# US 10,769,815 B2 · Image processing device and image processing method

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

- Number: US 10,769,815 B2
- Document ID: US10769815B2
- Status: Granted
- Kind: B2
- Application number: 16/318,932
- Filed: 2017-07-20
- Published: 2019-08-22
- Granted: 2020-09-08
- Earliest claimed: 2016-07-21
- Assignees: Isuzu Motors Limited
- Applicants: Isuzu Motors Limited
- Inventors: Teruhiko Suzuki
- Web page: https://patentgrep.com/patent/US10769815B2

## CPC

- G06T 7/80: Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- B60W 40/04: Traffic conditions
- B60W 40/11: Pitch movement
- G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle
- G06T 2207/10016: Video; Image sequence
- G06T 2207/30256: Lane; Road marking
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- B60W: CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

The image processing device includes a scale correction unit. In a case where a difference between a width of a lane calculated by a lane-width calculation unit and a width of the lane acquired from map data is greater than a predetermined value that serves as a criterion for correcting errors, the scale correction unit corrects a correlation between a length of a subject in a captured image and the number of pixels constituting the captured image.

## Claims

### Claim 1

An image processing device comprising:
a storage unit configured to store executable instructions; and
an electronic control unit (ECU) communicatively coupled to the storage unit, the ECU configured to execute the executable instructions to:
calculate a width of a lane in which a vehicle travels from a captured image, in which a front of the vehicle in a traveling direction is captured, based on a correlation between a length of a subject in the captured image and a number of pixels constituting the captured image;
acquire information indicating a position of the vehicle;
acquire information indicating a width of the lane in which the vehicle travels, from map data, based on the information indicating the position of the vehicle; and
correct the correlation between the length of the subject in the captured image and the number of pixels constituting the captured image in a case where a difference between the width of the lane calculated from thee captured image and the width of the lane acquired from the map data is greater than a predetermined value that serves as a criterion for correcting errors.

### Claim 2 (depends on 1)

The image processing device according to claim 1,
wherein the ECU is further configured to correct the correlation between the length of the subject in the captured image and the number of pixels constituting the captured image in a case where the difference between the width of the lane calculated from thee captured image and the width of the lane acquired the map data is greater than the predetermined value for a period longer than a predetermined period.

### Claim 3 (depends on 1)

The image processing device according to claim 1,
wherein the predetermined value is determined based on the width of the lane acquired from the map data and a width of the vehicle.

### Claim 4 (depends on 3)

The image processing device according to claim 3,
wherein the predetermined value is decreased as a difference between the width of the lane acquired from the map data and the width of the vehicle is decreased.

### Claim 5

An image processing method comprising:
calculating a width of a lane in which a vehicle travels from a captured image, in which a front of the vehicle in a traveling direction is captured, based on a correlation between a length of a subject in the captured image and a number of pixels constituting the captured image;
acquiring information indicating a position of the vehicle;
acquiring information indicating a width of the lane in which the vehicle travels, from map data, based on the information indicating the position of the vehicle; and
correcting the correlation between the length of the subject in the captured image and the number of pixels constituting the captured image in a case where a difference between the calculated width of the lane and the width of the lane acquired from the map data is greater than a predetermined value that serves as a criterion for correcting errors.