IP Library › Granted Patent US 12,594,888
Granted Patent B2
US 12,594,888 · App. 19/006,382 · Granted Apr 7, 2026

Hitch angle detection system, hitch angle detection device, and non-transitory recording medium

Inventor: Noboru Tanase (Machida, JP)
Assignee: TOYOTA JIDOSHA KABUSHIKI KAISHA
B60R1/26G06T7/70H04N7/183G06T2207/20081G06T2207/20092G06T2207/30252
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 12,594,888
App. No.
19/006,382
Granted
Apr 7, 2026
Kind
B2
Abstract

A hitch angle detection device detects a trailer hitch angle based on a trailer image shot by a vehicle camera using a model obtained by performing learning using learning data of a learning trailer image shot by a learning vehicle camera and a label indicating learning trailer hitch angle, additional learning of the model is performed in a server by using additional learning data of an additional learning trailer image shot by the vehicle camera and the label indicating the trailer hitch angle when the additional learning trailer image is shot, input of the trailer hitch angle is accepted by a vehicle HMI, the hitch angle detection device detects the trailer hitch angle based on the trailer image shot by the vehicle camera by using the model with the additional learning performed in the server.

Claims (19)

1 . A hitch angle detection system including:

a trailer;

a vehicle towing the trailer;

a camera mounted on the vehicle;

a hitch angle detection device detecting a hitch angle of the trailer based on an image of the trailer shot by the camera mounted on the vehicle by using a model obtained by performing learning using learning data which is a data set of the image of a learning trailer shot by a learning camera mounted on a learning vehicle and a label indicating the hitch angle of the learning trailer; and

a server performing additional learning of the model, wherein

the vehicle includes HMI accepting input of the hitch angle of the trailer used for the additional learning of the model and communication device communicating with the server,

the camera mounted on the vehicle shoots an additional learning image of the trailer used for the additional learning of the model,

the HMI accepts the input of the hitch angle of the trailer when the additional learning image of the trailer is shot,

the server performs the additional learning of the model by using additional learning data which is the data set of the additional learning image of the trailer and the label indicating the hitch angle of the trailer, the input of the hitch angle of the trailer is accepted by the HMI,

the hitch angle detection device detects the hitch angle of the trailer based on the image of the trailer shot by the camera mounted on the vehicle by using the model with the additional learning performed in the server.

2 . A hitch angle detection device comprising a processor configured to

detect a hitch angle of a trailer towed by a vehicle based on an image of the trailer shot by a camera mounted on the vehicle by using a model obtained by performing learning using learning data which is a data set of the image of a learning trailer shot by a learning camera mounted on a learning vehicle and a label indicating the hitch angle of the learning trailer,

wherein additional learning of the model is performed in a server communicating with a communication device mounted on the vehicle, by using additional learning data which is the data set of an additional learning image of the trailer shot by the camera mounted on the vehicle and the label indicating the hitch angle of the trailer when the additional learning image of the trailer is shot, the input of the hitch angle of the trailer is accepted by an HMI mounted on the vehicle,

the processor is configured to detect the hitch angle of the trailer based on the image of the trailer shot by the camera mounted on the vehicle by using the model with the additional learning performed in the server.

3 . A non-transitory recording medium having recorded thereon a computer program for causing a processor to perform a process which is configured to detect a hitch angle of a trailer based on an image of the trailer towed by a vehicle shot by a camera mounted on the vehicle by using a model obtained by performing learning using learning data which is a data set of the image of a learning trailer shot by a learning camera mounted on a learning vehicle and a label indicating the hitch angle of the learning trailer, comprising:

acquiring the model with additional learning performed in a server using additional learning data which is the data set of an additional learning image of the trailer shot by the camera mounted on the vehicle and the label indicating the hitch angle of the trailer when the additional learning image of the trailer is shot, input of the hitch angle of the trailer being accepted by an HMI mounted on the vehicle: and

detecting the hitch angle of the trailer based on the image of the trailer shot by the camera mounted on the vehicle by using the model with the additional learning performed in the server,

wherein the server communicates with a communication device mounted on the vehicle.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 31, 2024
From: TANASE, NOBORU
To: TOYOTA JIDOSHA KABUSHIKI KAISHA
Reel/Frame 069706/0502 →
Priority Claims (1)
JP 2024-040512 · Mar 14, 2024 · national
Continuity (1)
Related Publication 20250289368A1 · Sep 18, 2025
References Cited (8)
US 11155298B2 · Niewiadomski · 2021 [cited by examiner]
US 11358639B2 · Raeis Hosseiny · 2022 [cited by examiner]
US 20180319438A1 · Herzog · 2018 [cited by applicant]
US 20220297601A1 · Hatzakis · 2022 [cited by examiner]
US 20230227104A1 · Pandey · 2023 [cited by examiner]
US 20240393452A1 · Ghannam · 2024 [cited by examiner]
JP 2019509204A · 2019 [cited by applicant]
JP 7305850B1 · 2023 [cited by applicant]