IP Library › Granted Patent US 12,511,780
Granted Patent B2
US 12,511,780 · App. 18/198,432 · Granted Dec 30, 2025

Device, method, and computer program for estimating seat position

Inventor: Masayuki Yamazaki (Yokohama, JP)
Assignee: TOYOTA JIDOSHA KABUSHIKI KAISHA
G06T7/74G06T7/11G06T7/13G06V10/22G06V10/764G06V20/59G06T2207/30268
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 12,511,780
App. No.
18/198,432
Granted
Dec 30, 2025
Kind
B2
Abstract

A device for estimating a seat position includes a processor configured to generate a mask image by masking a region representing a driver in a driver image representing the interior of a vehicle and generated by a camera while the driver is in the vehicle, generate one or more difference images based on the difference between the mask image and each of one or more reference images among which the position of a driver's seat differs, determine an individual estimate of the position of the driver's seat for each of the one or more difference images by inputting each of the difference images into a classifier, and calculate a statistically representative value of the individual estimates determined for the respective difference images as an estimate of the position of the driver's seat.

Claims (25)

1 . A device for estimating a seat position, comprising:

a memory configured to store one or more reference images representing the interior of a vehicle where a driver's seat of the vehicle is at a predetermined position that differs among the one or more reference images; and

a processor configured to:

identify a region representing a driver in a driver image generated while the driver is in the vehicle by a camera provided to take pictures of the interior of the vehicle,

generate a mask image by masking the identified region,

generate one or more difference images based on the difference between the mask image and each of the one or more reference images,

determine an individual estimate of the position of the driver's seat for each of the one or more difference images by inputting each of the difference images into a classifier which has been trained to estimate the position of the driver's seat, and

calculate a statistically representative value of the individual estimates for the one or more difference images as an estimate of the position of the driver's seat.

2 . The device according to claim 1 , wherein a tolerable range of the position of the driver's seat is set for each of the one or more reference images, and

the processor calculates a statistically representative value of individual estimates included in the respective tolerable ranges of the reference images corresponding to the difference images among the individual estimates of the position of the driver's seat determined for the one or more difference images, as the estimate of the position of the driver's seat.

3 . The device according to claim 1 , wherein the processor generates an edge mask image by applying an edge detection filter to the mask image, and generates the one or more difference images based on the difference between the edge mask image and each of one or more edge reference images obtained by applying the edge detection filter to the one or more reference images.

4 . The device according to claim 1 , wherein the one or more reference images further represent steering of the vehicle whose position differs among the reference images, and

the processor is further configured to determine an individual estimate of the position of the steering for each of the one or more difference images by inputting each of the difference images into a second classifier which has been trained to estimate the position of the steering, and calculate a statistically representative value of the individual estimates of the position of the steering for the one or more difference images as an estimate of the position of the steering.

5 . A method for estimating a seat position, comprising:

identifying a region representing a driver in a driver image generated while the driver is in a vehicle by a camera provided to take pictures of the interior of the vehicle;

generating a mask image by masking the identified region;

generating one or more difference images based on the difference between the mask image and each of one or more reference images representing the interior of the vehicle where a driver's seat of the vehicle is at a predetermined position that differs among the one or more reference images;

determining an individual estimate of the position of the driver's seat for each of the one or more difference images by inputting each of the difference images into a classifier that has been trained to estimate the position of the driver's seat; and

calculating a statistically representative value of the individual estimates for the one or more difference images as an estimate of the position of the driver's seat.

6 . A non-transitory recording medium that stores a computer program for estimating a seat position, the computer program causing a processor mounted on a vehicle to execute a process comprising:

identifying a region representing a driver in a driver image generated while the driver is in the vehicle by a camera provided to take pictures of the interior of the vehicle;

generating a mask image by masking the identified region;

generating one or more difference images based on the difference between the mask image and each of one or more reference images representing the interior of the vehicle where a driver's seat of the vehicle is at a predetermined position that differs among the one or more reference images;

determining an individual estimate of the position of the driver's seat for each of the one or more difference images by inputting each of the difference images into a classifier that has been trained to estimate the position of the driver's seat; and

calculating a statistically representative value of the individual estimates for the one or more difference images as an estimate of the position of the driver's seat.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 17, 2023
From: YAMAZAKI, MASAYUKI
To: TOYOTA JIDOSHA KABUSHIKI KAISHA
Reel/Frame 063671/0407 →
Priority Claims (1)
JP 2022-089735 · Jun 1, 2022 · national
Continuity (1)
Related Publication 20230394702A1 · Dec 7, 2023
References Cited (20)
US 20040040772A1 · Ertl et al. · 2004 [cited by applicant]
US 20070289800A1 · Aoki · 2007 [cited by examiner]
US 20130230256A1 · Deng · 2013 [cited by examiner]
US 20140218268A1 · Olesen · 2014 [cited by examiner]
US 20150186715A1 · Zhao · 2015 [cited by examiner]
US 20170028987A1 · Yamada · 2017 [cited by applicant]
US 20170166122A1 · Ando · 2017 [cited by examiner]
US 20180232636A1 · Kawaguchi · 2018 [cited by applicant]
US 20190057264A1 · Schmidt · 2019 [cited by examiner]
US 20190370580A1 · Aoi et al. · 2019 [cited by applicant]
US 20200189572A1 · Rowell · 2020 [cited by examiner]
US 20200257371A1 · Sung · 2020 [cited by examiner]
US 20210334564A1 · Park · 2021 [cited by examiner]
US 20230058530A1 · Kang · 2023 [cited by examiner]
JP 2004516470A · 2004 [cited by applicant]
JP 2017024653A · 2017 [cited by applicant]
JP 2018132996A · 2018 [cited by applicant]
JP 2018152034A · 2018 [cited by applicant]
JP 2019133446A · 2019 [cited by applicant]
JP 2020042422A · 2020 [cited by applicant]