IP Library › Granted Patent US 10,074,551
Granted Patent B2
US 10,074,551 · App. 15/278,623 · Granted Sep 11, 2018

Position detection apparatus, position detection method, information processing program, and storage medium

Inventors: Yoshihisa Minato (Kyoto, JP); Kosuke Hattori (Kusatsu, JP); Yutaka Kiuchi (Kusatsu, JP); Yuki Akatsuka (Kyoto, JP)
Assignee: OMRON Corporation
H01L21/67259G06T7/0004G06T7/0042H01L21/681H01L21/682G06T2207/10004G06T2207/30148
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 10,074,551
App. No.
15/278,623
Granted
Sep 11, 2018
Kind
B2
Abstract

A hypothesis testing position detection apparatus improves robustness against abnormal detection values, and achieves both high accuracy estimation and high-speed estimation processing. An image processing apparatus extracts, from calculated values for a central position of a plane shape, one of the calculated values nearer a provisional center as a candidate for evaluation (testing) performed using a plurality of detection points.

Claims (43)

1. A position detection apparatus comprising a processor configured with a program to perform operations comprising:

operation as an image obtaining unit configured to obtain a shape;

operation as a provisional value setting unit configured to set a provisional parameter comprising an estimated value for a parameter associated with the shape;

operation as a calculation unit configured to:

extract a plurality of detection points associated with the shape;

select, from the detection points, one or more combinations of selection points;

generate a plurality of hypothesis shapes based on the one or more combinations of selection points; and

calculate a plurality of potential values for the parameter, each potential value of the plurality of potential values corresponding to at least one of the plurality of hypothesis shapes;

operation as an extraction unit configured to extract, from the plurality of potential values calculated by the calculation unit, one or more of the plurality of potential values having an error relative to the provisional parameter that falls within a predetermined range; and

operation as a determination unit configured to determine, from the one or more of the plurality of potential values extracted by the extraction unit, a potential value with a smallest error as a final estimated value for the parameter.

2. The position detection apparatus according to claim 1 , wherein

the shape comprises a captured image or a measurement value of an object for which the parameter is to be determined by the position detection apparatus.

3. The position detection apparatus according to claim 1 , wherein

the processor is further configured with the program to perform operations such that operation as the determination unit comprises operation as the determination unit that determines, from the one or more of the plurality of potential values extracted by the extraction unit, the final estimated value for the parameter using a number of the plurality of detection points located within a predetermined distance from the shape estimated using the plurality of potential values or a sum of distances to each of the detection points from the shape estimated using the plurality of potential values.

4. The position detection apparatus according to claim 1 , wherein the processor is further configured with the program to perform operations such that operation as the provisional value setting unit configured to set the provisional parameter comprising an estimated value for the parameter associated with the shape comprises operation as the provisional value setting unit configured to set the provisional parameter using an area designated as an area including an outline of the shape, or a value designated as an approximate value of the parameter.

5. The position detection apparatus according to claim 1 , wherein

the processor is further configured with the program to perform operations such that when the processor, operating as the calculation unit, calculates the plurality of potential values using one of the hypothesis shapes, the processor, operating as the extraction unit extracts, from the plurality of potential values, one of the plurality of potential values whose error relative to the provisional parameter falls within the predetermined range.

6. The position detection apparatus according to claim 1 , wherein

the parameter is a central position of a substantially circular shape,

the processor is further configured with the program to perform operations such that operation as the calculation unit comprises operation as the calculation unit that calculates intersections of two of the plurality of hypothesis shapes with a predetermined radius, each having a different one of the selection points as a center, as at least one value for the central position; and

when the processor, operating as the calculation unit, obtains two intersections using the selection points, the processor, operating as the extraction unit, extracts, from the two intersections, an intersection with a shorter distance to a provisional central position set as the provisional parameter of the central position, or an intersection included in a provisional central area set as the provisional parameter of the central position, as the calculated value for the central position.

7. A position detection method, comprising:

obtaining a shape;

setting a provisional parameter comprising an estimated value for a parameter associated with the shape;

extracting a plurality of detection points associated with the shape;

selecting, from the detection points, one or more combinations of selection points;

generating a plurality of hypothesis shapes based on the one or more combinations of selection points;

calculating a plurality of potential values for the parameter, each potential value of the plurality of potential values corresponding to at least one of the plurality of hypothesis shapes;

extracting, from the calculated plurality of potential values, one or more of the plurality of potential values with an error relative to the provisional parameter that fall within a predetermined range; and

determining, from the extracted one or more of the plurality of potential values, a potential value with a smallest error as a final estimated value for the parameter.

8. A non-transitory computer-readable storage medium comprising instructions that, when executed, cause a processor to perform operations comprising the position detection method according to claim 7 .

9. The position detection method according to claim 7 , wherein the shape comprises a captured image or a measurement value of an object.

10. The position detection method according to claim 7 , wherein

determining from the extracted one or more of the plurality of potential values, the potential value with the smallest error as the final estimated value for the parameter comprises determining, from the extracted one or more of the plurality of potential values, the final estimated value for the parameter using a number of the plurality of detection points located within a predetermined distance from the shape estimated using the plurality of potential values or a sum of distances to each of the detection points from the shape estimated using the plurality of potential values.

11. The method according to claim 7 , further comprising:

setting the provisional parameter using an area designated as an area including an outline of the shape, or a value or a range of values designated as an approximate value of the parameter.

12. The method according to claim 7 , wherein:

when calculating a plurality of potential values for the parameter, each potential value of the plurality of potential values corresponding to at least one of the plurality of hypothesis shapes comprises calculating a plurality of potential values for the parameter using one of the hypothesis shapes,

extracting, from the calculated plurality of potential values, one or more of the calculated plurality of potential values having the error relative to the provisional parameter that falls within a predetermined range comprises extracting one of the plurality of potential values whose error relative to the provisional parameter falls within the predetermined range.

13. The method according to claim 7 , wherein

the parameter is a central position of a substantially circular shape,

calculating the plurality of potential values for the parameter comprises calculating intersections of the plurality of hypothesis shapes with a predetermined radius, each having one of the selection points as a center, as at least one value for the central position, and

when calculating the plurality of potential values for the parameter returns two intersections, extracting, from the calculated plurality of potential values, one or more of the plurality of potential values having the error relative to the provisional parameter that falls within a predetermined range comprises extracting, from the two intersections, an intersection with a shorter distance to a provisional central position set as a provisional parameter of the central position, or an intersection included in a provisional central area set as the provisional parameter of the central position, as the calculated value for the central position.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 18, 2016
From: MINATO, YOSHIHISA; HATTORI, KOSUKE; KIUCHI, YUTAKA; AKATSUKA, YUKI
To: OMRON CORPORATION
Reel/Frame 040045/0582 →
Priority Claims (1)
JP 2015-212123 · Oct 28, 2015 · national
Continuity (1)
Related Publication 20170125271A1 · May 4, 2017