# US 2019/0318492 A1 · Method for estimating lane information, and electronic device

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

- Number: US 2019/0318492 A1
- Document ID: US20190318492A1
- Status: Published application
- Kind: A1
- Application number: 16/469,910
- Filed: 2017-12-15
- Published: 2019-10-17
- Earliest claimed: 2016-12-23
- Assignees: Samsung Electronics Co., Ltd.
- Applicants: Samsung Electronics Co., Ltd.
- Inventors: Ji-man KIM; Chan-jong PARK; Do-jun YANG; Hyun-woo LEE
- Web page: https://patentgrep.com/patent/US20190318492A1

## CPC

- G06V 20/588: {Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road}
- B60W 50/00: Details of control systems for road vehicle drive control not related to the control of a particular sub-unit {, e.g. process diagnostic or vehicle driver interfaces}
- G06F 18/20: Analysing
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06T 7/536: from perspective effects, e.g. by using vanishing points
- G06T 7/60: Analysis of geometric attributes
- G08G 1/167: {Driving aids for lane monitoring, lane changing, e.g. blind spot detection}
- B60W 2050/0014: {Adaptive controllers}
- B60W 2420/403: Image sensing, e.g. optical camera
- B60W 2520/10: Longitudinal speed
- B60W 2552/00: Input parameters relating to infrastructure
- B60W 2552/10: Number of lanes
- B60W 2552/53: Road markings, e.g. lane marker or crosswalk
- B60W 2554/00: Input parameters relating to objects
- B60W 2554/4041: Position
- B60W 2554/802: Longitudinal distance
- B60W 2555/60: Traffic rules, e.g. speed limits or right of way
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30236: Traffic on road, railway or crossing
- G06T 2207/30256: Lane; Road marking
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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

Provided is an Artificial Intelligence (AI) system for simulating a human brain's functions, such as recognition, decision, etc., by using a machine learning algorithm such as deep learning, etc. and applications of the AI system. Provided is an electronic device including: a camera configured to capture an outside image of a vehicle, and a processor configured to execute one or more instructions stored in a memory, wherein the processor executes the one or more instructions to: determine, from the captured image, at least one object for estimating lane information; estimate, from the image, lane information of a road on which the vehicle is traveling, based on a distance between the determined at least one object and the vehicle and a vanishing point of the image; and output guide information for guiding driving of the vehicle based on the estimated lane information.

## Claims

### Claim 1

An electronic device comprising:
a camera configured to capture an outside image of a vehicle;
a memory storing one or more instructions; and
a processor configured to execute the one or more instructions stored in the memory,
wherein the processor executes the one or more instructions to:
determine, from the captured image, at least one object for estimating lane information,
estimate, from the image, lane information of a road on which the vehicle is traveling, based on a distance between the determined at least one object and the vehicle and a vanishing point of the image, and
output guide information for guiding driving of the vehicle based on the estimated lane information.

### Claim 2 (depends on 1)

The electronic device of claim 1, wherein the processor further executes the one or more instructions to:
acquire an artificial intelligence learning model based on a result obtained by using a plurality of images for a same subject to learn a relationship between the plurality of images for the same subject;
convert the captured image by using the acquired artificial intelligence learning model such that the captured image has visibility that is greater than or equal to a predetermined value; and
determine the at least one object for estimating the lane information from the converted image.

### Claim 3 (depends on 1)

The electronic device of claim 1, wherein the processor further executes the one or more instructions to:
determine a road area from the captured image;
acquire information about the number of lanes of a road on which the vehicle is traveling, based on position information of the vehicle;
estimate a lane width from the image, based on a distance between the determined at least one object and the vehicle, the determined road area, and the information about the number of lanes; and
estimate the lane information from the image, based on the estimated lane width and the vanishing point of the image.

### Claim 4 (depends on 1)

The electronic device of claim 1, wherein the processor further executes the one or more instructions to:
determine a traveling center line of the vehicle;
estimate, when the determined at least one object includes a first front vehicle located on the traveling center line, a first lane width of a first lane on which the vehicle is traveling from the image, based on a distance between the first front vehicle and the vehicle and a vehicle width of the first front vehicle; and
estimate the lane information from the image based on the estimated first lane width and the vanishing point of the image.

### Claim 5 (depends on 4)

The electronic device of claim 4, wherein the processor further executes the one or more instructions to:
estimate, when the determined at least one object includes a second front vehicle not located on the traveling center line, a second lane width of a second lane on which the second front vehicle is traveling, based on a distance between the second front vehicle and the traveling center line, a distance between the second front vehicle and the vehicle, and a vehicle width of the second front vehicle; and
estimate the lane information based on the estimated second lane width and the vanishing point of the image.

### Claim 6 (depends on 1)

The electronic device of claim 1, further comprising a display displaying the captured image,
wherein the processor further executes the one or more instructions to:
create the guide information based on the estimated lane information and a driving speed of the vehicles, and
synthesize the created guide information with a road area of the captured image to display a result of the synthesizing on the display.

### Claim 7 (depends on 1)

The electronic device of claim 1, wherein the processor further executes the one or more instructions to:
determine whether a position of the vehicle is included in a predetermined range, based on the estimated lane information; and
output the guide information based on a result of the determining.

### Claim 8

A method comprising:
acquiring an outside image of a vehicle;
determining, from the acquired image, at least one object for estimating lane information;
estimating, from the image, lane information of a road on which the vehicle is traveling, based on a distance between the determined at least one object and the vehicle and a vanishing point of the image; and
outputting guide information for guiding driving of the vehicle based on the estimated lane information.

### Claim 9 (depends on 8)

The method of claim 8, further comprising:
learning a relationship between the plurality of images for the same subject by using a plurality of images for a same subject; and
converting the acquired image based on a result of the learning such that the acquired image has visibility that is greater than or equal to a predetermined value,
wherein the determining of the at least one object for estimating the lane information from the acquired image comprises:
determining the at least one object for estimating the lane information from the converted image.

### Claim 10 (depends on 8)

The method of claim 8, further comprising:
determining a road area from the acquired image; and
acquiring information about the number of lanes of a road on which the vehicle is traveling, based on position information of the vehicle,
wherein the estimating, from the image, of the lane information of the road on which the vehicle is traveling, based on the distance between the determined at least one object and the vehicle and the vanishing point of the image, comprises:
estimating a lane width from the image based on the distance between the determined at least one object and the vehicle, the determined road area, and the information about the number of lanes, and
estimating the lane information from the image based on the estimated lane width and the vanishing point of the image.

### Claim 11 (depends on 8)

The method of claim 8, further comprising:
determining a traveling center line of the vehicle,
wherein when the determined at least one object includes a first front vehicle located on the traveling center line, the estimating of the lane information of the road on which the vehicle is traveling from the image based on the distance between the determined at least one object and the vehicle and the vanishing point of the image comprises:
estimating, from the image, a first lane width of a first lane on which the vehicle is traveling, based on the distance between the first front vehicle and the vehicle and a vehicle width of the first front vehicle, and
estimating the lane information from the image, based on the estimated first lane width and the vanishing point of the image.

### Claim 12 (depends on 11)

The method of claim 11, wherein when the determined at least one object includes a second front vehicle not located on the traveling center line, the estimating of the lane information from the image, based on the distance between the determined at least one object and the vehicle and the vanishing point of the image comprises:
estimating, from the image, a second lane width of a second lane on which the second front vehicle is traveling, based on a distance between the second front vehicle and the traveling center line, a distance between the second front vehicle and the vehicle, and a vehicle width of the second front vehicle; and
estimating the lane information from the image based on the estimated second lane width and the vanishing point of the image.

### Claim 13 (depends on 8)

The method of claim 8, wherein the outputting of the guide information for guiding driving of the vehicle, based on the estimated lane information, comprises:
creating the guide information based on the estimated lane information and driving speed of the vehicle; and
synthesizing the created guide information with the road area of the acquired image to display a result of the synthesizing.

### Claim 14 (depends on 8)

The method of claim 8, wherein the outputting of the guide information for guiding driving of the vehicle, based on the estimated lane information, comprises:
determining whether a position of the vehicle is included in a predetermined range, based on the estimated lane information; and
outputting the guide information based on a result of the determining.

### Claim 15 (depends on 8)

A computer-readable recording medium storing a program for executing the method of claim 8 on a computer.
