Method and device for detecting deviations of an object surface

• US 10,101,153 B2
• Filed: 07/25/2013
• Issued: 10/16/2018
• Est. Priority Date: 08/27/2012
• Status: Active Grant

• Current Assignee: INB Vision AG (Micro-Epsilon Messtechnik GmbH & Co., KG)
• Original Assignee: INB Vision AG (Micro-Epsilon Messtechnik GmbH & Co., KG)
• Inventors: Michaelis, Bernd, Lilienblum, Tilo, Von Enzberg, Sebastian
• Primary Examiner(s): Diallo, Mamadou
• Application Number:
  US14/423,393
• Publication Number:
  US 20150276397A1
• Time in Patent Office: 1,909 Days
• CPC Class Codes: G01B 21/047 Accessories, e.g. for positioning, for tool-setting, for measuring probes
• CPC Class Codes: G01B 21/20 for measuring contours or curvatures, e.g. determining profile
• CPC Class Codes: G01B 21/30 for measuring roughness or irregularity of surfaces
• CPC Class Codes: G06T 17/30 Polynomial surface description

Abstract

The invention relates to a method for detecting deviations of an object surface using a comparison between measured data of the surface and specified reference data. A surface description, at least portions of which are parametric, is generated as a target surface model using the specified reference data, and the comparison is carried out using the target surface model and the measured data. The invention likewise relates to a device for detecting deviations of an object surface using a comparison between measured data of the surface and specified reference data.

Claims

1. A method for recognizing deviations (D3) of a surface (1) of an object, said method comprising the steps of:

generating, via a computing unit, pre-specified machine-readable reference data (A1);

computing, via the computing unit, an at least sectionally parametric machine-readable description of the surface (1) as a target surface model (D4), said at least sectionally parametric machine-readable description of the surface (1) being computed based at least in part upon the pre-specified machine-readable reference data (A1);

capturing, via a sensing unit, measured data (D1) of the surface (1), said sensing unit being configured to capture data at least one tactilely, optically, or via sounds, the sounds comprising at least one of ultrasonic or a radar; and

performing, via the computing unit, a comparison of the measured data (D1) of the surface (1) captured via the sensing unit with the pre-specified machine-readable reference data (A1), the comparison being carried out based upon said target surface model (D4),

wherein the target surface model (D4) is computed, via the computing unit, from the pre-specified machine-readable reference data (A1) using statistical methods, with a plurality of different data sets of reference data (A1).

2. A method according to claim 1, wherein the parametric target surface description (1) is a spline surface description.

3. A method according to claim 2, wherein a particularly hierarchical, tensor product B-spline surface is used as the spline surface description.

4. A method according to one claim 1, wherein the measured data (D1) is determined via an optical photogrammetric method, particularly in the form of a time correlation and/or phase shift method.

5. A method according to one claim 4, wherein the optical photogrammetric method comprises at least one of a time correlation method or a phase shift method.

6. A method according to claim 4, wherein the measured data (D1) is determined using a projection of a predetermined pattern sequence onto the surface (1) and by a subsequent optical detection of the projected pattern sequence.

7. A method according to claim 6, wherein the predetermined pattern sequence is a sine pattern sequence.

8. A method according to claim 1, wherein:

the target surface model (D4) is created via a neural network which is trained with a plurality of different data sets of reference data (A1);

the at least sectionally parametric description of the surface is created from the measured data (D1) as a current surface model; and

the comparison is carried out as a model comparison of the target surface model (D4) and the current surface model.

9. A method according to claim 1, wherein the comparison is carried out on the basis of an orthogonal distance between the at least sectionally parametric description of the surface (1) and at least one measurement point of the measured data (D1).

10. A method according to claim 1, wherein a target surface model (D4) which is adapted to the measured data (D1) is created and used for the comparison.

11. A method according to claim 1, wherein:

at least one of the pre-specified reference data (A1) or the measured data (D1) are filtered prior to the creation of the at least sectionally parametric description of the surface via at least one filter method; and

the pre-specified reference data (A1) and at least one of the measured data (A1) or the difference data, from the measured data (A1) and the target surface model (D4), calculated from the comparison, are filtered via the same filter method.

12. A method according to claim 1, wherein the prespecified reference data (A1) is generated at least partially artificially.

13. A device for recognizing deviations (D3) in a surface of an object using a comparison of measured data (D1) of the surface and pre-specified machine-readable reference data (A1) and for carrying out the method according to claim 1, said device comprising:

the sensing unit configured for detecting the measured data (D1) and the reference data (A1); and

one or more processing devices (4) configured to;

compute the at least sectionally parametric machine-readable description of the surface (1) as the target surface model (D4) via the pre-specified machine-readable reference data (A1); and

perform the comparison based upon the target surface model (D4) and the measured data (D1),

wherein the target surface model (D4) is determined, via the one or more processing devices (4), from the pre-specified machine-readable reference data (A1) using statistical methods, with the plurality of different data sets of reference data (A1).

14. A device according to claim 13, wherein the sensing unit includes at least one camera (2) and one illumination device (3).

15. A device according to claim 14, wherein the illumination device (3) is configured to provide a structured illumination of the surface (1).

16. A device according to claim 13, wherein the sensing unit comprises a linear sensor.