IP Library Granted Patent US 12,450,776
Granted Patent B2
US 12,450,776 · App. 18/286,063 · Granted Oct 21, 2025

Information processing apparatus, information processing method, and program

Inventors: Toshio Yamazaki (Tokyo, JP); Yasuhiro Sutou (Kanagawa, JP); Kentaro Doba (Tokyo, JP); Seungha Yang (Kanagawa, JP)
Assignee: SONY GROUP CORPORATION
G06T7/80G06V10/44
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 12,450,776
App. No.
18/286,063
Granted
Oct 21, 2025
Kind
B2
Abstract

A novel and improved information processing method, information processing apparatus, and program is proposed which can execute a calibration process with higher accuracy. The information processing apparatus includes: a detection unit configured to detect a feature point from each of images obtained by imaging a subject with a plurality of cameras respectively at a certain timing; and a processing unit configured to execute a process of calibrating at least one of the plurality of cameras by use of the cameras' respective images having the feature point detected by the detection unit, the feature point satisfying a predetermined condition.

Claims (48)

1. An information processing apparatus comprising:

circuitry configured to

detect a feature point from each image of a plurality of images obtained by imaging a subject with a plurality of cameras respectively at a certain timing, and

execute a process of calibrating at least one of the plurality of cameras by use of respective images of the plurality of cameras having the detected feature point, the feature point satisfying a predetermined condition,

wherein the predetermined condition is based on a calculated degree of correlation of the detected feature point among the respective images of the plurality of cameras, and

wherein the circuitry executes the process of calibrating the at least one of the plurality of cameras by use of respective images of the plurality of cameras having a distribution of disparity values for which a calculated disparity distribution score is equal to or greater than a predetermined value.

2. The information processing apparatus according to claim 1 ,

wherein the circuitry executes the process of calibrating the at least one of the plurality of cameras by use of the respective images of the plurality of cameras having a number of detected feature points, the number being equal to or greater than a predetermined value.

3. The information processing apparatus according to claim 2 ,

wherein the circuitry is further configured to distinguish, for each detected feature point included in a first image, a feature point having a highest correlation among feature points included in a second image as a pair of feature points, and

wherein the circuitry executes the process of calibrating the at least one of the plurality of cameras by use of the respective images of the plurality of cameras having the pair of feature points that satisfies a predetermined condition.

4. The information processing apparatus according to claim 3 ,

wherein the circuitry executes the process of calibrating the at least one of the plurality of cameras by use of the respective images of the plurality of cameras having a number of the pairs of feature points, the number being equal to or greater than a predetermined value.

5. The information processing apparatus according to claim 4 ,

wherein the circuitry executes the process of calibrating the at least one of the plurality of cameras by use of the respective images of the plurality of cameras having the distribution of disparity values obtained for each pair of feature points with the calculated disparity distribution score equal to or greater than the predetermined value.

6. The information processing apparatus according to claim 5 ,

wherein the circuitry executes the process of calibrating the at least one of the plurality of cameras by use of the respective images of the plurality of cameras having a predetermined distribution of feature points for each pair of feature points.

7. The information processing apparatus according to claim 6 ,

wherein the circuitry is further configured to calculate a displacement between the plurality of cameras based on a rectification process executed on the respective images of the plurality of cameras, and

wherein the circuitry executes the process of calibrating the at least one of the plurality of cameras by use of the respective images of the plurality of cameras having a result of calculation indicating that the displacement between the plurality of cameras is equal to or greater than a predetermined value.

8. The information processing apparatus according to claim 7 , further comprising:

a non-transitory computer-readable storage medium configured to store the respective images of the plurality of cameras having a result of calculation, the result being that the displacement between the plurality of cameras is equal to or greater than the predetermined value,

wherein the circuitry executes the process of calibrating the at least one of the plurality of cameras by use of a predetermined number of the respective images of the plurality of cameras having a new imaging time among the respective images of the plurality of cameras stored in the non-transitory computer-readable storage medium.

9. The information processing apparatus according to claim 8 ,

wherein the circuitry executes the process of calibrating the at least one of the plurality of cameras by use of a predetermined number of the respective images of the plurality of cameras stored in the non-transitory computer-readable storage medium upon the predetermined number or more of the respective images of the plurality of cameras being stored in the non-transitory computer-readable storage medium after a point in time of previous calibration.

10. The information processing apparatus according to claim 9 ,

wherein the circuitry executes the process of calibrating the at least one of the plurality of cameras upon calibration execution permission being obtained in response to an operation by a user.

11. The information processing apparatus according to claim 10 ,

wherein the circuitry is further configured to output control information related to travel of a moving body on which the plurality of cameras is mounted, and

wherein the circuitry executes the process of calibrating the at least one of the plurality of cameras by use of the respective images of the plurality of cameras obtained by being captured by the plurality of cameras after the moving body moves in accordance with the control information.

12. The information processing apparatus according to claim 11 ,

wherein the circuitry outputs the control information to move the moving body on which the plurality of cameras is mounted to a certain target location.

13. The information processing apparatus according to claim 11 ,

wherein the circuitry is further configured to control a display mounted on the moving body to display guidance information regarding the travel of the moving body from a current location to a target location.

14. The information processing apparatus according to claim 13 ,

wherein the circuitry is further configured to disable control related to a predetermined operation of the moving body when a difference between a post-calibration parameter and a pre-calibration parameter of at least one of the plurality of cameras calibrated by the circuitry is equal to or greater than a predetermined value.

15. The information processing apparatus according to claim 14 ,

wherein the circuitry calibrates the plurality of cameras by use of the respective images of the plurality of cameras where the detected feature point satisfies the predetermined condition.

16. An information processing method to be executed by a computer, the method comprising:

detecting a feature point from each image of a plurality of images obtained by imaging a subject with a plurality of cameras respectively at a certain timing; and

executing a process of calibrating at least one of the plurality of cameras by use of respective images of the plurality of cameras having the detected feature point that satisfies a predetermined condition,

wherein the predetermined condition is based on a calculated degree of correlation of the detected feature point among the respective images of the plurality of cameras, and

wherein the process of calibrating the at least one of the plurality of cameras is executed by use of respective images of the plurality of cameras having a distribution of disparity values for which a calculated disparity distribution score is equal to or greater than a predetermined value.

17. A non-transitory computer-readable storage medium having embodied thereon a program, which when executed by a computer causes the computer to execute a method, the method comprising:

detecting a feature point from each image of a plurality of images obtained by imaging a subject with a plurality of cameras respectively at a certain timing; and

executing a process of calibrating at least one of the plurality of cameras by use of respective images of the plurality of cameras having the detected feature point, the feature point satisfying a predetermined condition,

wherein the predetermined condition is based on a calculated degree of correlation of the detected feature point among the respective images of the plurality of cameras, and

wherein the process of calibrating the at least one of the plurality of cameras is executed by use of respective images of the plurality of cameras having a distribution of disparity values for which a calculated disparity distribution score is equal to or greater than a predetermined value.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 6, 2023
From: YAMAZAKI, TOSHIO; SUTOU, YASUHIRO; DOBA, KENTARO; YANG, SEUNGHA
To: SONY GROUP CORPORATION
Reel/Frame 065151/0075 →
Priority Claims (1)
JP 2021-069074 · Apr 15, 2021 · national
Continuity (1)
Related Publication 20240378751A1 · Nov 14, 2024
References Cited (29)
US 9734419B1 · Ye · 2017 [cited by examiner]
US 10096114B1 · Lasenby · 2018 [cited by examiner]
US 10097812B2 · Livyatan · 2018 [cited by examiner]
US 10917593B2 · Sakano · 2021 [cited by examiner]
US 10970877B2 · Eshima · 2021 [cited by examiner]
US 11178382B1 · Wang · 2021 [cited by examiner]
US 20130083993A1 · Sutou · 2013 [cited by examiner]
US 20130135439A1 · Kakuko · 2013 [cited by examiner]
US 20160275683A1 · Sakano · 2016 [cited by examiner]
US 20180007345A1 · Bougnoux · 2018 [cited by applicant]
US 20180322658A1 · Wang · 2018 [cited by examiner]
US 20180350107A1 · Myokan · 2018 [cited by examiner]
US 20190037205A1 · Itoh · 2019 [cited by examiner]
US 20190347822A1 · Nash · 2019 [cited by examiner]
US 20200034989A1 · Koyama · 2020 [cited by examiner]
US 20210001776A1 · Kim · 2021 [cited by examiner]
US 20210327091A1 · Park · 2021 [cited by examiner]
US 20220101549A1 · Sadeghi · 2022 [cited by examiner]
US 20220132092A1 · Shibata · 2022 [cited by examiner]
US 20220210388A1 · Ren · 2022 [cited by examiner]
US 20230141515A1 · Danziger · 2023 [cited by examiner]
US 20240107001A1 · Bai · 2024 [cited by examiner]
US 20240202974A1 · Doba · 2024 [cited by examiner]
CN 110838148A · 2020 [cited by applicant]
JP 2014101075A · 2014 [cited by applicant]
JP 2014138332A · 2014 [cited by applicant]
JP 2017116321A · 2017 [cited by applicant]
JP 2018112522A · 2018 [cited by applicant]
Xiao Tan et al: “Feature Correspondence with Even Distribution”, Digital Image Computing Techniques and Applications (DICTA) ,2012 International Conference On, IEEE,Dec. 3, 2012 (Dec. 3, 2012), pp. 1-7, XP032310838,DOI:… [cited by applicant]