# US 2026/0087795 A1 · Apparatuses for driving assistance and methods for driving assistance

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

- Number: US 2026/0087795 A1
- Document ID: US20260087795A1
- Status: Published application
- Kind: A1
- Application number: 19/409,983
- Filed: 2025-12-05
- Published: 2026-03-26
- Earliest claimed: 2022-12-23
- Assignees: Hl Klemove Corp.
- Applicants: HL Klemove Corp.
- Inventors: Hanshin CHO
- Web page: https://patentgrep.com/patent/US20260087795A1

## CPC

- G06V 10/98: Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
- G06V 10/803: {of input or preprocessed data}
- G06V 20/588: {Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road}
- G07C 5/02: Registering or indicating driving, working, idle, or waiting time only (apparatus forming part of taximeters G07B13/00)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G07C: TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE

## Abstract

Methods and apparatuses for driving assistance. In one example, an apparatus for driving assistance includes at least one memory and at least one processor. The at least one processor acquires behavior data of a vehicle from at least one behavior sensor provided in the vehicle, wherein the behavior data include a yaw rate of the vehicle, acquires image sensor information based on image data acquired from at least one camera provided in the vehicle, identifies a curvature of a lane line based on the image data, compares the identified curvature of the lane line with a corresponding yaw rate value derived from the yaw rate, when the curvature is greater than the corresponding yaw rate value, corrects the identified curvature in a decreasing direction, and when the curvature is smaller than the corresponding yaw rate value, corrects the identified curvature in an increasing direction.

## Claims

### Claim 1

An apparatus for driving assistance, the apparatus comprising:
at least one memory; and
at least one processor configured to:
acquire behavior data of a vehicle from at least one behavior sensor provided in the vehicle, wherein the behavior data include a yaw rate of the vehicle;
acquire image sensor information based on image data acquired from at least one camera provided in the vehicle, wherein the image sensor information includes lane line information;
identify a curvature of a lane line based on the image data;
compare the identified curvature of the lane line with a corresponding yaw rate value derived from the yaw rate;
when the curvature is greater than the corresponding yaw rate value, correct the identified curvature in a decreasing direction; and
when the curvature is smaller than the corresponding yaw rate value, correct the identified curvature in an increasing direction.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the processor is further configured to identify a time delay in the image data based on the behavior data, and compensate for the time delay before comparing the identified curvature with the corresponding yaw rate value.

### Claim 3 (depends on 2)

The apparatus of claim 2, wherein the processor is further configured to compensate for the time delay by comparing a steering point derived from the image sensor information with a steering point derived from the yaw rate and a steering angle included in the behavior data.

### Claim 4 (depends on 1)

The apparatus of claim 1, wherein the behavior data further comprises data on at least one of a steering angle of the vehicle, a steering speed of the vehicle, and a wheel speed of the vehicle.

### Claim 5 (depends on 1)

The apparatus of claim 1, wherein the processor is further configured to determine whether a lane in which the vehicle is traveling is curved based on the behavior data before performing the comparison and correction.

### Claim 6 (depends on 1)

The apparatus of claim 1, wherein the processor is further configured to transmit the lane line information that includes information on the corrected curvature, to a driving assistance system configured to perform at least one of lane departure warning, lane keeping assist, and adaptive cruise control.

### Claim 7

An apparatus for driving assistance, the apparatus comprising:
at least one memory; and
at least one processor configured to:
acquire behavior data of a vehicle from at least one behavior sensor provided in the vehicle;
acquire image sensor information based on image data from at least one camera provided in the vehicle;
identify a curvature of a lane line from lane line information included in the image sensor information;
identify an error in the lane line information included in the image sensor information;
calculate a first reliability for the behavior data and a second reliability for the image sensor information;
when the first reliability is greater than the second reliability, correct the identified curvature of the lane line by:
comparing the identified curvature determined with a corresponding yaw rate value derived from the behavior data;
correcting the identified curvature in a decreasing direction when the curvature is greater than the corresponding yaw rate value; and
correcting the identified curvature in an increasing direction when the curvature is smaller than the corresponding yaw rate value.

### Claim 8 (depends on 7)

The apparatus of claim 7, wherein the processor is further configured to:
determine a first weight assigned to the behavior data and a second weight assigned to the image sensor information based on the calculated first reliability and the calculated second reliability; and
apply the first weight and the second weight when correcting the curvature.

### Claim 9 (depends on 7)

The apparatus of claim 7, wherein the processor is configured to continuously calculate the first reliability and the second reliability during vehicle operation, and wherein the correction is dynamically adjusted based on changes in the first reliability and the second reliability.

### Claim 10 (depends on 7)

The apparatus of claim 7, wherein the first reliability being greater than the second reliability requires that a difference between the first reliability and the second reliability exceeds a predetermined threshold value.

### Claim 11

An apparatus for driving assistance, the apparatus comprising:
at least one memory; and
at least one processor configured to:
acquire behavior data of a vehicle from at least one behavior sensor provided in the vehicle, wherein the behavior data include at least one of a steering angle, a steering speed, a yaw rate, and a wheel speed;
acquire image sensor information based on image data from at least one camera provided in the vehicle, wherein the image sensor information includes lane line information and road boundary information;
determine whether a lane in which the vehicle is traveling is curved based on at least one of the behavior data and the road boundary information;
when the lane is curved, identify a curvature of a lane line based on the image data, and determine whether the identified curvature corresponds to the behavior data;
when the identified curvature does not correspond to the behavior data, correct the identified curvature based on the behavior data, the image sensor information, and yaw rate information, by performing:
comparing the identified curvature with a corresponding yaw rate value; and
adjusting the identified curvature in a decreasing direction when the identified curvature is greater than the corresponding yaw rate value, or in an increasing direction when the identified curvature is smaller than the corresponding yaw rate value.

### Claim 12 (depends on 11)

The apparatus of claim 11, wherein the road boundary information includes curvature information of at least one of a median strip, a barrier, a fence, and a curb recognized from the image data.

### Claim 13 (depends on 11)

The apparatus of claim 11, wherein the processor is further configured to, in determining of whether the lane is curved:
determine a first curvature indicator based on the behavior data;
determine a second curvature indicator based on the road boundary information; and
determine that the lane is curved when at least one of the first curvature indicator and the second curvature indicator exceeds a predetermined threshold.

### Claim 14

A method for driving assistance, the method comprising:
acquiring behavior data of a vehicle from at least one behavior sensor provided in the vehicle, wherein the behavior data include a yaw rate of the vehicle;
acquiring image sensor information based on image data from at least one camera provided in the vehicle, wherein the image sensor information includes lane line information;
identifying a curvature of a lane line based on the image data;
comparing the identified curvature of the lane line with a corresponding yaw rate value derived from the yaw rate;
when the identified curvature is greater than the corresponding yaw rate value, correcting the identified curvature in a decreasing direction; and
when the identified curvature is smaller than the corresponding yaw rate value, correcting the identified curvature in an increasing direction.

### Claim 15 (depends on 14)

The method of claim 14, further comprising identifying a time delay in the image data based on the behavior data, and compensating for the time delay before comparing the curvature with the corresponding yaw rate value.

### Claim 16 (depends on 14)

The method of claim 14, further comprising determining whether a lane in which the vehicle is traveling is curved based on the behavior data, and wherein the comparing and correcting are performed only when the lane is determined to be curved.

### Claim 17 (depends on 14)

The method of claim 14, wherein the behavior data further comprises data on at least one of a steering angle, a steering speed, and a wheel speed, and wherein the corresponding yaw rate value is derived from the yaw rate and the steering angle.

### Claim 18

A method for driving assistance, the method comprising:
acquiring behavior data of a vehicle from at least one behavior sensor provided in the vehicle;
acquiring image sensor information based on image data from at least one camera provided in the vehicle;
identifying a curvature of a lane line from lane line information included in the image sensor information;
calculating a first reliability for the behavior data and a second reliability for the image sensor information;
determining whether the first reliability is greater than the second reliability;
when the first reliability is greater than the second reliability:
comparing the identified curvature with a corresponding yaw rate value derived from the behavior data;
correcting the identified curvature in a decreasing direction when the identified curvature is greater than the corresponding yaw rate value; and
correcting the identified curvature in an increasing direction when the identified curvature is smaller than the corresponding yaw rate value; and
when the second reliability is greater than the first reliability, maintaining the identified curvature or applying reduced correction based on the corresponding yaw rate value.

### Claim 19 (depends on 18)

The method of claim 18, further comprising:
determining a first weight assigned to the behavior data and a second weight assigned to the image sensor information based on the calculated first reliability and the calculated second reliability; and
applying the first weight to a yaw rate-based correction component and the second weight to an image-based curvature component when correcting the curvature.

### Claim 20 (depends on 18)

The method of claim 18, wherein the correcting of the curvature when the first reliability is greater than the second reliability further comprises:
calculating a correction amount based on a difference between the identified curvature and the corresponding yaw rate value;
adjusting the correction amount based on a ratio of the first reliability to the second reliability; and
applying the adjusted correction amount to the identified curvature.
