IP Library › Granted Patent US 12,541,875
Granted Patent B2
US 12,541,875 · App. 18/592,091 · Granted Feb 3, 2026

Camera location estimation apparatus, method and storage medium

Inventor: Yasuki Tanabe (Yokohama, JP)
Assignee: KABUSHIKI KAISHA TOSHIBA
G06T7/74G06T7/20G06T2207/30196G06T2207/30244
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 12,541,875
App. No.
18/592,091
Granted
Feb 3, 2026
Kind
B2
Abstract

According to one embodiment, a camera location estimation apparatus including a processor included to acquire map information indicating a map of a facility, acquire first locations of a moving object on the map indicated by the map information in response to movements of the moving object moving within the facility, acquire a plurality of images containing the moving object, the plurality of images being captured by a camera, and estimate a location of the camera on the map indicated by the map information so that each of the first locations of the moving object and a second location of the moving object on an image containing the moving object located at the first location among the plurality of images match with each other.

Claims (42)

1 . A camera location estimation apparatus for estimating a location of a camera installed in a facility, the apparatus comprising:

a processor configured to:

acquire map information indicating a map of the facility;

acquire first locations of a moving object on the map determined by the moving object in response to movements of the moving object moving within the facility;

acquire a plurality of images containing the moving object, the plurality of images being captured by the camera; and

estimate the location of the camera on the map indicated by the map information so that each of the first locations of the moving object on the map acquired in response to the movements of the moving object and second locations of the moving object on images containing the moving object located at the first locations on the map among the plurality of images match with each other.

2 . The camera location estimation apparatus of claim 1 , wherein

the processor is configured to

calculate, on an assumption that the camera is installed at a third location on the map indicated by the map information, fourth locations of the moving object on images captured by the camera installed at the third location based on each of the first locations of the moving object on the map,

calculate differences between the second locations of the moving object on the image containing the moving object located at each of the first locations on the map and the fourth locations on the images calculated for each of the first locations on the map, and

estimate a fifth location of the camera at which the differences calculated for each of the first locations on the map are decreased.

3 . The camera location estimation apparatus of claim 2 , wherein

the processor is configured to estimate the fifth location of the camera by bundle adjustment.

4 . The camera location estimation apparatus of claim 1 , wherein

the processor is configured to

calculate, on an assumption that the camera is installed at a third location on the map indicated by the map information and is installed at a first angle, a fourth location of the moving object on an image captured by the camera based on each of the first locations of the moving object on the map,

calculate differences between the second locations of the moving object on the image containing the moving object at each of the first locations on the map and the fourth locations on the image calculated for each of the first locations, and

estimate a fifth location and a second angle of the camera at which the difference calculated for each of the first locations on the map is decreased.

5 . The camera location estimation apparatus of claim 4 , wherein

the processor is configured to estimate a camera imaging area of the camera based on the map information, view angle information indicating an angle of view of the camera held in advance, the estimated fifth location and second angle of the camera.

6 . The camera location estimation apparatus of claim 5 , wherein

the processor is configured to generate camera imaging area information in which the camera imaging area of the camera is mapped on the map indicated by the map information.

7 . The camera location estimation apparatus of claim 1 , wherein

the processor is configured to acquire the map information from the moving object or a management system that manages the moving object.

8 . The camera location estimation apparatus of claim 1 , wherein

the processor is configured to acquire the first locations of the moving object on the map from the moving object or a management system that manages the moving object.

9 . The camera location estimation apparatus of claim 1 , wherein

when a plurality of cameras are installed in the facility, locations of the cameras are estimated for each of the cameras.

10 . The camera location estimation apparatus of claim 1 , wherein

the processor is configured to

calculate, on an assumption that the camera is installed at a third location on the map indicated by the map information, fourth locations of the moving object on images captured by the camera installed at the third location based on each of the first locations of the moving object on the map, and

calculate differences between the second locations of the moving object on the image containing the moving object located at each of the first locations on the map and the fourth locations on the images calculated for each of the first locations on the map.

11 . A method executed by a camera location estimation apparatus for estimating a location of a camera installed in a facility, the method comprising:

acquiring map information indicating a map of the facility;

acquiring first locations of a moving object on the map determined by the moving object in response to movements of the moving object moving within the facility;

acquiring a plurality of images containing the moving object, the plurality of images being captured by the camera; and

estimating the location of the camera on the map indicated by the map information so that each of the first locations of the moving object on the map acquired in response to the movements of the moving object and second locations of the moving object on images containing the moving object located at the first locations on the map among the plurality of images match with each other.

12 . A non-transitory computer-readable storage medium having stored thereon a program which is executed by a computer of a camera location estimation apparatus for estimating a location of a camera installed in a facility, the program comprising instructions capable of causing the computer to execute functions of:

acquiring map information indicating a map of the facility;

acquiring first locations of a moving object on the map determined by the moving object in response to movements of the moving object moving within the facility;

acquiring a plurality of images containing the moving object, the plurality of images being captured by the camera; and

estimating the location of the camera on the map indicated by the map information so that each of the first locations of the moving object on the map acquired in response to the movements of the moving object and second locations of the moving object on images containing the moving object located at the first locations on the map among the plurality of images match with each other.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 10, 2024
From: TANABE, YASUKI
To: KABUSHIKI KAISHA TOSHIBA
Reel/Frame 067377/0442 →
Priority Claims (1)
JP 2023-111588 · Jul 6, 2023 · national
Continuity (1)
Related Publication 20250014217A1 · Jan 9, 2025
References Cited (18)
US 10495661B2 · Tu · 2019 [cited by examiner]
US 11700448B1 · Cogliandro · 2023 [cited by examiner]
US 20040219978A1 · Teramoto · 2004 [cited by examiner]
US 20080285808A1 · Chang · 2008 [cited by examiner]
US 20090018768A1 · Jo · 2009 [cited by examiner]
US 20090085935A1 · Yamashita · 2009 [cited by examiner]
US 20090188800A1 · Chachisvilis · 2009 [cited by examiner]
US 20120230589A1 · Baba · 2012 [cited by examiner]
US 20150092226A1 · Anderson · 2015 [cited by examiner]
US 20190149770A1 · Oami · 2019 [cited by examiner]
US 20190335077A1 · Rieveschl · 2019 [cited by examiner]
US 20200101621A1 · Sato · 2020 [cited by examiner]
US 20250087084A1 · Kim · 2025 [cited by examiner]
EP 2933790 · 2013 [cited by examiner]
JP 2014216813A · 2014 [cited by applicant]
Álvaro Parra Bustos et al., “Visual SLAM: Why Bundle Adjust?”, arXiv:1902.03747v2 [cs.CV], Jun. 2019, 7 pages. [cited by applicant]
“Cocobo, a Security Robot that Harmonizes with Public Spaces”, SECOM Co., Ltd., Jan. 17, 2022, https://www.secom.co.jp/business/cocobo/, 73 pages (with English Translation). [cited by applicant]
“Launch of “People Flow Analysis Service” that Visualizes “People's Trajectories”—Visualizes Human Movements Captured Using Toshiba AI Technology and the Cloud and Supports Improvements”, Toshiba Lighting & Technology C… [cited by applicant]