IP Library › Granted Patent US 12,590,815
Granted Patent B2
US 12,590,815 · App. 18/656,055 · Granted Mar 31, 2026

VSLAM with image buffer and extraction

Inventor: Kazuyuki Ohhashi (Yokohama, JP)
Assignee: SOCIONEXT INC.
G01C21/3837G06T1/60G06T7/73G06V10/40G06V20/58
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 12,590,815
App. No.
18/656,055
Granted
Mar 31, 2026
Kind
B2
Abstract

According to one embodiment, an information processing device includes a buffer and a VSLAM processor. The buffer buffers image data of surroundings of a moving body obtained by an imaging unit of the moving body, and transmits extracted image data extracted based on extracted image determination information from among the buffered image data. The VSLAM processor executes a VSLAM process by using the extracted image data.

Claims (34)

1 . An information processing device comprising:

a buffer configured to buffer image data of surroundings of a moving body obtained by an imaging unit of the moving body, execute a thinning process of the buffered image data at different intervals according to extracted image determination information to extract image data, and transmit the extracted image data in a time-series sequence; and

a VSLAM processor configured to execute a VSLAM process by using the extracted image data.

2 . The information processing device according to claim 1 , wherein

the extracted image determination information includes information determined based on at least one of information on a state of movement of the moving body, instruction information by a passenger of the moving body, information on a surrounding object of the moving body identified by a surrounding object detection sensor mounted on the moving body, and information on surroundings of the moving body recognized based on the image data obtained by the imaging unit.

3 . The information processing device according to claim 1 , wherein

the buffer is configured to extract image data of a first period from among the buffered image data as the extracted image data, based on the extracted image determination information.

4 . The information processing device according to claim 3 , wherein

the buffer is configured to execute a thinning process of the buffered image data based on the extracted image determination information to generate the extracted image data, and

in the thinning process, a time interval of thinning out from the buffered image data is different between the first period and a second period different from the first period.

5 . The information processing device according to claim 1 , wherein

the buffer is configured to:

buffer first image data obtained by imaging a first direction and second image data obtained by imaging a second direction different from the first direction from among the image data of surroundings of the moving body; and

transmit first extracted image data extracted from the first image data and second extracted image data extracted from the second image data, as the extracted image data based on the extracted image determination information.

6 . The information processing device according to claim 1 , wherein

the buffered image data includes a plurality of frames, and

the extracted image data includes image data obtained by cutting out a partial region of at least one frame of the buffered image data.

7 . The information processing device according to claim 1 , wherein

the image data of surroundings of the moving body includes image data obtained by a plurality of the imaging units, and

the buffer is configured to buffer, when the moving body makes a change in a traveling direction, the image data of surroundings of the moving body acquired by the imaging units different before and after the change.

8 . The information processing device according to claim 7 , wherein

the VSLAM processor is configured to perform an integration of:

map information obtained by a VSLAM process based on image data of the surroundings of the moving body before the change in the traveling direction of the moving body; and

map information obtained by a VSLAM process based on image data of the surroundings of the moving body after the change in the traveling direction of the moving body.

9 . An information processing method executed by a computer, the method comprising:

buffering image data of surroundings of a moving body obtained by an imaging unit of the moving body;

executing a thinning process of the buffered image data at different intervals according to extracted image determination information to extract image data;

transmitting extracted image data in a time-series sequence; and

executing a VSLAM process by using the extracted image data.

10 . A computer program product including programmed instructions embodied in and stored on a non-transitory computer readable medium, the instructions, when executed by a computer causing the computer to perform:

buffering image data of surroundings of a moving body obtained by an imaging unit of the moving body;

executing a thinning process of the buffered image data at different intervals according to extracted image determination information to extract image data;

transmitting extracted image data in a time-series sequence; and

executing a VSLAM process by using the extracted image data.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 8, 2024
From: OHHASHI, KAZUYUKI
To: SOCIONEXT INC.
Reel/Frame 067343/0198 →
Continuity (2)
Continuation PCTJP2021041428 · Nov 10, 2021
Related Publication 20240288281A1 · Aug 29, 2024
References Cited (23)
US 10268201B2 · Iwama · 2019 [cited by examiner]
US 20160205889A1 · Bin · 2016 [cited by applicant]
US 20170206666A1 · Homma et al. · 2017 [cited by applicant]
US 20190043204A1 · Mandal · 2019 [cited by examiner]
US 20200230820A1 · Watanabe et al. · 2020 [cited by applicant]
US 20210107465A1 · Hiei · 2021 [cited by applicant]
US 20210270633A1 · Tomono · 2021 [cited by applicant]
US 20220222851A1 · Yamaguchi et al. · 2022 [cited by applicant]
US 20220277480A1 · Tokuhiro et al. · 2022 [cited by applicant]
US 20230245471A1 · Hiei · 2023 [cited by applicant]
JP 2016045874A · 2016 [cited by applicant]
JP 2016123021A · 2016 [cited by applicant]
JP 2018205949A · 2018 [cited by applicant]
JP 2020153956A · 2020 [cited by applicant]
JP 2021062684A · 2021 [cited by applicant]
JP 2021082181A · 2021 [cited by applicant]
WO 2019073795A1 · 2019 [cited by applicant]
WO 2020026294A1 · 2020 [cited by applicant]
WO 2020246261A1 · 2020 [cited by applicant]
Machine translation of JP2020153956A specification (Year: 2020). [cited by examiner]
International Search Report dated Dec. 21, 2021 issued in International Patent Application No. PCT/JP2021/041428, with English translation. [cited by applicant]
Written Opinion of the International Searching Authority dated Dec. 21, 2021 issued in International Patent Application No. PCT/JP2021/041428, with English translation. [cited by applicant]
Fu-Sheng Huang et al., “Vision SLAM Using Omni-Directional Visual Scan Matching”, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, Sep. 22-26, 2008, pp. 1588-1593. [cited by applicant]