charge based on the classified number of axles.

## Claims

### Claim 1

A system comprising:
one or more cameras positioned to capture images of vehicles passing through a toll station;
vehicle detection and classification circuitry to receive an image of a vehicle from the one or more cameras and execute a first machine learning (ML) model to classify the vehicle;
axle count circuitry to, in response to receiving data from the vehicle detection and classification circuitry that a vehicle was detected, execute a second ML model to classify a number of axles of the vehicle for determining a toll charge; and
toll circuitry to issue the toll charge based on the classified number of axles.

### Claim 2 (depends on 1)

The system of claim 1 further comprising license plate detection circuitry to execute a third ML model to identify a license plate in an image of the captured images.

### Claim 3 (depends on 2)

The system of claim 2, further comprising character recognition circuitry to execute a fourth ML model to identify a license plate number on the license plate.

### Claim 4 (depends on 3)

The system of claim 3, wherein:
the character recognition circuitry is further to provide the license plate number to the toll circuitry; and
the toll circuitry is to issue the toll charge to an owner of the vehicle as determined further based on the license plate number.

### Claim 5 (depends on 4)

The system of claim 4, wherein the toll circuitry is to issue a query including the identified license plate number to a vehicle owner information database and receive data identifying the owner of the vehicle is provided to the toll circuitry in response to the query.

### Claim 6 (depends on 2)

The system of claim 2, wherein the license plate detection circuitry is to retrieve an image captured by the one or more cameras in response to receiving data from the vehicle detection and classification circuitry indicating the vehicle was detected.

### Claim 7 (depends on 1)

The system of claim 1, wherein the vehicle detection and classification circuitry is further to classify a height, length, or type of the detected vehicle, wherein the type includes a car, motorcycle, or truck.

### Claim 8 (depends on 3)

The system of claim 3, wherein the first, second, third, and fourth ML models include convolutional neural networks.

### Claim 9

A method for issuing a toll charge, the method comprising:
capturing, by one or more cameras, images of vehicles passing through a toll station;
receiving, by vehicle detection and classification circuitry, an image of a vehicle from the one or more cameras and execute a first machine learning (ML) model to classify the vehicle;
executing, by axle count circuitry and in response to receiving data from the vehicle detection and classification circuitry indicating that a vehicle was detected, a second ML model to classify a number of axles of the vehicle for determining a toll charge; and
issuing, by toll circuitry, the toll charge based on the classified number of axles.

### Claim 10 (depends on 1)

The method of claim 1 further comprising executing, by license plate detection circuitry, a third ML model to identify a license plate in an image of the captured images.

### Claim 11 (depends on 10)

The method of claim 10, further comprising executing, by character recognition circuitry, a fourth ML model to identify a license plate number on the license plate.

### Claim 12 (depends on 11)

The method of claim 11, further comprising:
providing, by the character recognition circuitry, the license plate number to the toll circuitry; and
issuing, by the toll circuitry, the toll charge to an owner of the vehicle as determined further based on the license plate number.

### Claim 13 (depends on 12)

The method of claim 12, further comprising issuing, by the toll circuitry, a query including the identified license plate number to a vehicle owner information database and information identifying the owner of the vehicle is provided to the toll circuitry in response to the query.

### Claim 14 (depends on 10)

The method of claim 10, further comprising retrieving, by the license plate detection circuitry, an image captured by the one or more cameras in response to receiving data from the vehicle detection and classification circuitry indicating the vehicle was detected.

### Claim 15 (depends on 9)

The method of claim 9, further comprising classifying, by the vehicle detection and classification circuitry, a height, length, or type of the detected vehicle, wherein the type includes a car, motorcycle, or truck.

### Claim 16

A non-transitory machine-readable medium including instructions that, when executed by a machine, cause the machine to perform operations for improved automatic toll generation, the operations comprising:
receiving an image of a vehicle from the one or more cameras and execute a first machine learning (ML) model to classify the vehicle;
executing, in response to receiving data indicating that a vehicle was detected, a second ML model to classify a number of axles of the vehicle for determining a toll charge; and
issuing the toll charge based on the classified number of axles.

### Claim 17 (depends on 16)

The non-transitory machine-readable medium of of claim 16, wherein the operations further comprise executing a third ML model to identify a license plate in an image of the captured images.

### Claim 18 (depends on 17)

The non-transitory machine-readable medium of claim 17, wherein the operations further comprise executing a fourth ML model to identify a license plate number on the license plate.

### Claim 19 (depends on 18)

The non-transitory machine-readable medium of claim 18, wherein the operations further comprise:
providing the license plate number to the toll circuitry; and
issuing the toll charge to an owner of the vehicle as determined further based on the license plate number.

### Claim 20 (depends on 18)

The non-transitory machine-readable medium of claim 18, wherein the first, second, third, and fourth ML models include convolutional neural networks.