IP Library › Granted Patent US 12,354,253
Granted Patent B2
US 12,354,253 · App. 18/863,659 · Granted Jul 8, 2025

Alignment system, alignment method, and recording medium

Inventors: Yuji Asano (Tokyo, JP); Weihau Lee (Tokyo, JP); Yoshihiro Sugiyama (Tokyo, JP)
Assignee: MITSUBISHI ELECTRIC CORPORATION
G06T7/0004G05B15/02G06T7/70G06T2207/30164
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 12,354,253
App. No.
18/863,659
Granted
Jul 8, 2025
Kind
B2
Abstract

An alignment system includes an image processor to detect an identification target included in a workpiece from a captured image of the workpiece, and an operation controller to control a driver to move the workpiece based on actual coordinates of the identification target detected by the image processor. The image processor determines within the captured image a search range partially covering the captured image and having a predetermined size based on position information generated based on an output from a position sensor in the driver, and detects the identification target from a portion of the captured image corresponding to the search range.

Claims (39)

1. An alignment system, comprising:

an image processor to detect an identification target included in a workpiece from a captured image of the workpiece; and

an operation controller to control a driver to move the workpiece based on actual coordinates in a reference coordinate system that indicate a position of the identification target detected by the image processor in the captured image,

wherein the image processor

pre-identifies a constant matrix representing a correspondence between coordinates indicating position information acquired from a position sensor in the driver and the actual coordinates of the identification target,

determines within the captured image a search range partially covering the captured image, having a predetermined size, and including prediction coordinates that are calculated based on the position information using the constant matrix and that are predicted values of the actual coordinates, and

detects the identification target from a portion of the captured image corresponding to the search range.

2. The alignment system according to claim 1 , wherein

the driver is a servomotor to move a mount table on which the workpiece is placed, and

the position information corresponds to a position of the mount table and is generated based on an output from an encoder attached to the servomotor.

3. The alignment system according to claim 1 , wherein

the search range has a size acquired by adding a margin determined based on a movement speed of the driver to a shape or a size of the identification target.

4. The alignment system according to claim 1 , wherein

the search range has a size acquired by adding, to a shape or a size of the identification target, a margin determined based on a difference between the prediction coordinates calculated based on the position information and the actual coordinates detected from the captured image at past time points corresponding to each other.

5. The alignment system according to claim 1 , wherein

the actual coordinates include a rotation angle of the identification target, and

the image processor identifies the rotation angle of the identification target by searching a portion of the captured image within a search angular range having a predetermined angular width and including the prediction coordinates calculated based on the position information.

6. The alignment system according to claim 1 , wherein

the image processor performs a rough search on a full range of the captured image when the identification target is not detected through a fine search performed on the portion of captured image corresponding to the search range determined based on the position information.

7. An alignment method, comprising:

searching a captured image of a workpiece including an identification target to detect the identification target; and

providing a command to a driver to move the workpiece based on actual coordinates in a reference coordinate system that indicate a position of the detected identification target in the captured image,

wherein searching the captured image includes

pre-identifying a constant matrix representing a correspondence between coordinates indicating position information acquired from a position sensor in the driver and the actual coordinates of the identification target, and

detecting the identification target from a portion of the captured image corresponding to a search range within the captured image, the search range partially covering the captured image, having a predetermined size, and including prediction coordinates that are calculated based on the position information using the constant matrix and that are predicted values of the actual coordinates.

8. A non-transitory computer-readable recording medium storing a program executable by a computer in an alignment system to detect an identification target included in a workpiece from a captured image of the workpiece and to perform alignment control of the workpiece based on actual coordinates in a reference coordinate system that indicate a position of the detected identification target in the captured image, the computer being configured to perform image processing on the captured image, the program causing the computer to function as:

a searcher to

pre-identify a constant matrix representing a correspondence between coordinates indicating position information acquired from a position sensor in a driver performing the alignment control and the actual coordinates of the identification target,

determine within the captured image a search range partially covering the captured image, having a predetermined size, and including prediction coordinates that are calculated based on the position information using the constant matrix and that are predicted values of the actual coordinates, and

detect the identification target from a portion of the capture image

corresponding to the determined search range.

9. The alignment system according to claim 2 , wherein

the image processor performs a rough search on a full range of the captured image when the identification target is not detected through a fine search performed on the portion of captured image corresponding to the search range determined based on the position information.

10. The alignment system according to claim 3 , wherein

the image processor performs a rough search on a full range of the captured image when the identification target is not detected through a fine search performed on the portion of captured image corresponding to the search range determined based on the position information.

11. The alignment system according to claim 4 , wherein

the image processor performs a rough search on a full range of the captured image when the identification target is not detected through a fine search performed on the portion of captured image corresponding to the search range determined based on the position information.

12. The alignment system according to claim 5 , wherein

the image processor performs a rough search on a full range of the captured image when the identification target is not detected through a fine search performed on the portion of captured image corresponding to the search range determined based on the position information.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 7, 2024
From: ASANO, YUJI; LEE, WEIHAU; SUGIYAMA, YOSHIHIRO
To: MITSUBISHI ELECTRIC CORPORATION
Reel/Frame 069177/0250 →
Continuity (1)
Related Publication 20250166156A1 · May 22, 2025
References Cited (31)
US 8320613B2 · Krahnstoever · 2012 [cited by examiner]
US 10909715B1 · Boggs · 2021 [cited by examiner]
US 20010016293A1 · Nishi et al. · 2001 [cited by applicant]
US 20140301632A1 · Ikeda et al. · 2014 [cited by applicant]
US 20150077543A1 · Kerr · 2015 [cited by examiner]
US 20160192553A1 · Kawaguchi · 2016 [cited by applicant]
US 20180289982A1 · Sayeh · 2018 [cited by examiner]
US 20190139196A1 · Adler-Golden · 2019 [cited by examiner]
US 20210182077A1 · Chen · 2021 [cited by examiner]
US 20210327259A1 · Lin · 2021 [cited by examiner]
US 20230044983A1 · Sayeh · 2023 [cited by examiner]
JP H05332742A · 1993 [cited by applicant]
JP H09036202A · 1997 [cited by applicant]
JP 2002023851A · 2002 [cited by applicant]
JP 2014020336A · 2014 [cited by applicant]
JP 2014203365A · 2014 [cited by applicant]
JP 2019215633A · 2019 [cited by applicant]
JP 2020110916A · 2020 [cited by applicant]
JP 2022045522A · 2022 [cited by applicant]
WO 2015019487A1 · 2015 [cited by applicant]
International Search Report and Written Opinion mailed on Sep. 27, 2022, received for PCT Application PCT/JP2022/028957, filed on Jul. 27, 2022, 9 pages including English Translation. [cited by applicant]
Notice of Reason for Refusal mailed on Feb. 28, 2023, received for JP Application 2022-577414, 4 pages including English Translation. [cited by applicant]
Notice of Reason for Refusal mailed on Jul. 4, 2023, received for JP Application 2022-577414, 8 pages including English Translation. [cited by applicant]
Decision to Grant mailed on Sep. 26, 2023, received for JP Application 2022-577414, 5 pages including English Translation. [cited by applicant]
International Search Report and Written Opinion mailed on Sep. 27, 2022, received for PCT Application PCT/JP2022/028956, filed on Jul. 27, 2022, 9 pages including English Translation. [cited by applicant]
Notice of Reason for Refusal mailed on Feb. 28, 2023, received for JP Application 2022-577409, 4 pages including English Translation. [cited by applicant]
Notice of Reason for Refusal mailed on Jul. 4, 2023, received for JP Application 2022-577409, 8 pages including English Translation. [cited by applicant]
Decision to Grant mailed on Sep. 26, 2023, received for JP Application 2022-577409, 5 pages including English Translation. [cited by applicant]
International Search Report and Written Opinion mailed on Sep. 27, 2022, received for PCT Application PCT/JP2022/028958, filed on Jul. 27, 2022, 9 pages including English Translation. [cited by applicant]
Decision to Grant mailed on Mar. 7, 2023, received for JP Application 2022-577416, 5 pages including English Translation. [cited by applicant]
Chinese Office Action dated Apr. 4, 2025, issued for the corresponding CN patent application No. 202280096683.8 and the English translation, 18pp. [cited by applicant]