IP Library Granted Patent US 12,418,713
Granted Patent B2
US 12,418,713 · App. 18/172,598 · Granted Sep 16, 2025

Main object determination apparatus, imaging apparatus, and control method for controlling main object determination apparatus

Inventors: Tomohiro Nishiyama (Tokyo, JP); Reiji Hasegawa (Kanagawa, JP)
Assignee: Canon Kabushiki Kaisha
H04N23/611G06V10/40G06V10/945G06V40/10H04N23/631
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 12,418,713
App. No.
18/172,598
Granted
Sep 16, 2025
Kind
B2
Abstract

A main object determination apparatus includes an image acquisition unit configured to acquire images captured at different timings, a selection unit configured to select main object candidate(s) from objects in the images, a determination unit configured to determine whether the main object candidate(s) each selected at the respective different timings are the same, and an input unit configured to receive an operation. In a case where the determination unit determines that the main object candidate(s) selected by the selection unit in an image of interest and one or more images captured within a predetermined time before the image of interest is captured are the same, the determination unit determines the main object candidate(s) to be a main object. In a case where the input unit receives an instruction to specify a new main object, the determination unit switches the main object according to the instruction.

Claims (23)

1. A main object determination apparatus comprising:

one or more processors; and

a memory storing instructions which, when executed by the one or more processors, cause the main object determination apparatus to function as:

an object detection unit configured to detect persons from a first image captured;

a calculation unit configured to, when the persons are detected by the object detection unit, for each of the detected persons, acquire posture information about the person, the posture information being estimated from positional relationships between joints, and, based on the posture information, calculate a reliability corresponding to a probability of a main object in the first image;

a determination unit configured to, based on the reliability, determine whether or not a main object candidate in the first image exists;

a decision unit configured to, in a case where the determination unit determines that the main object candidate in the first image exists, determine whether or not the main object candidate in the first image is identical to a main object candidate in a plurality of images that were captured within predetermined frames before the first image, and configured to, in a case of determining as being identical in images of a determined number of frames or more, the determined number having been determined in advance, decide the main object candidate as the main object, and configured to, in a case where the determination unit determines that the main object candidate in the first image does not exist, does not perform the determination as to whether identical or not; and

a switching unit configured to, upon receiving an instruction from a user for designating a main object anew, perform main object switching.

2. The main object determination apparatus according to claim 1 , wherein the calculation unit calculates the reliability corresponding to a degree of possibility of being the main object from each of the objects.

3. The main object determination apparatus according to claim 2 , wherein the calculation unit calculates the reliability using a distance between the respective objects and an important physical body.

4. The main object determination apparatus according to claim 2 , wherein the calculation unit selects an object of which the reliability has the greatest value as the main object candidate.

5. The main object determination apparatus according to claim 4 , wherein the calculation unit selects also an object in which a difference from the greatest value of the reliability has a value smaller than a value determined in advance as the main object candidate.

6. The main object determination apparatus according to claim 1 , wherein the calculation unit does not perform selection of the one or more main object candidates from an image that is not captured within the predetermined time before an image of interest is captured.

7. An imaging apparatus comprising:

an imaging unit configured to capture an object image formed through an imaging optical system; and

the main object determination apparatus according to claim 1 .

8. A control method for controlling a main object determination apparatus, the control method comprising:

detecting persons from a first image captured;

acquiring, when the persons are detected, for each of the detected persons, posture information about the person, the posture information being estimated from positional relationships between joints, and, based on the posture information, calculating a reliability corresponding to a probability of a main object in the first image;

determining, based on the reliability, whether or not a main object candidate in the first image exists;

determining, in a case where it is determined that the main object candidate in the first image exists, whether or not the main object candidate in the first image is identical to a main object candidate in a plurality of images that were captured within predetermined frames before the first image, and deciding, in a case of determining as being identical in images of a determined number of frames or more, the determined number having been determined in advance, the main object candidate as the main object, and not performing, in a case where it is determined that the main object candidate in the first image does not exist, the determination as to whether identical or not; and

performing, upon receiving an instruction from a user for designating a main object anew, main object switching.

9. A non-transitory computer-readable storage medium storing a program for causing a computer to perform the control method according to claim 8 .

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 6, 2023
From: NISHIYAMA, TOMOHIRO; HASEGAWA, REIJI
To: CANON KABUSHIKI KAISHA
Reel/Frame 063237/0077 →
Priority Claims (1)
JP 2022-028466 · Feb 25, 2022 · national
Continuity (1)
Related Publication 20230276117A1 · Aug 31, 2023
References Cited (38)
US 10055853B1 · Fisher · 2018 [cited by applicant]
US 10455154B2 · Kinoshita · 2019 [cited by applicant]
US 12236652B2 · Datar · 2025 [cited by applicant]
US 20090059007A1 · Wagg · 2009 [cited by applicant]
US 20130243323A1 · Yaguchi · 2013 [cited by examiner]
US 20150070526A1 · Kinoshita · 2015 [cited by examiner]
US 20150116517A1 · Kinoshita · 2015 [cited by applicant]
US 20150296133A1 · Kodama · 2015 [cited by applicant]
US 20160055651A1 · Oami · 2016 [cited by examiner]
US 20160334885A1 · Togawa · 2016 [cited by examiner]
US 20170255832A1 · Jones · 2017 [cited by examiner]
US 20180036590A1 · Deangelis · 2018 [cited by applicant]
US 20180204070A1 · Kawano · 2018 [cited by applicant]
US 20180241984A1 · Sun · 2018 [cited by applicant]
US 20190057592A1 · Kusens · 2019 [cited by applicant]
US 20190080495A1 · Andronikos · 2019 [cited by applicant]
US 20190139229A1 · Ohira · 2019 [cited by examiner]
US 20200245904A1 · Ikeda · 2020 [cited by examiner]
US 20210097291A1 · Kosiakova · 2021 [cited by applicant]
US 20210127068A1 · Nishiyama · 2021 [cited by applicant]
US 20210158537A1 · Funamoto · 2021 [cited by examiner]
US 20210192783A1 · Huelsdunk · 2021 [cited by applicant]
US 20210203838A1 · Tsuji · 2021 [cited by examiner]
US 20230124466A1 · Shimauchi · 2023 [cited by applicant]
US 20230237835A1 · Fu · 2023 [cited by applicant]
US 20240104765A1 · Babazaki · 2024 [cited by examiner]
US 20250006337A1 · Oprea · 2025 [cited by applicant]
JP 2008085737A · 2008 [cited by applicant]
JP 5987306B2 · 2016 [cited by applicant]
JP 2017016592A · 2017 [cited by applicant]
JP 2018066889A · 2018 [cited by applicant]
JP 2018538631A · 2018 [cited by applicant]
JP 2021071794A · 2021 [cited by applicant]
JP 2021082999A · 2021 [cited by applicant]
WO 2017084204A1 · 2017 [cited by applicant]
Yamamoto et al. “JP 2017016592A Translation”. 2017 (Year: 2017). [cited by examiner]
D. Hui, et al., Research on Sports Video Tracking Based on Clustering Extraction Algorithm, 2021 International Conference on Networking, Communications and Information Technology (NetCIT), Manchester, United Kingdom, 20… [cited by applicant]
L. Yu, et al., Research of Image Main Objects Detection Algorithm Based on Deep Learning, 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC), Chongqing, China, 2018. [cited by applicant]