IP Library Granted Patent US 12,361,721
Granted Patent B2
US 12,361,721 · App. 17/693,543 · Granted Jul 15, 2025

Image processing apparatus for estimating vehicle spatial motion

Inventors: Yuji Yasui (Wako, JP); Masamitsu Tsuchiya (Wako, JP); Akira Kanehara (Wako, JP)
Assignee: HONDA MOTOR CO., LTD.
G06V20/58G06T7/194G06T7/38G06V20/59
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 12,361,721
App. No.
17/693,543
Granted
Jul 15, 2025
Kind
B2
Abstract

An image processing apparatus that processes images acquired by a camera. In processing the images, a moving object may be recognized or identified from the images. Masking processing is performed on the moving object recognized in the image. An estimate of the spatial motion of the image processing apparatus relative to a surrounding environment is determined based on the images that are subjected to the masking processing.

Claims (37)

1. An image processing apparatus comprising:

a camera; and

a processing unit configured to process an image acquired by the camera, wherein

the processing unit includes

at least one processor and at least one memory storing at least one program, and

the at least one program causes the at least one processor to:

recognize a moving object from the image acquired by the camera, perform masking processing on the moving object recognized in the image; and

estimate spatial motion of the image processing apparatus based on the image subjected to the masking processing,

wherein estimation of the spatial motion includes:

generating a plurality of scaled images by scaling a captured first image with a plurality of different scale factors,

capturing a second image after a predetermined time has elapsed since the first image was captured, and

estimating a movement speed based on a scale factor of a scaled image of which a difference from the second image is the smallest difference among the plurality of scaled images.

2. The image processing apparatus according to claim 1 , wherein

the camera is provided in an internal space separated from an outside, the image includes an image of the internal space and an image of an external space, and the moving object includes a moving object estimated to be located in the external space.

3. The image processing apparatus according to claim 2 , wherein

the moving object further includes a moving object estimated to be located in the internal space.

4. The image processing apparatus according to claim 1 , wherein

the camera acquires an image of outside through a transparent part provided in a partition between the internal space separated from the outside and an external space.

5. The image processing apparatus according to claim 4 , wherein

the transparent part is provided at a plurality of positions to have symmetry with respect to a plane, and

the camera is disposed to cause an optical axis to be along the plane and to have symmetry with respect to the plane.

6. The image processing apparatus according to claim 5 , wherein

the image processing apparatus is mounted on a vehicle, and the internal space is an inside of a vehicle interior, and the camera is provided in the vehicle interior to face a rear of the vehicle.

7. The image processing apparatus according to claim 1 , wherein

the image processing apparatus is mounted on a vehicle, and

the at least one program causes the at least one processor to perform the masking processing on at least two images acquired at a certain time interval, and estimate a movement speed of the vehicle based on a difference between the at least two images subjected to the masking processing.

8. The image processing apparatus according to claim 1 , wherein

the image processing apparatus is mounted on a vehicle, and

the at least one program causes the at least one processor to perform the masking processing on at least two images acquired at a certain time interval, estimate positions of a same target object appearing in both the at least two images subjected to the masking processing, and estimate, as the spatial motion, a movement speed of the vehicle based on a difference between the estimated positions.

9. The image processing apparatus according to claim 1 , wherein

the image processing apparatus is mounted on a vehicle, and

the at least one program causes the at least one processor to perform the masking processing on at least two images acquired at a certain time interval, and estimate a turning direction of the vehicle based on a difference between the at least two images subjected to the masking processing.

10. The image processing apparatus according to claim 9 , wherein

the at least one program causes the at least one processor to shift, in accordance with the turning direction, a direction that brings the at least two images into correlation.

11. The image processing apparatus according to claim 5 , wherein

the image processing apparatus is mounted on a vehicle, and

the at least one program causes the at least one processor to estimate a traveling direction of the vehicle based on a difference between images captured through the transparent parts provided to have symmetry with respect to the plane.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 10, 2023
From: YASUI, YUJI; TSUCHIYA, MASAMITSU; KANEHARA, AKIRA
To: HONDA MOTOR CO., LTD.
Reel/Frame 062323/0961 →
Priority Claims (1)
JP 2021-050360 · Mar 24, 2021 · national
Continuity (1)
Related Publication 20220309796A1 · Sep 29, 2022
References Cited (26)
US 9846043B2 · Aoki et al. · 2017 [cited by applicant]
US 10229505B2 · Ding · 2019 [cited by examiner]
US 10565714B2 · Hunt · 2020 [cited by examiner]
US 10872433B2 · Stein et al. · 2020 [cited by applicant]
US 20050265453A1 · Saito · 2005 [cited by examiner]
US 20100045799A1 · Lei · 2010 [cited by examiner]
US 20130235201A1 · Kiyohara · 2013 [cited by examiner]
US 20160196654A1 · Aoki · 2016 [cited by examiner]
US 20160358022A1 · Dziurda · 2016 [cited by examiner]
US 20180012068A1 · Tanaka · 2018 [cited by examiner]
US 20190325595A1 · Stein et al. · 2019 [cited by applicant]
US 20200209402A1 · Abari · 2020 [cited by examiner]
US 20210109543A1 · Hiromitsu · 2021 [cited by examiner]
US 20210118161A1 · Stein et al. · 2021 [cited by applicant]
US 20220044424A1 · Jayaraman · 2022 [cited by examiner]
US 20220301185A1 · Yasui · 2022 [cited by examiner]
US 20220301427A1 · Ueno · 2022 [cited by examiner]
US 20240029449A1 · Futatsugi · 2024 [cited by examiner]
US 20240312341A1 · Baba · 2024 [cited by examiner]
JP 2009122990A · 2009 [cited by examiner]
JP 2013186668A · 2013 [cited by applicant]
JP 2016126662A · 2016 [cited by applicant]
JP 2020126432A · 2020 [cited by applicant]
WO 2019202397A8 · 2020 [cited by applicant]
WO WO2022064641A1 · 2022 [cited by examiner]
Japanese Office Action for Japanese Patent Application No. 2021-050360 mailed Dec. 9, 2022 (partially translated). [cited by applicant]