WO2023208507A1 - Procédé pour étalonner un système de traitement d'image d'une machine d'usinage de tôle - Google Patents

Procédé pour étalonner un système de traitement d'image d'une machine d'usinage de tôle Download PDF

Info

Publication number
WO2023208507A1
WO2023208507A1 PCT/EP2023/058283 EP2023058283W WO2023208507A1 WO 2023208507 A1 WO2023208507 A1 WO 2023208507A1 EP 2023058283 W EP2023058283 W EP 2023058283W WO 2023208507 A1 WO2023208507 A1 WO 2023208507A1
Authority
WO
WIPO (PCT)
Prior art keywords
transformation rule
removal area
calibration plate
transformation
camera
Prior art date
Application number
PCT/EP2023/058283
Other languages
German (de)
English (en)
Inventor
Willi Pönitz
Marc Teschner
Korbinian WEISS
Original Assignee
TRUMPF Werkzeugmaschinen SE + Co. KG
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by TRUMPF Werkzeugmaschinen SE + Co. KG filed Critical TRUMPF Werkzeugmaschinen SE + Co. KG
Publication of WO2023208507A1 publication Critical patent/WO2023208507A1/fr

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
    • B25J9/1697—Vision controlled systems
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K26/00—Working by laser beam, e.g. welding, cutting or boring
    • B23K26/02—Positioning or observing the workpiece, e.g. with respect to the point of impact; Aligning, aiming or focusing the laser beam
    • B23K26/03—Observing, e.g. monitoring, the workpiece
    • B23K26/032—Observing, e.g. monitoring, the workpiece using optical means
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K26/00—Working by laser beam, e.g. welding, cutting or boring
    • B23K26/36—Removing material
    • B23K26/38—Removing material by boring or cutting
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
    • G05B19/401—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by control arrangements for measuring, e.g. calibration and initialisation, measuring workpiece for machining purposes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/36—Nc in input of data, input key till input tape
    • G05B2219/36199—Laser cutting
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/37—Measurements
    • G05B2219/37009—Calibration of vision system, camera, adapt light level
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/37—Measurements
    • G05B2219/37015—Adaptive online camera, vision calibration
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/39—Robotics, robotics to robotics hand
    • G05B2219/39057—Hand eye calibration, eye, camera on hand, end effector
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/45—Nc applications
    • G05B2219/45041—Laser cutting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30164—Workpiece; Machine component
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30244—Camera pose

Definitions

  • the invention relates to a method for calibrating an image processing system of a sheet metal processing machine, wherein at least one camera of the image processing system detects a removal area for processed workpieces.
  • WO 2016/005159 A2 describes a calibration method for an image processing system as part of a method for processing flat workpieces, in particular sheets, or three-dimensional workpieces on a processing machine.
  • a live image of a workpiece to be machined is captured using an image capture device for capturing two-dimensional images.
  • the two-dimensional live image from the image capture device must be calibrated to the three-dimensional machine coordinate system.
  • a processing contour e.g. a laser cut to be carried out
  • one of the machine reference points can be formed by a movable machine component (e.g. by the laser processing head of a laser processing machine), which has been moved to a position known in the machine coordinate system before the at least one reference live image is detected.
  • machine reference points can be added to a workpiece through machining operations, for example by marking or cutting out hole circles.
  • the image capture device is calibrated in particular manually by a CAD representation is brought to coincide with a displayed image of the workpiece.
  • WO 2018/073418 Al or WO 2018/073419 Al it is known to aim a camera at a sorting table of a flat-bed machine tool for sheet metal processing. After calibrating the camera to the sheet metal surface or the sorting table, an image processing algorithm can be used to detect parts. For example, an optimal sorting strategy can be suggested to an operator via a projection surface of a data source.
  • the removal area is usually formed by support elements, such as webs.
  • the removal area should extend in a plane that is typically horizontal. Furthermore, the removal area should be in a defined position relative to the sheet metal processing machine and camera according to the design specification.
  • the removal area is not exactly flat and/or is inaccurately aligned with the sheet metal processing machine or camera.
  • the removal area may be uneven, for example wavy. Misalignments and changes in position of the removal area also occur in practice.
  • a method for calibrating an image processing system of a sheet metal processing machine is therefore provided.
  • the sheet metal processing machine is in particular a flatbed machine.
  • the sheet metal processing machine can be a punching machine.
  • the sheet metal processing machine is preferably a laser cutting machine.
  • At least one camera of the image processing system captures a removal area for processed workpieces.
  • the camera is typically arranged obliquely above the removal area. An image captured by the camera therefore has perspective distortions.
  • the camera can be attached to a housing of the sheet metal processing machine.
  • the removal area can be formed on a pallet changer of the sheet metal processing machine.
  • the pallet changer particularly simplifies the transfer of processed workpieces and preferably also the transfer of raw parts to be processed.
  • the removal area can be formed with bars.
  • the webs can run parallel and at a distance from one another. Forming a support surface of the removal area with webs can help prevent workpieces, especially sheet metal workpieces, from sticking to the support surface. This simplifies the removal of the workpieces.
  • the removal area can have an extent of more than one meter, in particular more than two meters, in the plane of its extension.
  • the removal area should generally be flat. Due to manufacturing tolerances, wear and/or damage, the removal area is typically not exactly flat in practice, but can Have waves, depressions and / or elevations. Accordingly, an inclination of the removal area can deviate from a target orientation, for example due to inaccuracies during assembly. Furthermore, a position of the removal area relative to the sheet metal processing machine can deviate from a target position.
  • the calibration procedure includes the steps:
  • step C) transforming the images recorded in step B) with the transformation rule and measuring the calibration plate in the transformed images
  • step D calculating an error measure for the deviation between the known size of the calibration plate and the measured values for the size of the calibration plate determined in step C);
  • the transformation rule specified in step A) can be stored in the image processing system, in particular in a control device of the image processing system.
  • the transformation rule specifies how the captured perspective image can be converted into the top view.
  • the specified transformation rule can have been determined mathematically based on a target arrangement of the camera relative to the sampling area. Alternatively, the specified transformation rule can have been determined during a previously carried out calibration.
  • the calibration plate serves as a standard for comparison with the image processing system. For this purpose, the calibration plate has a known size.
  • the calibration plate can have different dimensions in two different, in particular mutually perpendicular, directions. Typically the calibration plate is rectangular.
  • the calibration plate can have a predefined surface quality, particularly with regard to color and/or pattern.
  • step B the calibration plate is arranged in the different test sections of the removal area.
  • the calibration plate is placed at different points in the sampling area.
  • the camera takes one picture at a time.
  • the transformation of the recorded images into the top view makes it possible to determine the size of the calibration plate by image evaluation in step C).
  • the calibration plate is measured by image analysis.
  • properties, in particular edges, of the calibration plate can be extracted from the transformed images.
  • distances between the edges in the transformed images can be determined. Since the transformation rule - as explained above - does not generally take the specific conditions on the sheet metal processing machine or in the removal area into account exactly, the measured values obtained through image analysis usually deviate from the known, actual size of the calibration plate.
  • step D an error measure is calculated from these deviations.
  • the error measure basically takes into account the deviations in all test sections.
  • the error measure can give greater weight to larger deviations than to smaller deviations.
  • the error measure can be the sum of the squares of the deviations of the measured values from the known size of the calibration plate.
  • Carrying out step D) quantifies the quality of the transformation rule specified in step A). This quantitative evaluation of the specified transformation rule serves as a starting point for optimizing the calibration.
  • the transformation rule specified in step A) is changed.
  • Steps C) and D) are repeated with the changed transformation rule.
  • the recorded images are thus transferred to the top view using different transformation regulations and the quality of the respective transformation is quantified using the error measure. Typically, a number of differently modified transformation regulations are used.
  • step F) the transformation rule is stored which minimizes the error level.
  • the transformation rule selected in step F) will differ from the transformation rule specified in step A).
  • the real conditions of the extraction area in particular with regard to deviations from a target configuration, can be taken into account in the transformation rule without these deviations having to be determined in detail.
  • the image quality can be automatically compensated in different sections of the sampling area.
  • the selected transformation rule can be stored in the image processing system, in particular in its control device.
  • the transformation rule can be changed in accordance with a rotation of the removal area, in particular about at least one axis running horizontally through the removal area. In this way, a tilting of the removal area can be compensated for. By using multiple rotation axes, multi-dimensional tilting can be taken into account. Tilting around axes that run horizontally (ie typically in the nominal plane of the sampling area) are particularly problematic for the imaging quality and must therefore be compensated for as precisely as possible in the transformation rule.
  • the transformation rule can be changed according to a translation of the camera relative to the sampling area. In this way, a changed distance as well as a changed relative position of the camera and the sampling area can be taken into account. Such positional deviations can occur when industrial trucks collide with the removal area.
  • step E a scaling factor of the transformation rule can be changed. In this way, an enlargement or reduction can be obtained in the transformed image.
  • the transformation rule for shifting the removal area in the detection area of the camera can be changed.
  • this can be done by an assumed rotation about an axis by the camera, in particular a vertical axis (typically perpendicular to the sampling area). Inaccurate adjustment of the camera's viewing direction can be compensated for in this way.
  • the transformation rule is particularly preferably described with a transformation matrix. In this way, the transformation rule can be saved with little memory requirement. In addition, the transformation rule can be applied to the recorded images with little computational effort.
  • the transformation matrix can also be referred to as a homography matrix.
  • step E) elements of the transformation matrix can be changed step by step. This enables modified transformation regulations to be created efficiently. Individual elements of the transformation matrix can be changed one after the other or together, preferably within predefined limits. Typically, the elements of the transformation matrix are gradually increased and gradually decreased starting from the initial value.
  • the transformation matrix is changed by mathematically applying a rotation of the removal area about a first axis to the transformation matrix. Changing the transformation matrix can be done easily by multiplying it with a rotation matrix.
  • An angle of rotation about the first axis used here can be increased step by step for a (mathematically) positive and for a (mathematically) negative rotation.
  • the first axis can run through a center point of the removal area.
  • the first axis preferably extends in a nominal plane of the removal area. In this way, a tilting of the removal area can be compensated for.
  • the transformation matrix is changed by mathematically applying a rotation of the removal area about a second axis to the transformation matrix, in particular where the second axis runs orthogonally to the first axis.
  • the second axis can run through a center point of the removal area.
  • the second axis preferably extends in a nominal plane of the removal area.
  • the error dimension is first minimized for the rotation about the first axis, so that a partially optimized transformation rule is obtained.
  • the rotation about the second axis is then applied to the transformation matrix of the partially optimized transformation rule, so that the optimized transformation rule to be stored in step F) is obtained by minimizing the error measure again.
  • the transformation rule to be stored in step F) can be determined by balancing calculation, in particular using the least squares method. In this way, the optimized transformation rule be labeled in an efficient manner. When using the least squares method, larger deviations in individual test sections are more noticeable. This helps ensure that successful workpiece recognition is possible anywhere in the removal area.
  • Steps A) to F) can be repeated, with the transformation rule stored in step F) of the previous process cycle being used as a default in the repeated step A).
  • a (re)calibration can be carried out in an efficient and effective manner. Further wear or further changes in position of the removal area can be compensated for. But even after parts of the removal area have been replaced (whereby it returns to its nominal state), the functionality of the image processing system can be ensured in this way.
  • the image processing system preferably displays the test sections. This makes it easier to arrange the calibration plate in the different test sections.
  • the image processing system can display the test sections in the removal area. For this purpose, for example, lines that mark the boundaries of the test sections can be projected into the sampling area. This simplifies the correct positioning of the calibration plate.
  • the image processing system may have a display device for displaying the image captured by the camera. On the display device, the image can be transformed into a top view of the removal area are displayed. The displayed transformation of the image is typically determined using the transformation rule from step A). Preferably, the image processing system displays the test sections on the display device. The test sections or their boundaries can be placed over the displayed image. By looking at the display device, it can be seen whether the calibration plate is correctly positioned.
  • the image processing system can indicate whether the measured values for the size of the calibration plate determined in step C) for the different test sections are within a predefined tolerance of the known size of the calibration plate, in particular when applying the transformation rule specified in step A) and when applying the in Step F) stored transformation rule. If the indication as to whether the tolerance is adhered to is initially made with the transformation rule from step A), it can be assessed whether this transformation rule delivers sufficiently good results. If this is not the case, the transformation rule can be optimized using the method described. The predefined tolerance should then be adhered to at all positions (at least as long as the removal area is not excessively worn or damaged). The display can confirm that the optimized transformation rule ensures compliance with the tolerance.
  • the invention is shown in the drawing and is based on
  • FIG. 1 shows a sheet metal processing machine with an image processing system, which captures a removal area for processed workpieces with a camera, in a schematic perspective view;
  • FIG. 3 shows a schematic flow diagram of a calibration method according to the invention for the image processing system
  • FIG. 4 shows a schematic top view of the removal area, with a calibration plate being arranged in a first test section;
  • Fig. 5 is a schematic representation of an image of the removal area transformed into a top view on the display device of the image processing system, indicating that the size of the calibration plate was determined with sufficient precision in three test sections based on a predetermined transformation rule and was determined with insufficient precision in two test sections ;
  • FIG. 6 is a schematic representation of an image of the removal area transformed into a top view on the display device of the image processing system, indicating that the size of the calibration plate was correctly determined in all five test sections using an optimized transformation rule.
  • Figure 1 shows a sheet metal processing machine 10, here a flatbed laser cutting machine.
  • the sheet metal processing machine 10 has a pallet changer 12, on which a removal area 14 for processed workpieces 16 is formed.
  • the workpieces 16 can in particular be removed (sorted) manually from the removal area 14 and fed for further processing or use.
  • the sheet metal processing machine 10 also has an image processing system 18.
  • the image processing system 18 includes at least one camera 20 and a display device 22.
  • the image processing system 18 or the sheet metal processing machine 10 may include a control device 23.
  • the control device 23 is connected to the camera 20 and the display device 22 in a manner not shown.
  • the camera 20 is aimed at the removal area 14, see the dashed lines emanating from the camera 20.
  • the camera 20 captures the removal area 14 from diagonally above.
  • objects of the same size appear at different locations in the removal area and are of different sizes and distorted in perspective.
  • the image of the removal area 14 recorded by the camera 20 can be displayed on the display device 22.
  • the image is transformed into a top view (bird's eye view) with a view of the removal area 14 from vertically above.
  • the transformation is carried out using a transformation rule stored in the control device 23.
  • the image processing system 18 serves to support the manual sorting of the processed workpieces 16.
  • the workpieces 16 are identified in the image recorded by the camera 20 after its transformation into the top view and instructions for handling the individual workpieces can be displayed on the display device 22.
  • Workpiece recognition requires that the image processing system 18 is correctly calibrated.
  • a calibration plate 24 is used to calibrate the image processing system 18.
  • the calibration plate 24 has a predefined shape and size.
  • the calibration plate 24 is designed as a cuboid with known dimensions.
  • the calibration plate 24 can have a color and possibly a pattern on its surface (not shown in more detail in Figure 1).
  • the pallet changer 12 has several webs 25 which run approximately parallel to one another and which form the removal area 16. Workpieces 16 or calibration plates 24 can be placed on the top of the webs 25 of the removal area 14.
  • the webs 25 are generally not aligned so that their top sides run exactly in one plane. Rather, some of the webs 25 will typically deviate upwards and downwards from the target position. Likewise, the webs 25 can be arranged partially tilted.
  • a support surface of the removal area 16 therefore has irregular positional deviations from a nominal plane in which it should extend according to the design specification. This is exaggerated in Figure 2. The nominal plane is typically oriented horizontally.
  • a transformation rule stored in the control device 23 is used to transform the image recorded by the camera 20 into the top view.
  • the transformation rule can be described by a transformation matrix. Since the previously described deviations or changes in the removal area 14 were generally not known in detail when determining this transformation rule, the image processing system 18 is calibrated by optimizing the transformation rule.
  • the stored transformation rule is specified as a starting point in a step 102, see FIG. 3.
  • the calibration plate 24 is first arranged in a first test section 28 in a step 104, see Figure 4. Boundaries 26 of the first test section 28 and further test sections 28 can be projected into the removal area 14.
  • the camera 20 is used to record an image of the removal area 14 with the calibration plate 24 located in the first test section 28, see step 106. Steps 104 and 106 are repeated for the further test sections 28. In principle, only one image could be recorded if several calibration plates 24 of the same size are arranged in the different test sections 28 at the same time.
  • Each of the recorded images is transformed into the top view in a step 108 using the specified transformation rule.
  • the calibration plate 24 is measured in the transformed images by image analysis, see step 110. For this purpose, in particular edges of the calibration plate 24 can be determined in the transformed images.
  • an error measure is determined, which summarizes the deviations of the actual size of the calibration plate 24 from the measurement results (steps 110) for all test sections 28 in a key figure. This error measure describes the quality of the transformation rule with regard to the current state of the removal area 14.
  • the individual test sections 28 can be displayed on the display device 22 for the individual test sections 28 whether the deviations between the actual size and the size of the calibration plate 24 determined by measurement in the transformed images adhere to a predetermined tolerance or not, see Figure 5.
  • the permissible tolerance in the two left and central test sections 28 are undershot, while the permissible tolerance in the two right test sections 28 is exceeded.
  • a step 114 the Transformation rule optimized, that is, the image processing system 18 is calibrated.
  • the elements of the transformation matrix can be changed step by step.
  • the optimization preferably takes place in a multi-stage procedure, with a partial optimum being determined for a first type of change in the transformation rule, which is further optimized for a further type of change. This can be done in two or more optimization stages.
  • a rotation about a first axis 30 is applied to the predetermined transformation rule, so that a changed transformation rule is obtained. This can be done by multiplying the given transformation matrix with a rotation matrix.
  • the first axis 30 here runs horizontally through the removal area 14, in particular through its center, see Figure 1.
  • Steps 108 to 112 are repeated with the changed transformation rule.
  • the recorded images are therefore transformed into the top view using the changed transformation rule (step 108), the calibration plate 24 is measured in each case (step 110) and a comprehensive error measure is determined for all test sections (step 112).
  • This procedure is repeated for rotation angles of different sizes (in mathematically positive and negative directions) about the first axis 30.
  • a partially optimized transformation rule is selected from the transformation rules changed by different rotation angles about the first axis 30.
  • Transformation rule is the one for which the error level becomes minimal. It is possible to interpolate between the applied rotation angle steps using a compensation calculation.
  • a rotation about a second axis 32 is applied to the partially optimized transformation rule, so that a further changed Transformation rule is obtained. This can be done by multiplying the partially optimized transformation matrix with a second rotation matrix.
  • the second axis 32 here runs orthogonally to the first axis 30 and horizontally through the removal area 14, in particular through its center, see Figure 1.
  • steps 108 to 112 are repeated again.
  • the recorded images are transformed into the top view (step 108)
  • the calibration plate 24 is measured in each case (step 110) and a comprehensive error measure is determined for all test sections (step 112). This procedure is repeated for different angles of rotation (in mathematically positive and negative directions) about the second axis 32.
  • a further partially optimized transformation rule can be selected again in a further step 118 from the transformation rules that have been further changed by rotations of different sizes about the second axis 32.
  • the further partially optimized transformation rule is the one for which the error level is minimal. It is possible to interpolate between the applied rotation angle steps using a compensation calculation.
  • the further partially optimized transformation rule can be changed again in a step 122 in order to go through one or more further optimization stages by repeating steps 108 to 112.
  • the change in step 118 of the further or one of the further optimization stages can correspond to a rotation about a third axis, an application of a scaling factor and/or a translation of the camera 20 relative to the sampling area 14. It is understood that these further optimization stage(s) could also be carried out before or between the optimization for rotations about the first and second axes 30, 32.
  • the successive optimization for rotations about the first and second axes 30, 32 results in a sufficiently good one
  • an optimized transformation rule is selected from the transformation rules further changed by rotation about the second axis 32 (or possibly in further optimization stages).
  • the optimized transformation rule is the one for which the error level is minimal. It is possible to interpolate between the applied rotation angle steps using a compensation calculation.
  • the optimized transformation rule is stored in a step 126.
  • the optimized transformation matrix of the optimized transformation rule can be stored in the control device 23 of the image processing system 18.
  • the invention relates to a method for calibrating a preset image processing system.
  • a camera is used to take perspective images of an approximately flat surface. To analyze the captured images, they are transformed into a top view of the surface. The transformation takes place according to a given
  • Transformation rule In order to compensate for deviations in terms of shape, orientation and position of the surface, the transformation rule is optimized. For this purpose, a calibration plate of a known size is arranged in different test sections of the surface. The recorded images are transformed into the top view using the specified transformation rule and changed transformation rules. The calibration plate is measured in the transformed images. By comparing with the known dimensions of the calibration plate, the transformation rule can be determined for which the deviations between the measured values and the real dimensions of the calibration plate are minimized overall for the various test sections.
  • Test sections 28 first axis 30 second axis 32

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Mechanical Engineering (AREA)
  • Optics & Photonics (AREA)
  • General Physics & Mathematics (AREA)
  • Plasma & Fusion (AREA)
  • Human Computer Interaction (AREA)
  • Automation & Control Theory (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Manufacturing & Machinery (AREA)
  • Robotics (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

L'invention concerne un procédé pou étalonner un système de traitement d'images (18) d'une machine d'usinage de tôles (10), au moins une caméra (20) du système de traitement d'images (18) détectant une zone de prélèvement (14) pour les pièces (16) usinées. Le procédé comprend les étapes consistant à : A) prédéfinir une règle de transformation qui transforme une image de la zone de prélèvement (14) prise par la caméra (20) en une vue de dessus de la zone de prélèvement (14) ; B) placer une plaque d'étalonnage (24) de taille connue dans différentes parties de contrôle de la zone de prélèvement (14) et prendre respectivement une image au moyen de la caméra (20) pendant que la plaque d'étalonnage (24) se trouve dans la partie de contrôle respective ; C) transformer les images prises au cours de l'étape B) au moyen de la règle de transformation et mesurer la plaque d'étalonnage (24) dans les images transformées ; D) calculer une mesure d'erreur pour l'écart entre la taille connue de la plaque d'étalonnage (24) et les valeurs de mesure déterminées lors de l'étape C) pour la taille de la plaque d'étalonnage (24) ; E) modifier la règle de transformation et répéter les étapes C) et D) au moyen de la règle de transformation modifiée ; F) enregistrer la règle de transformation pour laquelle la mesure d'erreur est minimale.
PCT/EP2023/058283 2022-04-27 2023-03-30 Procédé pour étalonner un système de traitement d'image d'une machine d'usinage de tôle WO2023208507A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102022110109.6A DE102022110109A1 (de) 2022-04-27 2022-04-27 Verfahren zum Kalibrieren eines Bildverarbeitungssystems einer Blechbearbeitungsmaschine
DE102022110109.6 2022-04-27

Publications (1)

Publication Number Publication Date
WO2023208507A1 true WO2023208507A1 (fr) 2023-11-02

Family

ID=85980718

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2023/058283 WO2023208507A1 (fr) 2022-04-27 2023-03-30 Procédé pour étalonner un système de traitement d'image d'une machine d'usinage de tôle

Country Status (2)

Country Link
DE (1) DE102022110109A1 (fr)
WO (1) WO2023208507A1 (fr)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016005159A2 (fr) 2014-07-11 2016-01-14 Trumpf Werkzeugmaschinen Gmbh + Co. Kg Procédé, machine d'usinage et produit de programme d'ordinateur pour placer à partir d'une image des processus d'usinage de pièces
WO2018073419A1 (fr) 2016-10-21 2018-04-26 Trumpf Werkzeugmaschinen Gmbh + Co. Kg Procédé d'aide au triage et machine-outil à banc plat
WO2018073418A1 (fr) 2016-10-21 2018-04-26 Trumpf Werkzeugmaschinen Gmbh + Co. Kg Unité de points de collecte de pièces et procédé permettant de faciliter l'usinage de pièces

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2016005159A2 (fr) 2014-07-11 2016-01-14 Trumpf Werkzeugmaschinen Gmbh + Co. Kg Procédé, machine d'usinage et produit de programme d'ordinateur pour placer à partir d'une image des processus d'usinage de pièces
WO2018073419A1 (fr) 2016-10-21 2018-04-26 Trumpf Werkzeugmaschinen Gmbh + Co. Kg Procédé d'aide au triage et machine-outil à banc plat
WO2018073418A1 (fr) 2016-10-21 2018-04-26 Trumpf Werkzeugmaschinen Gmbh + Co. Kg Unité de points de collecte de pièces et procédé permettant de faciliter l'usinage de pièces

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
"Wiley Encyclopedia of Computer Science and Engineering", 7 January 2008, JOHN WILEY & SONS, INC., Hoboken, NJ, USA, ISBN: 978-0-470-05011-8, article KANNALA JUHO ET AL: "Geometric Camera Calibration", XP093052687, DOI: 10.1002/9780470050118.ecse589 *

Also Published As

Publication number Publication date
DE102022110109A1 (de) 2023-11-02

Similar Documents

Publication Publication Date Title
EP3108311B1 (fr) Procédé, machine d'usinage et produit de programme d'ordinateur pour placer à partir d'une image des opérations d'usinage de pièces
EP3898060B1 (fr) Procédé et machine à lit plat laser pour découper des pièces
EP3030359B1 (fr) Presse à plier
DE102015200197A1 (de) Markierungsdetektionsverfahren
DE112007001360T5 (de) Stent-Inspektionssystem
EP3417237B1 (fr) Plaque de référence et procédé pour calibrer et/ou vérifier un système de détection par déflectométrie
EP3362848B1 (fr) Procédé et dispositif pour vérifier la distribution de puissance et le centrage
DE102007008699A1 (de) Verfahren und Vorrichtung zur Qualitätskontrolle bei Werkzeugmaschinen
DE102018007287B4 (de) Roboter-Controller zum Durchführen einer Kalibrierung, Messsystem und Kalibrierverfahren
DE102015104582A1 (de) Verfahren zum Kalibrieren eines Roboters an einem Arbeitsbereich und System zum Durchführen des Verfahrens
WO2022189236A1 (fr) Système de réparation additive
EP1157313A1 (fr) Procede permettant de determiner l'ecart de dimensions geometriques et/ou de la position d'un objet par rapport a des valeurs theoriques predeterminables des dimensions geometriques et/ou de la position de l'objet concerne
EP3725499A1 (fr) Étalonnage d'une camera permettant de surveiller un procédé de fabrication additive
DE102020120887A1 (de) Verfahren zum erfassen einer einhängeposition eines auflagestegs und flachbettwerkzeugmaschine
EP1946896A2 (fr) Procédé et dispositif destinés à l'ajustement d'au moins un axe
DE10147880B4 (de) Verfahren zur Messung einer charakteristischen Dimension wenigstens einer Struktur auf einem scheibenförmigen Objekt in einem Meßgerät
WO2023208507A1 (fr) Procédé pour étalonner un système de traitement d'image d'une machine d'usinage de tôle
DE102007058293A1 (de) Kalibriervorrichtung und Verfahren zum Abgleichen eines Roboterkoordinatensystems
DE102020105185A1 (de) Datenkorrelation zwischen verschiedenen Maschinen einer Fertigungslinie für elektronische Bauelemente
DE102015104587A1 (de) Verfahren zum Kalibrieren eines Roboters an einem Arbeitsbereich und System zum Durchführen des Verfahrens
WO2017181208A1 (fr) Barre de pliage pour plieuse pivotante
WO2023208508A1 (fr) Procédé de vérification de l'étalonnage d'un système de traitement d'image d'une machine de travail de tôle
DE102011084353B4 (de) Verfahren und Computerprogramm zum Einrichten eines Greifroboters, sowie Greifroboter
DE102017219207A1 (de) Verfahren und Vorrichtung zur Oberflächenbearbeitung und Verfahren zur Herstellung eines geformten Bauteils
EP3783301B1 (fr) Système de mesure d'objet pour une machine d'emballage permettant de déterminer les dimensions d'une surface de base et, en option, d'une hauteur d'une barquette d'emballage à enrouler

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23716273

Country of ref document: EP

Kind code of ref document: A1