IP Library › Granted Patent US 12,613,255
Granted Patent B2
US 12,613,255 · App. 18/273,872 · Granted Apr 28, 2026

Rotation state estimation apparatus, method thereof, and program

Inventors: Dan Mikami (Tokyo, JP); Naoki Saijo (Tokyo, JP); Masumi Yamaguchi (Tokyo, JP); Takehiro Fukuda (Tokyo, JP); Susumu Yamamoto (Tokyo, JP); Makio Kashino (Tokyo, JP)
Assignee: NTT, Inc.
G01P3/38G06T7/248G06T2207/10016G06T2207/30224
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 12,613,255
App. No.
18/273,872
Granted
Apr 28, 2026
Kind
B2
Abstract

A target estimation image which is an image of a target at a time point t+w·u obtained by spinning the object in an object image which is an image of the object at a time point t obtained from an input video in time-series by w unit time on the basis of a hypothesis of spin state and an object image at the time point t+w·u obtained from the input video are used, to estimate a spin state of the object by selecting a hypothesis of spin state and w in which likelihood of the target estimation image becomes high from among a plurality of hypotheses of spin states and a plurality of w, wherein an absolute value of W is an integer of 1 or more and u is a unit time.

Claims (24)

1 . A spin state estimation device comprising a processor executing a computer-executable instructions that cause the spin state estimation device to perform operations comprising:

iteratively updating, based on varying w, an estimated spin state of a spinning object as output by comparing a target estimation image at a time point t+w·u and an object image at the time point t+w·u to dynamically select a combination of a hypothesis of spin state of a plurality of hypotheses of spin state and the w of a plurality of w,

wherein an absolute value of the w is an integer of 1 or more,

the u represents a unit time,

the target estimation image at the time point t+w·u represents an image of the spinning object at the time point t+w·u estimated based on a captured image of the spinning object at a time point t from an input video in time-series according to the hypothesis of spin state of the plurality of hypotheses of spin state,

the object image at the time point t+w·u represents another captured image of the spinning object obtained from the input video, and

the dynamically selecting the combination of the hypothesis of spin state at the time point t+w·u and the w of the plurality of w is based on maximizing a likelihood of matching the target estimation image at the time point t+w·u and the object image at the time point t+w·u among target estimation images according to respective hypotheses of the plurality of hypotheses and respective w of the plurality of w, and the iteratively updating operation thereby enables estimating the spin state of the spinning object with accuracy over time.

2 . The spin state estimation device according to claim 1 , wherein

K as an integer of 2 or more, and

the target estimation images are images of an object of time points t 1 +w·u, t 2 +w·u, . . . , t K +w·u obtained by spinning the object in the object images at time points t 1 , t 2 , . . . , t K by w unit time on the basis of a hypothesis of spin state and object images at the time points t 1 +w·u, t 2 +w·u, . . . , t K +w·u obtained from the input video, to estimate the spin state of the object by dynamically and respectively selecting a hypothesis of spin state and w in which likelihood of the target estimation image becomes high from among a plurality of hypotheses of spin states and a plurality of w.

3 . The spin state estimation device, according to claim 1 , wherein

the hypothesis of spin state represents information corresponding to a spin shaft of the spinning object and information corresponding to a spin amount of the spinning object, and

the computer-executable instructions cause the spin state estimation device to further perform operations comprising: obtaining information corresponding to at least one of the spin shaft of the spinning object and the spin amount per unit time of the spinning object as the spin state of the spinning object on basis of information r w corresponding to the spin shaft of the spinning object, information θ w corresponding to the spin amount of the spinning object, and w represented by the dynamically selected hypothesis of spin state.

4 . The spin state estimation device, according to claim 1 , wherein

the hypothesis of spin state represents information corresponding to the spin shaft of the spinning object and information corresponding to a spin amount of the spinning object, and

the computer-executable instructions cause the spin state estimation device to further perform operations comprising: obtaining information including information corresponding to the spin amount per unit time and not including information corresponding to the spin shaft of the spinning object as the spin state of the spinning object and/or outputs an effect of being unable to estimate information corresponding to the spin shaft of the spinning object, when the spin amount per unit time obtained based on the information θ w and w corresponding to the spin amount of the spinning object represented by the dynamically selected hypothesis of spin state is a π+2 nπ.

5 . A spin state estimation method, comprising:

iteratively updating, based on varying w, an estimated spin state of a spinning object as output by comparing a target estimation image at a time point t+w·u and an object image at the time point t+w·u to dynamically select a combination of a hypothesis of spin state of a plurality of hypotheses of spin state and the w of a plurality of w,

wherein an absolute value of the w is an integer of 1 or more,

the u represents a unit time,

the target estimation image at the time point t+w·u represents an image of a target at the time point t+w·u estimated based on a captured image of the spinning object at a time point t from an input video in time-series according to the hypothesis of spin state of the plurality of hypotheses of spin state,

the object image at the time point t+w·u represents another captured image of the spinning object from the input video, and

the dynamically selecting the combination of the hypothesis of spin state at the time point t+w·u and the w of the plurality of w is based on maximizing a likelihood of matching the target estimation image at the time point t+w·u and the object image at the time point t+w·u among target estimation images according to respective hypotheses of the plurality of hypotheses and respective w of the plurality of w, and the iteratively updating operation thereby enables estimating the spin state of the spinning object with accuracy over time.

6 . A non-transitory computer-readable recording medium storing a program for causing a computer to function as a spin state estimation device according to claim 1 .

Assignments (2)
CHANGE OF NAME Recorded Jan 1, 2026
From: NIPPON TELEGRAPH AND TELEPHONE CORPORATION
To: NTT, INC.
Reel/Frame 074164/0641 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 24, 2023
From: MIKAMI, DAN; SAIJO, NAOKI; YAMAGUCHI, MASUMI; FUKUDA, TAKEHIRO; YAMAMOTO, SUSUMU; KASHINO, MAKIO
To: NIPPON TELEGRAPH AND TELEPHONE CORPORATION
Reel/Frame 064358/0274 →
Continuity (1)
Related Publication 20240069055A1 · Feb 29, 2024
References Cited (18)
US 9855481B2 · Tuxen · 2018 [cited by examiner]
US 9911046B1 · Yakimenko · 2018 [cited by examiner]
US 10319108B2 · Segert · 2019 [cited by examiner]
US 20130135466A1 · Kim · 2013 [cited by examiner]
US 20140185881A1 · Nakamura · 2014 [cited by examiner]
US 20160350922A1 · Tofolo · 2016 [cited by examiner]
US 20180005385A1 · Suk · 2018 [cited by examiner]
US 20180174308A1 · Ijiri · 2018 [cited by examiner]
US 20180353828A1 · Otten · 2018 [cited by examiner]
US 20220152453A1 · Mikami et al. · 2022 [cited by applicant]
US 20220375203A1 · Mikami · 2022 [cited by examiner]
US 20240104750A1 · Mikami · 2024 [cited by examiner]
US 20240112346A1 · Mikami · 2024 [cited by examiner]
JP 2020153677A · 2020 [cited by applicant]
Ijiri et al. “Automatic spin measurements for pitched Baseballs via consumer-grade high-speed cameras”, Springer-Verlag London 2017 (Year: 2017). [cited by examiner]
Sz'ep, “Ballrotationdetectionbased on Arbitraryfeatures”, In Proceedings of the International Conferenceon Computer Vision Theory and Applications (VISAPP-2011), pp. 700-703 (Year: 2011). [cited by examiner]
Theobalt et al., “Pitching a Baseball |Tracking High-Speed Motion with Multi-Exposure Images”, 2004 ACM 0730-0301/04/0800-0540 (Year: 2004). [cited by examiner]
Jiri et al. (2017) “Automatic spin measurements for pitched Baseballs via consumer-grade high-speed cameras” Signal, Image and Video Processing, vol. 11, Issue 7, issued on Oct. 2017. [cited by applicant]