# US 11,908,165 B2 · Systems and methods for calibrating image capturing models

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

- Number: US 11,908,165 B2
- Document ID: US11908165B2
- Status: Granted
- Kind: B2
- Application number: 17/535,153
- Filed: 2021-11-24
- Published: 2022-03-17
- Granted: 2024-02-20
- Earliest claimed: 2020-03-12
- Assignees: BNSF Railway Company
- Applicants: BNSF Railway Company
- Inventors: Darrell R. Krueger; Garrett Smitley
- Web page: https://patentgrep.com/patent/US11908165B2

## CPC

- G06T 7/80: Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- H04N 17/002: {for television cameras}
- G01C 25/00: Manufacturing, calibrating, cleaning, or repairing instruments or devices referred to in the other groups of this subclass (testing, calibrating or compensating compasses G01C17/38)
- G06T 7/97: {Determining parameters from multiple pictures (depth or shape recovery from multiple images G06T7/55; stereo camera calibration G06T7/85)}
- G06T 2207/30252: Vehicle exterior; Vicinity of vehicle
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S)

## Abstract

In one embodiment, a method includes capturing, by a camera of an image capturing module, a first image of a target. The image capturing module and a drum are attached to a fixture and the target is attached to the drum. The method also includes determining a number of lateral pixels in a lateral pitch distance of the image of the target, determining a lateral object pixel size based on the number of lateral pixels, and determining a drum encoder rate based on the lateral object pixel size. The drum encoder rate is programmed into a drum encoder. The method further includes capturing, by the camera, a second image of the target while the target is rotated about an axis of the drum, determining a number of longitudinal pixels in a longitudinal pitch distance of the second image, and comparing the number of lateral pixels to the number of longitudinal pixels.

## Claims

### Claim 1

A system for field calibration of an image capture module, comprising:
a vehicle having a beam for orienting components of the system for field calibration while the vehicle is in motion; and
an image capture module operably coupled to the beam, comprising:
a camera configured to capture images of a target disposed proximate railroad tracks; and
a memory configured to store the captured images of the target;
wherein the image capture module is configured to perform the field calibration of the image capture module by:
capturing, via the camera, a first image of a target;
initializing a vehicle encoder operably coupled to the vehicle with a vehicle encoder rate;
adjusting a contrast between two pixels identifying the boundary of light and dark portions of target;
comparing the number of lateral pixels to the number of longitudinal pixels; and
adjusting the vehicle encoder rate until the number of lateral pixels matches the number of longitudinal pixels.

### Claim 2 (depends on 1)

The system of claim 1, wherein the target includes a calibration pattern.

### Claim 3 (depends on 2)

The system of claim 2, wherein the calibration pattern has a pitch between 0.375 inch and 2.0 inches.

### Claim 4 (depends on 2)

The system of claim 2, wherein the calibration pattern includes units with an unequal length-to-width ratio.

### Claim 5 (depends on 1)

The system of claim 1, wherein the vehicle encoder rate is a number of electrical pulses generated by vehicle encoder in one revolution of a shaft of the vehicle encoder.

### Claim 6 (depends on 1)

The system of claim 1, wherein the contrast is adjusted by unlocking the focus.

### Claim 7 (depends on 1)

The system of claim 1, wherein the vehicle encoder is a timing device used to measure axle rotation.

### Claim 8 (depends on 1)

The system of claim 1, wherein the vehicle encoder is a rotary encoder.

### Claim 9

A method for field calibration of an image capture module, comprising:
capturing, via an image capture module operably coupled to a beam of a vehicle, a first image of a target disposed proximate railroad tracks;
initializing a vehicle encoder operably coupled to the vehicle with a vehicle encoder rate;
capturing, via the image capture module, a second image of the target while the vehicle is moved over the target;
receiving image adjustments adjusting a contrast between two pixels to identify the boundary of light and dark portions of target;
comparing the number of lateral pixels to the number of longitudinal pixels; and
adjusting the vehicle encoder rate until the number of lateral pixels matches the number of longitudinal pixels.

### Claim 10 (depends on 9)

The method of claim 9, wherein the target includes a calibration pattern.

### Claim 11 (depends on 10)

The method of claim 10, wherein the calibration pattern has a pitch between 0.375 inch and 2.0 inches.

### Claim 12 (depends on 10)

The method of claim 10, wherein the calibration pattern includes units with an unequal length-to-width ratio.

### Claim 13 (depends on 9)

The method of claim 9, wherein the vehicle encoder rate is a number of electrical pulses generated by vehicle encoder in one revolution of a shaft of the vehicle encoder.

### Claim 14 (depends on 9)

The method of claim 9, wherein the contrast is adjusted by unlocking the focus.

### Claim 15 (depends on 9)

The method of claim 9, wherein image capture module includes a camera configured to capture the images.

### Claim 16 (depends on 9)

The method of claim 9, wherein image capture module includes a plurality of cameras configured to capture the images of the target from different angles.

### Claim 17

A system for calibrating image capturing modules, comprising:
a camera array for acquiring at least one image sequence of each item;
a memory for storing the acquired images and information for each image; and
a processor configured to calibrate image capturing modules by performing the steps of:
capturing, by the camera array, a first image of a target attached to a drum;
determining a number of lateral pixels in a lateral pitch distance of the first image of the target;
determining a lateral object pixel size based on the number of lateral pixels;
determining a drum encoder rate based on the lateral object pixel size, wherein the drum encoder rate is programmed into a drum encoder attached to the drum; and
calculating a vehicle encoder rate based on the drum encoder rate.

### Claim 18 (depends on 17)

The system of claim 17, further comprising capturing, by the camera of the image capturing module, a second image of the target while the target is rotated about an axis of the drum.

### Claim 19 (depends on 18)

The system of claim 18, further comprising determining a number of longitudinal pixels in a longitudinal pitch distance of the second image.

### Claim 20 (depends on 19)

The system of claim 19, further comprising comparing the number of lateral pixels to the number of longitudinal pixels.

### Claim 21 (depends on 20)

The system of claim 20, further comprising determining, in response to comparing the number of lateral pixels to the number of longitudinal pixels, that the number of lateral pixels matches the number of longitudinal pixels.

### Claim 22 (depends on 21)

The system of claim 21, further comprising programming the vehicle encoder rate into a vehicle encoder attached to a wheel of the vehicle.

### Claim 23 (depends on 22)

The system of claim 22, further comprising:
capturing, by the camera of the image capturing module, a third image of the target while the target is rotated about an axis of the drum;
determining a number of longitudinal pixels in a longitudinal pitch distance of the third image; and
comparing the number of lateral pixels to the number of longitudinal pixels in the longitudinal pitch distance of the third image.