IP Library Granted Patent US 12,479,428
Granted Patent B2
US 12,479,428 · App. 18/380,788 · Granted Nov 25, 2025

Vehicle control device

Inventor: Chenyu Wang (Toyota, JP)
Assignee: TOYOTA JIDOSHA KABUSHIKI KAISHA
B60W30/12B60W50/14B60W2420/403B60W2552/50B60W2554/20
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,479,428
App. No.
18/380,788
Granted
Nov 25, 2025
Kind
B2
Abstract

A vehicle control device recognizes a border of a traveling area of a vehicle based on image data acquired when a camera photographs a forward view of the vehicle, and performs at least one of a departure alarm and a departure control when the vehicle is predicted to depart from a reference line set based on the border or when the vehicle has departed from the border. Furthermore, the vehicle control device determines whether a particular registered three-dimensional object that is previously registered exists, based on the image data, and makes it easier to recognize the border in a predetermined easing area set based on the position of the registered three-dimensional object on the image data, than in a normal area on the image data other than the easing area, when it is determined that the registered three-dimensional object exists.

Claims (37)

1 . A vehicle control device comprising:

a camera that photographs a forward view of a vehicle and that acquires image data; and

a control unit that is configured to:

extract feature points in the image data;

perform fitting of the feature points to approximate lines expressed by multidimensional functions;

acquire a vote value based on numbers of the feature points on each of the approximate lines;

specify one or more of the approximate lines for each of which the vote value is equal to or more than a recognition threshold, as border candidates of a traveling area for the vehicle;

recognize a border of the traveling area for the vehicle from the border candidates;

determine, based on the image data, whether a starting point three-dimensional object provided at only a starting point of a median strip on the border exists;

set an easing area based on a position of the starting point three-dimensional object on the image data and based on setting at least one of a first threshold, for the easing area as the recognition threshold which is smaller than a second threshold for a normal area, and a weight of the vote value in the easing area to a larger value than the weight of the vote value in the normal area, the starting point three-dimensional object exists in the normal area, and the normal area being an area that is on the image data and that is other than the easing area;

determine whether the vehicle is predicted to depart from a reference line that is set based on at least one of the border and whether the vehicle has departed from the reference line; and

perform at least one of a departure alarm and a departure control based on determining that the vehicle is predicted to depart from the reference line that is set based on the at least one of the border and whether the vehicle has departed from the reference line, the departure alarm indicating a departure of the vehicle from the reference line, the departure control comprising controlling the vehicle to avoid departing from the reference line.

2 . The vehicle control device according to claim 1 , wherein the control unit is configured to cause an execution condition to be satisfied and execute any of the departure alarm and the departure control, when there is a possibility that the vehicle collides with a registered three-dimensional object.

3 . The vehicle control device according to claim 1 , wherein the control unit is configured to select, based on the image data, a kind of the border from among kinds comprising a white line, a guardrail, a curbstone, and a wall.

4 . The vehicle control device according to claim 1 , further comprising

a millimeter wave radar that sends a millimeter wave in a forward direction of the vehicle, receives a reflected wave from a physical object, and acquires radar physical object information based on the received reflected wave,

wherein the control unit is configured to specify a position of stationary physical object based on the radar physical object information, and determine whether a registered three-dimensional object exists in the stationary physical objects on the image data.

5 . The vehicle control device according to claim 2 , further comprising

a millimeter wave radar that sends a millimeter wave in a forward direction of the vehicle, receives a reflected wave from a physical object, and acquires radar physical object information based on the received reflected wave,

wherein the control unit is configured to specify positions of stationary physical objects based on the radar physical object information, and determine whether the starting point three-dimensional object and the registered three-dimensional object exist in the stationary physical objects on the image data.

6 . The vehicle control device according to claim 1 , wherein the control unit is configured to perform the departure alarm, and the departure alarm comprises controlling a speaker of the vehicle to emit a sound.

7 . The vehicle control device according to claim 1 , wherein the control unit is configured to perform the departure control, and the departure control comprises controlling a steering motor of the vehicle to change a steering angle of the vehicle.

8 . A vehicle control system comprising:

a camera that photographs a forward view of a vehicle and that acquires image data;

a millimeter wave radar that that sends a millimeter wave in a forward direction of the vehicle, receives a reflected wave from a physical object, and acquires radar physical object information based on the received reflected wave; and

a control unit that is configured to:

extract feature points in the image data, the feature points representing at least part of any of a white line, a guardrail, a curbstone, and a wall;

perform fitting of the feature points to approximate lines expressed by multidimensional functions;

acquire a vote value based on numbers of the feature points on each of the approximate lines and a number of pixels in at least part of the image data;

specify one or more of the approximate lines for each of which the vote value is equal to or more than a recognition threshold, as border candidates of a traveling area for the vehicle;

recognize a border of the traveling area for the vehicle from the border candidates and, based on recognizing the border, set a reference line to a preset distance away from at least part of the border, the border being at least one of a right border and a left border relative to the forward direction of the vehicle;

determine a distance from the vehicle to a traffic light;

determine, based on the image data and the distance from the vehicle to the traffic light, whether a starting point three-dimensional object provided at only a starting point of a median strip on the border exists;

specify a position of stationary physical object based on the radar physical object information, and determine whether a registered three-dimensional object exists in the stationary physical objects on the image data

set an easing area based on a position of the starting point three-dimensional object on the image data and based on setting at least one of a first threshold, for the easing area as the recognition threshold which is smaller than a second threshold for a normal area, and a weight of the vote value in the easing area to a larger value than the weight of the vote value in the normal area, the starting point three-dimensional object exists in the normal area, and the normal area being an area that is on the image data and that is other than the easing area;

determine whether the vehicle is predicted to depart from a reference line that is set based on at least one of the border and whether the vehicle has departed from the reference line; and

perform at least one of a departure alarm and a departure control based on determining that the vehicle is predicted to depart from the reference line that is set based on the at least one of the border and whether the vehicle has departed from the reference line, the departure alarm indicating a departure of the vehicle from the reference line, the departure control comprising controlling the vehicle to avoid departing from the reference line.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 17, 2023
From: WANG, CHENYU
To: TOYOTA JIDOSHA KABUSHIKI KAISHA
Reel/Frame 065250/0702 →
Priority Claims (1)
JP 2022-196109 · Dec 8, 2022 · national
Continuity (1)
Related Publication 20240190427A1 · Jun 13, 2024
References Cited (27)
US 6647139B1 · Kunii · 2003 [cited by examiner]
US 7692534B2 · Kataoka et al. · 2010 [cited by applicant]
US 8352124B2 · Taguchi · 2013 [cited by applicant]
US 8682500B2 · Sakugawa · 2014 [cited by applicant]
US 8818634B2 · Fujita et al. · 2014 [cited by applicant]
US 9168953B2 · Mitsumoto et al. · 2015 [cited by applicant]
US 9489584B2 · Osanai · 2016 [cited by examiner]
US 9714034B2 · Otake et al. · 2017 [cited by applicant]
US 9880558B2 · Nakamura · 2018 [cited by applicant]
US 9902399B2 · Torii et al. · 2018 [cited by applicant]
US 10345443B2 · Masui et al. · 2019 [cited by applicant]
US 10611240B2 · Masui et al. · 2020 [cited by applicant]
US 10795374B2 · Kita · 2020 [cited by examiner]
US 11370420B2 · Yasui · 2022 [cited by examiner]
US 11858510B2 · Motegi · 2024 [cited by examiner]
US 20090245626A1 · Norimatsu · 2009 [cited by examiner]
US 20110044503A1 · Sato · 2011 [cited by examiner]
US 20130272577A1 · Sakamoto · 2013 [cited by examiner]
US 20140133745A1 · Razavi · 2014 [cited by examiner]
US 20190050993A1 · Jang · 2019 [cited by examiner]
US 20190279386A1 · Motohashi · 2019 [cited by examiner]
US 20200019794A1 · Engelcke · 2020 [cited by examiner]
US 20210291836A1 · Cho · 2021 [cited by examiner]
US 20210402996A1 · Wang · 2021 [cited by examiner]
US 20220144304A1 · Ehsanibenafati · 2022 [cited by examiner]
JP 2007179386A · 2007 [cited by applicant]
JP 2014159249A · 2014 [cited by applicant]