Method and flat bed machine tool for detecting a fitting position of a supporting bar

Patent metadata

Field	Value
Publication number	US-12106513-B2
Application number	US-202318159099-A
Country	US
Kind code	B2
Filing date	Jan 25, 2023
Priority date	Aug 7, 2020
Publication date	Oct 1, 2024
Grant date	Oct 1, 2024

Abstract

A method detects a suspension position of a supporting bar in a pallet, having supporting bars along a longitudinal direction, each with multiple supporting bar tips along a main direction of extent. The supporting bar tips define a supporting plane. A two-dimensional contrast-image dataset of the pallet is created, its pixels being assigned a pixel value and a pixel-area unit of the supporting plane. The contrast-image dataset has regions that are assigned to the supporting bar tips as local pixel-value extremes in a uniform pixel-value background. A longitudinal position is determined in the contrast-image dataset of the regions that are assigned to the supporting bar tips a supporting bar using the local pixel-value extremes. The suspension position of the supporting bar in the pallet is deduced based on the longitudinal position in the contrast-image dataset and an extent of the pixel-area unit in the longitudinal direction.

First claim

The invention claimed is:

1. A method for detecting a suspension position of a supporting bar in a pallet, which is fitted with a plurality of supporting bars along a longitudinal direction, the supporting bars comprising the supporting bar, each of the supporting bars having multiple supporting bar tips along a main direction of extent, which is aligned transversely to the longitudinal direction of the pallet, and the supporting bar tips of the plurality of supporting bars defining a supporting plane, the method comprising:
creating a two-dimensional contrast-image dataset of the pallet, having a plurality of image pixels, each of the image pixels being assigned a pixel value and a pixel-area unit of the supporting plane, and the contrast-image dataset comprising regions that are assigned to the supporting bar tips as local pixel-value extremes in a uniform pixel-value background;
determining a longitudinal position in the contrast-image dataset of the regions that are assigned to the supporting bar tips of one of the plurality of supporting bars using the local pixel-value extremes; and
deducing the suspension position of the supporting bar in the pallet on the basis of the longitudinal position in the contrast-image dataset and an extent of the pixel-area unit in the longitudinal direction.

2. The method as claimed in claim 1 , wherein one of the regions assigned to the supporting bar tips is assigned to a supporting bar tip or to a flank leading to the supporting bar tip.

3. The method as claimed in claim 1 , wherein the uniform pixel-value background does not represent a structure or comprises image pixels that have a constant pixel value or an arbitrary pixel-value distribution about a constant pixel value.

4. The method as claimed in claim 1 , wherein the creation of the contrast-image data set of the pallet also comprises:
producing a two-dimensional camera image of the pallet in the visible or infrared spectrum, the camera image comprising the image pixels arranged in rows and columns, to which the pixel-area unit of the supporting plane is respectively assigned;
Fourier transforming the camera image into a frequency domain and outputting a transformation-frequency dataset;
filtering the transformation-frequency dataset to emphasize frequencies in the frequency domain that belong to the regions that are assigned to the supporting bar tips; and
transforming back the filtered transformation-frequency dataset into a back-transformed image dataset by an inverse Fourier transformation, and outputting the back-transformed image dataset as the contrast-image dataset.

5. The method as claimed in claim 4 , wherein the supporting bar tips comprise adjacent supporting bar tips in the main direction of extent that have substantially the same tip spacing from one another, and wherein the filtering of the transformation-frequency dataset comprises:
identifying a frequency band assigned to the tip spacing in the frequency domain, the frequency band being formed around a tip repetition frequency, which is assigned to the main direction of extent, and being obtained from:

h
*
Δ
⁢
x

d

,

 where:
h: is a number of pixels of the region of the supporting plane in the main direction of extent that is represented in the camera image,
Δx: is the extent of the pixel-area unit in the main direction of extent and
d: is the tip spacing of adjacent supporting bar tips; and
restricting the transformation-frequency dataset to the frequency band.

6. The method as claimed in claim 4 , wherein the production of the two-dimensional camera image is performed by producing a dark-field camera image of the pallet in the near-infrared frequency spectrum, and wherein the dark-field camera image is recorded from a recording direction that forms an angle with the supporting plane that lies in the range from 10° to 70°, and which extends at an angle in a range from 70° to 110° to the main direction of extent.

7. The method as claimed in claim 1 , wherein the creation of the contrast-image data set of the pallet further comprises:
producing the contrast-image dataset by producing a dark-field camera image of the pallet in the near-infrared frequency spectrum from a recording direction, which forms an angle with the supporting plane which lies in the range from 10° to 70°, and which extends at an angle in a range from 70° to 110° to the main direction of extent.

8. The method as claimed in claim 1 , wherein the creation of the contrast-image dataset of the pallet further comprises:
illuminating the pallet from above with light of a near-infrared frequency spectrum from one or more illumination directions.

9. The method as claimed in claim 8 , wherein at least one of the illumination directions forms an angle with the supporting plane which is less than 30°, and the at least one of the illumination directions, projected into the supporting plane, forms an angle with a main direction of extent of the supporting bar which is less than 30°.

10. The method as claimed in claim 4 , wherein the production of the two-dimensional camera image or the production of the two-dimensional dark-field camera image comprises:
recording multiple partial camera images, which in each case two-dimensionally represent a partial region of the pallet, and
putting together the partial camera images to form the two-dimensional camera image or the two-dimensional dark-field camera image of the pallet.

11. The method as claimed in claim 1 , wherein the determination of the longitudinal position in the contrast-image dataset comprises:
carrying out a template-matching image analysis by using a template, which is formed as an image dataset of a supporting bar having a plurality of supporting bar tips.

12. The method as claimed in claim 1 , wherein the determination of the longitudinal position in the contrast-image dataset comprises:
summating the pixel values of the image pixels of the contrast-image dataset row-by-row in accordance with the main direction of extent, and outputting a first distribution of first pixel-value sums; and
determining a local extreme in the first distribution, and outputting the row of the local extreme as a longitudinal position.

13. The method as claimed in claim 12 , the method further comprising:
summating the pixel values of the image pixels of the contrast-image dataset column-by-column in accordance with the longitudinal direction in the region of the local extreme, and outputting a second distribution of second pixel-value sums;
determining multiple local extremes in the second distribution, and outputting the columns of the local extremes; and
determining image positions of the regions in the contrast-image dataset that are assigned to the supporting bar tips on a basis of the corresponding row of the determined local extreme and the columns of the determined local extremes.

14. The method as claimed in claim 1 , wherein:
the supporting bars are suspendable at predetermined suspension positions on one longitudinal side of the pallet, and the main direction of extent extends transversely to the longitudinal side,
the pallet has a reference structure, which is identifiable in the contrast-image dataset as a reference pixel arrangement, and
the deduction of the suspension position of the supporting bar in the pallet is

Assignees

• Trumpf Werkzeugmaschinen Se Co Kg

Inventors

• Struckmeier Frederick

Classifications

• G06T5/94

  based on local image properties, e.g. for local contrast enhancement · CPC title

• G06T2207/30108

  Industrial image inspection · CPC title

• G06T2207/10048

  Infrared image · CPC title

• G06T7/001

  using an image reference approach · CPC title

• G06T5/50

  using two or more images, e.g. averaging or subtraction · CPC title