Driver assistance apparatus and driver assistance method

Patent metadata

Field	Value
Publication number	US-12573207-B2
Application number	US-202318181770-A
Country	US
Kind code	B2
Filing date	Mar 10, 2023
Priority date	Mar 10, 2022
Publication date	Mar 10, 2026
Grant date	Mar 10, 2026

Abstract

Disclosed herein is a driver assistance apparatus including a camera installed on a vehicle, having a forward field of view of the vehicle, and configured to acquire image data and a processor configured to process the image data. The processor may acquire image data of road guide signs from the image data and identify a position of the vehicle based on the image data of the road guide signs.

First claim

What is claimed is:

1 . A driver assistance apparatus comprising:
a camera installed on a vehicle, having a forward field of view of the vehicle, and configured to acquire image data; and a processor configured to process the image data, wherein the processor is configured to: acquire image data of road guide signs from the image data; extract a feature region from the image data of the road guide signs; and identify a road number, a regional name, and a distance to a junction based on the image data of the feature region; and identify a position of the vehicle based on the image data of the road guide signs, including a road number, a regional name, and a distance to a junction; identify a position of the junction based on the road number and the regional name; and
identify, as the position of the vehicle, a position moved from the position of the junction along a road of the road number as much as the distance to the junction; and
identify a position of the vehicle based on an output signal of a global navigation satellite system (GNSS) signal receiver of the vehicle; and identify a position of the vehicle based on the image data of the road guide signs based on a reception intensity of a GNSS signal of the GNSS signal receiver being smaller than or equal to a reference intensity.

2 . The driver assistance apparatus of claim 1 , wherein the processor is configured to:
train a learning model based on the position of the vehicle based on the output signal of the GNSS signal receiver and the image data; and identify a position of the vehicle using the trained learning model based on the signal intensity of the GNSS signal of the GNSS signal receiver being smaller than or equal to the reference intensity.

3 . The driver assistance apparatus of claim 2 , wherein the processor is configured to:
acquire a feature region from the image data of the road guide signs using the trained learning model; and identify the position of the vehicle based on image data of the feature region using the trained learning model.

4 . The driver assistance apparatus of claim 2 , wherein the learning model includes a convolutional neural network (CNN), and
the processor is configured to: input the image data into the CNN; identify an estimated position of the vehicle based on an output of the CNN; and train the CNN based on an error between the position of the vehicle based on the output signal of the GNSS signal receiver and the estimated position.

5 . The driver assistance apparatus of claim 2 , wherein the learning model includes a convolutional neural network (CNN), and
the processor is configured to: input the image data into the trained CNN; and identify a position of the vehicle based on an output of the trained CNN.

6 . A driver assistance method comprising:
acquiring image data through a camera having a forward field of view of a vehicle; acquiring image data of road guide signs from the image data; extracting a feature region from the image data of the road guide signs; identifying a road number, a regional name, and a distance to a junction based on the image data of the feature region; and identifying a position of the vehicle based on the image data of the road guide signs, including a road number, a regional name, and a distance to a junction; identifying a position of a junction based on the road number and the regional name; and identifying, as the position of the vehicle, a position moved from the position of the junction along a road of the road number as much as the distance to the junction; and identifying a position of the vehicle based on an output signal of a global navigation satellite system (GNSS) signal receiver of the vehicle; and identifying a position of the vehicle based on the image data of the road guide signs based on a reception intensity of a GNSS signal of the GNSS signal receiver being smaller than or equal to a reference intensity.

7 . The driver assistance method of claim 6 , wherein the identifying of the position of the vehicle includes:
training a learning model based on the position of the vehicle based on the output signal of the GNSS signal receiver and the image data; and identifying a position of the vehicle using the trained learning model based on the reception intensity of the GNSS signal of the GNSS signal receiver being smaller than or equal to the reference intensity.

8 . The driver assistance method of claim 7 , wherein the identifying of the position of the vehicle includes:
acquiring a feature region from the image data of the road guide signs using the trained learning model; and identifying a position of the vehicle based on image data of the feature region using the trained learning model.

9 . The driver assistance method of claim 7 , wherein the learning model includes a convolutional neural network (CNN), and
the training of the learning model includes: inputting the image data into the CNN; identifying an estimated position of the vehicle based on an output of the CNN; and training the CNN based on an error between the position of the vehicle based on the output signal of the GNSS signal receiver and the estimated position.

10 . The driver assistance method of claim 7 , wherein the learning model includes a convolutional neural network (CNN), and
the identifying of the position of the vehicle includes: inputting the image data into the trained CNN; and identifying a position of the vehicle based on an output of the trained CNN.

11 . A driver assistance apparatus comprising:
a camera installed on a vehicle, having a forward field of view of the vehicle, and configured to acquire image data; and a processor configured to process the image data, wherein the processor is configured to: acquire image data of road guide signs from the image data; identify a first position of the vehicle based on the image data of the road guide signs, including identifying a road number, a regional name, and a distance to a junction based on the image data of the road guide signs, identifying a position of the junction based on the road number and the regional name, and identifying, as the first position, a position moved from the position of the junction along a road of the road number as much as the distance to the junction; and identify a position of the vehicle based on an output signal of a global navigation satellite system (GNSS) receiver of the vehicle; and identify the first position of the vehicle based on the image data of the road guide signs based on a reception intensity of a GNSS signal of the GNSS receiver being smaller than or equal to a reference intensity; and identify a second position of the vehicle based on a comparison between a landmark in a high-definition map and object data detected by one or more sensors of the vehicle.

12 . The driver assistance apparatus of claim 11 ,
wherein the object data is generated by sensor fusion of at least two types selected from the group consisting of image data from the camera, radar data, and LiDAR data.

13 . The driver assistance apparatus of claim 11 ,
wherein the landmark in the high-definition map comprises at least one of a road guide sign, a lane line, a traffic light, or a building.

14 . The driver assistance apparatus of claim 11 ,
wherein the processor is configured to compare a relative position of the detected object data with a relative position of a landmark in the high-definition map within a predetermined position error range.

15 . The driver assistance apparatus of claim 11 ,
wherein the processor is confi

Assignees

• Hl Klemove Corp

Inventors

• Kim Daejong

Classifications

• G01S19/485

  whereby the further system is an optical system or imaging system · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T7/70

  Determining position or orientation of objects or cameras (camera calibration G06T7/80) · CPC title

• B60W2556/50

  of positioning data, e.g. GPS [Global Positioning System] data · CPC title