CN109822216B - Welding bead track and posture real-time tracking detection method, electronic equipment and medium - Google Patents

Welding bead track and posture real-time tracking detection method, electronic equipment and medium Download PDF

Info

Publication number
CN109822216B
CN109822216B CN201910037379.6A CN201910037379A CN109822216B CN 109822216 B CN109822216 B CN 109822216B CN 201910037379 A CN201910037379 A CN 201910037379A CN 109822216 B CN109822216 B CN 109822216B
Authority
CN
China
Prior art keywords
groove
area
imaging
original image
workpiece
Prior art date
Application number
CN201910037379.6A
Other languages
Chinese (zh)
Other versions
CN109822216A (en
Inventor
都东
薛博策
彭国栋
王力
王国庆
高彦军
田志杰
Original Assignee
清华大学
首都航天机械有限公司
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 清华大学, 首都航天机械有限公司 filed Critical 清华大学
Priority to CN201910037379.6A priority Critical patent/CN109822216B/en
Publication of CN109822216A publication Critical patent/CN109822216A/en
Application granted granted Critical
Publication of CN109822216B publication Critical patent/CN109822216B/en

Links

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B23MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23KSOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K26/00Working by laser beam, e.g. welding, cutting or boring
    • B23K26/20Bonding
    • B23K26/21Bonding by welding
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B23MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23KSOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K26/00Working by laser beam, e.g. welding, cutting or boring
    • B23K26/70Auxiliary operations or equipment

Abstract

The embodiment of the invention provides a welding bead track and posture real-time tracking detection method, electronic equipment and a medium, and belongs to the field of welding automation. Synchronously irradiating the area near the fine gap groove on the surface of a workpiece to be welded by using a uniform diffusion light source and a multi-line laser light source, and obtaining an original image with proper gray scale by adjusting the exposure time of an imaging element; determining two threshold values by calculating and analyzing a gray frequency histogram of the original image; respectively binarizing the original image by using two threshold values, and extracting a groove area and a laser projection area; and calculating and obtaining the three-dimensional position of the groove center and the normal vector of the surface of the workpiece to be welded based on the groove area and the laser projection area. The embodiment of the invention synchronously irradiates the surface of the workpiece by adopting the double light sources and obtains the image with unsaturated gray scale, can adapt to special occasions such as high-speed welding, remote detection and the like, has high image processing speed and can meet the requirement of real-time tracking of welding.

Description

Welding bead track and posture real-time tracking detection method, electronic equipment and medium

Technical Field

The embodiment of the invention relates to the field of welding automation, in particular to a welding bead track and posture real-time tracking detection method, electronic equipment and a medium.

Background

In the welding field, the automatic detection of the welding seam has important significance for automatic teaching before welding and automatic tracking in welding, and the visual detection becomes an important mode of automatic detection of the welding seam because the visual detection can provide rich information about the welding seam.

At present, structured light is projected on a groove by the method, the position information of the groove is obtained through the deformation of the structured light, however, when the gap of the groove is extremely small, the deformation of the structured light in an image is difficult to distinguish, and the method can only detect the three-dimensional coordinate of the groove and is difficult to detect the posture of the surface of a workpiece, so that a welding gun cannot be guided to adjust the posture in the welding process.

Chinese patent document (publication No. CN103954216A) discloses a device and a method for detecting a narrow bevel of a strong specular reflection workpiece based on a spherical light source, wherein a laser array and the spherical light source are alternately lightened and projected on the surface of the workpiece by a sensor, images of different light sources when lightened are synchronously shot by an imaging element, the position of the surface of the workpiece near the projection point of the laser array is obtained through the images of the lightened laser array, two-dimensional information of the bevel is obtained through the images with uniform brightness when the spherical light source is lightened, and the two images are combined to determine the three-dimensional position of the bevel. However, this method has two disadvantages: firstly, there is a time difference between the image lighted by the laser array acquired by the imaging element and the image lighted by the spherical light source, and when the pose of the surface of a workpiece to be welded is violently changed in high-speed welding or welding, the detection error caused by the time difference is obvious; secondly, the method requires that the image gray scale when the spherical surface light source is lightened is close to saturation so as to rapidly and accurately extract the central position of the groove, in the application of real-time tracking of the groove, the detection device is often fixedly connected with a welding torch, in some occasions needing remote welding, such as laser welding in some occasions, the welding torch is difficult to approach a workpiece, in order to enable the image gray scale to be close to saturation, a spherical light source with higher power is needed, and the larger power and the larger volume of the light source are generally larger, so that the integral volume of the detection device is increased.

Disclosure of Invention

The embodiment of the invention provides a real-time tracking detection method for a welding bead track and a welding bead attitude, electronic equipment and a medium, and aims to solve the problem that the real-time detection of a fine gap groove in the prior art is difficult to adapt to occasions such as high-speed welding, remote detection and the like.

In a first aspect, an embodiment of the present invention provides a method for tracking and detecting a weld bead trajectory and a weld bead attitude in real time, including:

synchronously irradiating the area near the fine gap groove on the surface of the workpiece to be welded by using a uniform diffusion light source and a multi-line laser light source, and obtaining an original image with proper gray scale by adjusting the exposure time of an imaging element;

calculating and analyzing a gray frequency histogram of the original image, and determining a first threshold value for extracting a groove region and a second threshold value for extracting a laser projection region;

respectively carrying out binarization on the original image by using the first threshold value and the second threshold value, and carrying out morphological operation and communication domain reservation on the original image subjected to binarization processing to obtain a groove area and a laser projection area;

and calculating and obtaining the three-dimensional position of the groove center and the normal vector of the surface of the workpiece to be welded based on the groove area and the laser projection area.

In a second aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the welding bead trajectory and posture real-time tracking detection method provided in the first aspect when executing the program.

In a third aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the welding bead trajectory and posture real-time tracking detection method provided in the first aspect.

The welding bead track and posture real-time tracking detection method, the electronic equipment and the medium provided by the embodiment of the invention can be suitable for occasions such as high-speed welding, remote detection and the like of the fine gap groove, the application scene of the fine gap groove detection method is widened, the image processing method is high in speed, and the requirement of welding real-time tracking can be met.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.

Fig. 1 is a schematic structural diagram of a detection apparatus adopting a detection method according to an embodiment of the present invention;

FIG. 2 is a schematic view of a multi-line laser light source projected on a surface of a workpiece to be welded;

fig. 3 is a schematic flow chart of a real-time tracking and detecting method for a weld path and a weld attitude according to an embodiment of the present invention;

FIG. 4 is a schematic illustration of an original image acquired by an imaging element;

fig. 5 is a grayscale frequency histogram of an original image captured by an imaging element.

Fig. 6 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention;

description of reference numerals: 1-a control unit; 2-a welding gun; 3-a sensor housing; 4-an imaging element; 5-a multi-line laser light source; 6-a filter element; 7-a uniform diffuse light source; 8-a workpiece to be welded; and (81) beveling.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Fig. 1 is a schematic structural principle diagram of a detection apparatus for real-time tracking and detecting a weld path and a weld attitude according to an embodiment of the present invention, including: a control unit 1, a sensor housing 3, and an imaging element 4, a filter element 6, a multiline laser light source 5, and a uniform diffusion light source 7 fixed within the sensor housing 3. Wherein, the control unit 1 is connected with the imaging element 4 through a control line; the multi-line laser light source 5 can emit at least two laser lines to be projected on the surface of the workpiece 8 to be welded, as shown in fig. 2, which is a schematic view of the multi-line laser light source 5 projected on the surface of the workpiece to be welded; the uniform diffusion light source 7 can emit diffused light with uniform brightness to be projected on the surface of the workpiece 8 to be welded; the reflected light from the surface of the workpiece 8 to be welded enters the imaging element 4 to be imaged after passing through the filter element 6.

In the welding process, a welding gun needs to be aligned with a welding bead, and meanwhile, the welding gun needs to keep a certain attitude relationship with the surface of a workpiece to be welded (for example, the axis of the welding gun needs to be vertical to the surface of the workpiece) so as to ensure the welding quality.

Fig. 3 is a schematic flow chart of a real-time tracking and detecting method for a weld path and a weld attitude according to an embodiment of the present invention, including:

step 100, synchronously irradiating the area near the fine gap groove on the surface of a workpiece to be welded by using a uniform diffusion light source and a multi-line laser light source, and obtaining an original image with proper gray scale by adjusting the exposure time of an imaging element;

the fine gap groove on the surface of the workpiece to be welded is a groove with extremely small gap, and generally does not exceed 0.1 mm.

The embodiment of the invention synchronously irradiates the area near the fine gap groove on the surface of the workpiece to be welded by using the uniform diffusion light source and the multi-line laser light source, thereby calculating the three-dimensional position of the groove and the normal vector of the surface of the workpiece according to the same frame of image, avoiding the detection error caused by time difference when the two frames of images are used for calculation in the prior art, avoiding the gray scale of the images from approaching saturation and reducing the requirement on the illumination brightness of the uniform diffusion light source.

And adjusting the exposure time of the imaging element to obtain an original image with proper gray scale, wherein proper gray scale means that the gray scale of the image obtained by the imaging element meets the preset gray scale range.

Specifically, the multi-line laser light source 5 and the uniform diffusion light source 7 are simultaneously turned on to irradiate an area near a groove 81 on the surface of the workpiece 8 to be welded, and the control unit 1 controls the imaging element 4 to capture an original image I of the area, as shown in fig. 4, wherein a represents the groove, b represents two laser lines, and small squares and ellipses in the figure show the trace on the surface of the workpiece. The control unit 1 then calculates the average gray level r of the original image IaveIf r isave∈[rmin,rmax]The next step is entered, otherwise the control unit 1 adjusts the exposure time of the imaging element 4 to acquire the original image I again until rave∈[rmin,rmax]Wherein [ r ]min,rmax]The gray scale range is preset, and the gray scale range is used for enabling the gray scale of the surface of the workpiece 8 to be welded in the original image I to be moderate, so that the groove area and the laser projection area can be conveniently extracted in the subsequent steps. For example, when the average gray level of the original image I is 128, the gray level of the original image I can be considered to be moderate.

In order to realize real-time tracking detection of the welding bead track and the welding bead posture, before step 100, a three-dimensional rectangular coordinate system { C } of the imaging element is established, wherein the origin of { C } is the optical center of the imaging element 4, and the z-axis direction of { C } is the same as the optical axis direction of the imaging element 4; establishing a pixel two-dimensional coordinate system { P } on the image acquired by the imaging element 4;

calibrating an imaging element 4 to obtain a conversion relation of corresponding points between the three-dimensional rectangular coordinate system { C } of the imaging element and the two-dimensional coordinate system { P } of the pixel;

and calibrating the multi-line laser light source 5 to obtain an equation of each light plane of the multi-line laser light source in the three-dimensional rectangular coordinate system { C } of the imaging element.

Step 200, calculating and analyzing a gray frequency histogram of the original image, and determining a first threshold value for extracting a groove region and a second threshold value for extracting a laser projection region;

after obtaining the original image I with the average gray level meeting the requirement, calculating a gray level frequency histogram p (r) of the original image I.

Determining a first threshold value for extracting a groove region and a second threshold value for extracting a laser projection region by analyzing a gray frequency histogram of the original image, specifically comprising:

calculating a first threshold t for extracting a groove region according to the following formulalow

tlow=max r,

Wherein r is the gray level value in the histogram of gray level frequency, p (i) is the frequency of occurrence of the gray level value i, a is a predetermined value, 0< a < 1.

Since the gray level of the laser line in the original image I is much higher than that in other areas, there is a peak in the high gray level area in the gray level frequency histogram, and as shown in fig. 5, the laser projection area can be extracted by using the gray level value corresponding to the valley in front of the peak as a threshold.

Specifically, the grayscale frequency histogram p (r) is smoothed to remove random fluctuation therein, and a smoothed grayscale frequency histogram p (r) is obtaineds(r) after finding ps(r) one minimum value point with the maximum gray level, and taking the gray level corresponding to the minimum value point as a second threshold value t for extracting the laser projection areahigh

It should be noted that, since the bevel 81 may be narrow, there may be no valley in the low gray level region of the gray frequency histogram, and therefore the threshold t for extracting the bevel region cannot be determined by a similar methodlow

The gray frequency histogram may be smoothed by a gaussian filtering method or an average filtering method.

300, respectively carrying out binarization on the original image by using the first threshold value and the second threshold value, and carrying out morphological operation and communication domain reservation on the binarized original image to obtain a groove area and a laser projection area;

specifically, the original image is binarized by using the first threshold value and the second threshold value respectively to obtain two binarized images, and the morphology and the connected domain of the binarized image obtained by using the first threshold value to perform binarization operation are reserved to obtain a groove area; and retaining morphology and a connected domain of the binary image obtained by performing the binary operation by using the second threshold value to obtain a laser projection area.

Step 300 includes the steps of:

using said first threshold value tlowCarrying out binarization processing on the original image I, and keeping the gray level in the original image I to be less than or equal to the first threshold value tlowTo obtain a first binarized image Ilow

The first binarized image I due to noise or the likelowThere may be small gaps and holes in the central notch area, so that the first binarized image I is processedlowA morphological closing operation is performed to close the gaps and holes therein.

Since there may be some low reflection areas on the surface of the workpiece 8 to be welded, as shown in fig. 4, the gray level in the original image I is low, and the low reflection areas are retained after binarization processing, and these low reflection areas are generally small in area or not as slender as the bevel 81, and therefore connected domain extraction is performed, and connected domains with large enough area and slender shape are retained.

Namely, the reserved area and the roundness rate meet the connected domain of a first preset condition, wherein the first preset condition is as follows:

wherein A represents the area of the connected domain, Amin1A first area threshold, R, representing a predetermined connected componentcRepresents the circularity of connected component, Rcmax1Representing a preset first roundness rate threshold value of the connected domain;

wherein, the roundness rate R of the connected domaincIs defined as:

where P represents the perimeter of the connected domain.

The first binarized image IlowAnd reserving the connected domain as a groove region, and acquiring the coordinate of the groove center in the pixel two-dimensional coordinate system { P } based on the groove region.

The specific steps of obtaining the coordinate of the groove center in the pixel two-dimensional coordinate system may be: in the first binarized image IlowAnd taking a middle row, finding two intersection points of the row and the reserved connected domain, taking the midpoint of the two intersection points as a groove center, and acquiring the coordinates of the intersection point, namely acquiring the coordinates of the groove center in the pixel two-dimensional coordinate system { P }. If the connected domain is discontinuous, performing linear fitting on the connected domain, and taking a first binarized image IlowAnd in the middle column, the intersection point of the column and the fitted connected domain is taken as a groove center, and the coordinate of the groove center in the pixel two-dimensional coordinate system { P } is further acquired.

Using said second threshold value thighCarrying out binarization processing on the original image I, and keeping the gray level in the original image I to be more than or equal to the second threshold value thighTo obtain a second binary image Ihigh

Due to laser speckle and other reasons, a large number of tiny low-gray-scale areas exist in a laser projection area in an original image I, and tiny gaps and holes are formed after binarization, so that the I is subjected to the binary processinghighAnd performing a morphological closing operation to eliminate micro gaps and holes in the laser projection area.

Because the surface of the workpiece 8 to be welded possibly has a partial high-reflection area, the gray level in the original image I is higher, and the image is remained in I after binarization treatmenthighIn addition, the high reflection regions are generally smaller in area or not as slender as the laser projection region, therefore, connected domain extraction is carried out, connected domains with large enough area and slender enough shape are reserved,

namely, the reserved area and the roundness rate meet the connected domain of a second preset condition, wherein the second preset condition is as follows:

wherein A represents the area of the connected domain, Amin2A second area threshold, R, representing a predetermined connected domaincRepresents the circularity of connected component, Rcmax2And a second roundness rate threshold value representing a preset connected domain. RcThe definition is as described above.

The second binary image I is processedhighAnd reserving the connected domain as a laser projection region, wherein the laser projection region refers to the surface region of the workpiece where the multi-line laser projection is positioned.

And acquiring coordinates of a series of points on the laser projection line in the pixel two-dimensional coordinate system { P } based on the laser projection area.

And step 400, calculating and obtaining a three-dimensional position of the groove center and a normal vector of the surface of the workpiece to be welded based on the groove area and the laser projection area.

Specifically, according to the coordinates of the series of points on the laser projection line in the pixel two-dimensional coordinate system { P } obtained in step 300, the coordinates of the series of points on the laser projection line in the imaging element three-dimensional rectangular coordinate system { C } are calculated by combining the conversion relationship of the corresponding points between the imaging element three-dimensional rectangular coordinate system { C } and the pixel two-dimensional coordinate system { P } obtained by the previous calibration and the equation of each light plane of the multi-line laser light source in the imaging element three-dimensional rectangular coordinate system { C };

and (3) regarding the surface area of the to-be-welded workpiece 8 where the plurality of laser projection lines are located as a plane W, and fitting an equation of the workpiece plane W where the plurality of laser projection lines are located in the three-dimensional rectangular coordinate system { C } of the imaging element based on coordinates of a series of points on the laser projection lines in the three-dimensional rectangular coordinate system { C } of the imaging element.

The fitting method may employ a least squares method.

And calculating to obtain a normal vector of the workpiece plane W according to the equation.

And calculating to obtain the coordinate of the bevel center in the three-dimensional rectangular coordinate system { C } according to the coordinate of the bevel center in the pixel two-dimensional coordinate system { P }, the equation of the workpiece plane W where the multi-line laser projection is located in the imaging element three-dimensional rectangular coordinate system { C }, and the conversion relation of the corresponding point between the imaging element three-dimensional rectangular coordinate system { C } and the pixel two-dimensional coordinate system { P }.

According to the three-dimensional position of the groove center and the normal vector of the surface of the workpiece, a reference basis can be provided for the position and posture adjustment of a welding gun and the parameter adjustment of a welding process in the welding process.

The welding bead track and posture real-time tracking detection method provided by the embodiment of the invention can detect the three-dimensional coordinate of the groove and the pose of the surface of the workpiece, is suitable for occasions such as high-speed welding, remote detection and the like of the fine gap groove, widens the application scene of the fine gap groove detection method, has high image processing speed and can meet the requirement of welding real-time tracking.

Fig. 6 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 6, the electronic device may include: a processor (processor)610, a communication Interface (Communications Interface)620, a memory (memory)630 and a communication bus 640, wherein the processor 610, the communication Interface 620 and the memory 630 communicate with each other via the communication bus 640. Processor 610 may invoke a computer program stored on memory 630 and executable on processor 610 to perform the weld bead trajectory and pose real-time tracking detection methods provided by the above-described method embodiments, including, for example: synchronously irradiating the area near the fine gap groove on the surface of the workpiece to be welded by using a uniform diffusion light source and a multi-line laser light source, and obtaining an original image with proper gray scale by adjusting the exposure time of an imaging element; calculating and analyzing a gray frequency histogram of the original image, and determining a first threshold value for extracting a groove region and a second threshold value for extracting a laser projection region; respectively carrying out binarization on the original image by using the first threshold value and the second threshold value, and carrying out morphological operation and communication domain reservation on the original image subjected to binarization processing to obtain a groove area and a laser projection area; and calculating and obtaining the three-dimensional position of the groove center and the normal vector of the surface of the workpiece to be welded based on the groove area and the laser projection area.

In addition, the logic instructions in the memory 630 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

An embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for tracking and detecting the trajectory and the posture of the weld bead in real time, which includes: synchronously irradiating the area near the fine gap groove on the surface of the workpiece to be welded by using a uniform diffusion light source and a multi-line laser light source, and obtaining an original image with proper gray scale by adjusting the exposure time of an imaging element; calculating and analyzing a gray frequency histogram of the original image, and determining a first threshold value for extracting a groove region and a second threshold value for extracting a laser projection region; respectively carrying out binarization on the original image by using the first threshold value and the second threshold value, and carrying out morphological operation and communication domain reservation on the original image subjected to binarization processing to obtain a groove area and a laser projection area; and calculating and obtaining the three-dimensional position of the groove center and the normal vector of the surface of the workpiece to be welded based on the groove area and the laser projection area.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. A welding bead track and posture real-time tracking detection method is characterized by comprising the following steps:
synchronously irradiating the area near the fine gap groove on the surface of the workpiece to be welded by using a uniform diffusion light source and a multi-line laser light source, and obtaining an original image with proper gray scale by adjusting the exposure time of an imaging element;
calculating and analyzing a gray frequency histogram of the original image, and determining a first threshold value for extracting a groove region and a second threshold value for extracting a laser projection region;
respectively carrying out binarization on the original image by using the first threshold value and the second threshold value, and carrying out morphological operation and communication domain reservation on the original image subjected to binarization processing to obtain a groove area and a laser projection area;
calculating and obtaining the three-dimensional position of the groove center and the normal vector of the surface of the workpiece to be welded based on the groove area and the laser projection area;
wherein, the fine gap groove is a groove with a gap not exceeding 0.1 mm.
2. The method of claim 1, wherein the step of synchronously irradiating the area near the fine groove of the surface of the workpiece to be welded by using the uniform diffusion light source and the multi-line laser light source and obtaining the original image with proper gray scale by adjusting the exposure time of the imaging element is preceded by the steps of:
establishing a three-dimensional rectangular coordinate system of an imaging element, and establishing a two-dimensional pixel coordinate system on an image acquired by the imaging element;
calibrating an imaging element to obtain a conversion relation of corresponding points between the three-dimensional rectangular coordinate system of the imaging element and the two-dimensional coordinate system of the pixel;
and calibrating the multi-line laser light source to obtain an equation of each light plane of the multi-line laser light source in the three-dimensional rectangular coordinate system of the imaging element.
3. The method according to claim 1, characterized in that the step of obtaining an original image with suitable gray scale by adjusting the exposure time of the imaging element comprises:
calculating the average gray scale of the image of the area near the fine gap groove on the surface of the workpiece to be welded, which is shot by an imaging element;
and if the average gray scale is not in the preset gray scale range, adjusting the exposure time of the imaging element until the average gray scale of the image in the area near the fine gap groove on the surface of the workpiece to be welded meets the preset gray scale range.
4. The method according to claim 1, wherein the step of calculating and analyzing a grayscale frequency histogram of the original image and determining a first threshold for extracting a groove region and a second threshold for extracting a laser projection region comprises:
calculating a gray level frequency histogram of the original image;
calculating the first threshold value t according to the following formulalow
tlow=maxr,
Wherein r is the gray value in the gray frequency histogram, p (i) is the frequency of occurrence of the gray value i, a is a preset value, and 0< a < 1;
smoothing the gray frequency histogram of the original image to obtain a smoothed gray frequency histogram ps(r) obtaining ps(r) one minimum value point having the largest gray level, and setting the gray level of the minimum value point as the second threshold value thigh
5. The method according to claim 2, wherein the steps of binarizing the original image by using the first threshold and the second threshold, respectively, performing morphological operation and preserving connected domains on the binarized original image, and obtaining a groove region and a laser projection region are specifically as follows:
carrying out binarization processing on the original image by using the first threshold value, and reserving points with the gray level less than or equal to the first threshold value to obtain a first binarized image;
performing morphological closing operation on the first binarized image, then extracting a connected domain, reserving the connected domain meeting a first preset condition, taking the connected domain reserved in the first binarized image as a groove area, and acquiring the coordinate of a groove center in the pixel two-dimensional coordinate system based on the groove area;
performing binarization processing on the original image by using the second threshold value, and reserving points with the gray level being more than or equal to the second threshold value to obtain a second binarized image;
and performing morphological closing operation on the second binary image, then extracting a connected domain, reserving the connected domain meeting a second preset condition, taking the reserved connected domain in the second binary image as a laser projection area, and acquiring coordinates of a series of points on a laser projection line in the pixel two-dimensional coordinate system based on the laser projection area.
6. The method according to claim 5, wherein the step of calculating the three-dimensional position of the groove center and the normal vector of the surface of the workpiece to be welded based on the groove area and the laser projection area comprises:
calculating the coordinates of a series of points on the laser projection line in the imaging element three-dimensional rectangular coordinate system according to the coordinates of the series of points on the laser projection line in the pixel two-dimensional coordinate system, the conversion relation of corresponding points between the imaging element three-dimensional rectangular coordinate system and the pixel two-dimensional coordinate system and the equation of each light plane of the multi-line laser light source in the imaging element three-dimensional rectangular coordinate system;
fitting an equation of a workpiece plane where the multi-line laser projection is located in the three-dimensional rectangular coordinate system of the imaging element based on coordinates of a series of points on the laser projection line in the three-dimensional rectangular coordinate system of the imaging element, and calculating according to the equation to obtain a normal vector of the workpiece plane;
and calculating to obtain the coordinate of the groove center in the three-dimensional rectangular coordinate system according to the coordinate of the groove center in the pixel two-dimensional coordinate system, an equation of a workpiece plane where the multi-line laser projection is located in the imaging element three-dimensional rectangular coordinate system, and a conversion relation of corresponding points between the imaging element three-dimensional rectangular coordinate system and the pixel two-dimensional coordinate system.
7. The method according to claim 4, wherein the step of smoothing the grayscale frequency histogram specifically comprises:
and smoothing the gray frequency histogram by adopting a Gaussian filtering method or an average value filtering method.
8. The method according to claim 5, wherein the first preset condition is specifically:
wherein A represents the area of the connected domain, Amin1A first area threshold, R, representing a predetermined connected componentcRepresents the circularity of connected component, Rcmax1Representing a preset first roundness rate threshold value of the connected domain;
wherein R iscIs defined as:
wherein P represents the perimeter of the connected domain;
accordingly, the second preset condition is:
wherein A represents the area of the connected domain, Amin2A second area threshold, R, representing a predetermined connected domaincRepresents the circularity of connected component, Rcmax2And a second roundness rate threshold value representing a preset connected domain.
9. An electronic device, comprising:
at least one processor; and
at least one memory communicatively coupled to the processor, wherein:
the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1 to 8.
10. A non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the method of any one of claims 1 to 8.
CN201910037379.6A 2019-01-15 2019-01-15 Welding bead track and posture real-time tracking detection method, electronic equipment and medium CN109822216B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910037379.6A CN109822216B (en) 2019-01-15 2019-01-15 Welding bead track and posture real-time tracking detection method, electronic equipment and medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910037379.6A CN109822216B (en) 2019-01-15 2019-01-15 Welding bead track and posture real-time tracking detection method, electronic equipment and medium
PCT/CN2020/071096 WO2020147639A1 (en) 2019-01-15 2020-01-09 Method for real-time tracking and detection of weld bead trajectory and attitude, electronic device and medium

Publications (2)

Publication Number Publication Date
CN109822216A CN109822216A (en) 2019-05-31
CN109822216B true CN109822216B (en) 2020-03-17

Family

ID=66861078

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910037379.6A CN109822216B (en) 2019-01-15 2019-01-15 Welding bead track and posture real-time tracking detection method, electronic equipment and medium

Country Status (2)

Country Link
CN (1) CN109822216B (en)
WO (1) WO2020147639A1 (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109822216B (en) * 2019-01-15 2020-03-17 清华大学 Welding bead track and posture real-time tracking detection method, electronic equipment and medium

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS6033874A (en) * 1983-08-03 1985-02-21 Mitsubishi Heavy Ind Ltd Robot for arc welding
US5481085A (en) * 1994-09-09 1996-01-02 University Of Kentucky Research Foundation Apparatus and method for measuring 3-D weld pool shape
CN102780845A (en) * 2012-06-14 2012-11-14 清华大学 Light source alternate strobe synchronous camera shooting method and vision detection system
CN103954216B (en) * 2014-05-13 2017-04-12 清华大学 Strong specular reflection workpiece thin and narrow groove detection device and method based on spherical surface light sources
CN104950800B (en) * 2015-06-12 2017-08-08 广东省自动化研究所 A kind of localization method for seeking track localization process system
CN106952281B (en) * 2017-05-15 2019-09-27 上海交通大学 The method that a kind of identification of weld profile feature and its welding bead are planned in real time
CN109822216B (en) * 2019-01-15 2020-03-17 清华大学 Welding bead track and posture real-time tracking detection method, electronic equipment and medium

Also Published As

Publication number Publication date
CN109822216A (en) 2019-05-31
WO2020147639A1 (en) 2020-07-23

Similar Documents

Publication Publication Date Title
US9798384B2 (en) Eye gaze tracking method and apparatus and computer-readable recording medium
KR101858491B1 (en) 3-d image analyzer for determining viewing direction
US9762881B2 (en) Reducing disparity and depth ambiguity in three-dimensional (3D) images
JP4469476B2 (en) Eye position detection method and eye position detection apparatus
US8755573B2 (en) Time-of-flight sensor-assisted iris capture system and method
KR100373002B1 (en) Method for judgment out of lane of vehicle
US9172931B2 (en) Projection display device, information processing device, projection display system, and program
US7835568B2 (en) Method and apparatus for image-based photorealistic 3D face modeling
US9313460B2 (en) Depth-aware blur kernel estimation method for iris deblurring
CN103761519B (en) Non-contact sight-line tracking method based on self-adaptive calibration
US10192103B2 (en) System and method for detecting and removing occlusions in a three-dimensional image
US8591030B2 (en) Eye position registering and tracking
US9886759B2 (en) Method and system for three-dimensional data acquisition
US8848978B2 (en) Fast obstacle detection
JP4723834B2 (en) Photorealistic three-dimensional face modeling method and apparatus based on video
US8897546B2 (en) Semi-global stereo correspondence processing with lossless image decomposition
US20170031437A1 (en) Sight tracking method and device
KR100405846B1 (en) Method for Locating a Subject&#39;s Lips in a Facial Image
US7916904B2 (en) Face region detecting device, method, and computer readable recording medium
CN104463795B (en) A kind of dot matrix DM image in 2 D code processing method and processing device
JP4004634B2 (en) Face image eye position detection apparatus and method
KR20010103631A (en) System and method for biometrics-based facial feature extraction
JP3868876B2 (en) Obstacle detection apparatus and method
Rabie Robust estimation approach for blind denoising
EP2234086A1 (en) Vehicle periphery monitoring device, vehicle, vehicle periphery monitoring program, and vehicle periphery monitoring method

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant