IP Library › Granted Patent US 12,387,455
Granted Patent B2
US 12,387,455 · App. 17/901,886 · Granted Aug 12, 2025

Image processing system, mobile object, image processing method, and storage medium, with output of image recognition result integrtated on basis of first result regarding image recognition on at least partial region and second result regarding image recognition on wider region

Inventor: Makiko Mori (Kanagawa, JP)
Assignee: Canon Kabushiki Kaisha
G06V10/25G06T5/20G06T5/80G06V20/58G06T2207/10148
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 12,387,455
App. No.
17/901,886
Granted
Aug 12, 2025
Kind
B2
Abstract

An image processing system includes a plurality of imaging units configured to capture optical images including a low-distortion region and a high-distortion region; a first image recognition unit configured to perform image recognition on at least a partial region out of image data obtained from the imaging unit and output a first image recognition result; a second image recognition unit configured to perform image recognition on image data in a wider region than the partial region out of the image data obtained from at least one of the imaging units and output a second image recognition result; and an integration processing unit configured to output an image recognition result integrated on the basis of the first image recognition result and the second image recognition result.

Claims (56)

1. An image processing system comprising:

at least one processor or circuit configured to function as a plurality of units comprising:

(1) a plurality of imaging units configured to capture optical images each including a low-distortion region and a high-distortion region;

(2) a first image recognition unit configured to (a) perform image recognition on at least a partial region out of image data obtained from an imaging unit of the plurality of imaging units and (b) output a first image recognition result;

(3) a second image recognition unit configured to (a) perform image recognition on image data in a wider region than the partial region out of image data obtained from at least one of the plurality of imaging units and (b) output a second image recognition result; and

(4) an integration processing unit configured to output an image recognition result integrated on the basis of (a) the first image recognition result and (b) the second image recognition result,

wherein each of the plurality of imaging units includes (a) an optical system that forms an optical image of the optical images, and (b) an imaging device that captures the optical image generated by the optical system, and

wherein when a focal distance of the optical system is defined as f, a half angle of view is defined as θ, an image height on an image plane is defined as y, and a projection property representing a relationship between the image height y and the half angle of view θ is defined as y(θ),

y(θ) in the low-distortion region is greater than f×θ and is different from the projection property in the high-distortion region.

2. The image processing system according to claim 1 , wherein the low-distortion region is configured to have a projection property that is approximated to a center projection method (y=f×tan θ) or an equidistant projection method (y=f×θ).

3. The image processing system according to claim 1 , wherein when θmax is defined as a maximum half angle of view that the optical system has and A is defined as a predetermined constant, the image processing system is configured to satisfy

1

<

f

×

sin

⁢

θ

max

y

⁡

(

θ

max

)

≤

A

.

4. An image processing system comprising:

a plurality of imaging units configured to capture optical images each including a low-distortion region and a high-distortion region;

at least one processor or circuit configured to function as a plurality of units comprising:

(1) a first image recognition unit configured to (a) perform image recognition on at least a partial region out of image data obtained from an imaging unit of the plurality of imaging units and (b) output a first image recognition result;

(2) a second image recognition unit configured to (a) perform image recognition on image data in a wider region than the partial region out of image data obtained from at least one of the plurality of imaging units and (b) output a second image recognition result; and

(3) an integration processing unit configured to output an image recognition result integrated on the basis of (a) the first image recognition result and (b) the second image recognition result,

wherein each of the plurality of imaging units includes (a) an optical system that forms an optical image of the optical images, and (b) an imaging device that captures the optical image generated by the optical system, and

wherein when a focal distance of the optical system is defined as f, a half angle of view is defined as θ, an image height on an image plane is defined as y, and a projection property representing a relationship between the image height y and the half angle of view θ is defined as y(θ),

y(θ) in the low-distortion region is greater than f×θ and is different from the projection property in the high-distortion region.

5. The image processing system according to claim 4 , wherein the low-distortion region is configured to have a projection property that is approximated to a center projection method (y=f×tan θ) or an equidistant projection method (y=f×θ).

6. The image processing system according to claim 4 , wherein when θmax is defined as a maximum half angle of view that the optical system has and A is defined as a predetermined constant, the image processing system is configured to satisfy

1

<

f

×

sin

⁢

θ

max

y

⁡

(

θ

max

)

≤

A

.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 10, 2022
From: MORI, MAKIKO
To: CANON KABUSHIKI KAISHA
Reel/Frame 061368/0860 →
Priority Claims (1)
JP 2021-155833 · Sep 24, 2021 · national
Continuity (1)
Related Publication 20230098424A1 · Mar 30, 2023
References Cited (31)
US 8289391B2 · Kiyohara · 2012 [cited by applicant]
US 9953211B2 · Hayasaka · 2018 [cited by applicant]
US 10769760B2 · Kawana · 2020 [cited by applicant]
US 10917610B2 · Aihara · 2021 [cited by applicant]
US 11310461B2 · Aihara · 2022 [cited by applicant]
US 20110074957A1 · Kiyohara · 2011 [cited by applicant]
US 20140232538A1 · Sobue · 2014 [cited by applicant]
US 20160110586A1 · Hayasaka · 2016 [cited by applicant]
US 20160148062A1 · Fürsich · 2016 [cited by examiner]
US 20160364619A1 · Ogata · 2016 [cited by examiner]
US 20180365859A1 · Oba · 2018 [cited by applicant]
US 20190066276A1 · Kawana · 2019 [cited by applicant]
US 20190266423A1 · Akiba · 2019 [cited by examiner]
US 20190273889A1 · Aihara · 2019 [cited by applicant]
US 20210127086A1 · Aihara · 2021 [cited by applicant]
US 20210188167A1 · Fürsich · 2021 [cited by examiner]
US 20220232182A1 · Watanabe · 2022 [cited by applicant]
JP 2004345554A · 2004 [cited by applicant]
JP 2008141568A · 2008 [cited by applicant]
JP 2010095202A · 2010 [cited by applicant]
JP 2011077772A · 2011 [cited by applicant]
JP 2012178639A · 2012 [cited by applicant]
JP 2013012849A · 2013 [cited by applicant]
JP 2016081212A · 2016 [cited by applicant]
JP 2019040521A · 2019 [cited by applicant]
WO 2019123840A1 · 2019 [cited by applicant]
WO 2020230660A1 · 2020 [cited by applicant]
Feb. 24, 2023 European Official Action in European Patent Appln. No. 22194539.7. [cited by applicant]
Yoshihisa Kiyota, “Simultaneous Human Detection in Three Directions Around a Construction Machine by Monocular Camera Image Recognition,” 25th Image Sensing Symposium (ISS 2019), Jun. 12, 2019. [cited by applicant]
Feb. 18, 2023 Modified Abstract in European Patent Appln. No. 22194539.7. [cited by applicant]
Feb. 20, 2024 Japanese Official Action in Japanese Patent Appln. No. 2021-155833. [cited by applicant]