WO2020147639A1 - 焊道轨迹及姿态实时跟踪检测方法、电子设备及介质 - Google Patents

焊道轨迹及姿态实时跟踪检测方法、电子设备及介质 Download PDF

Info

Publication number
WO2020147639A1
WO2020147639A1 PCT/CN2020/071096 CN2020071096W WO2020147639A1 WO 2020147639 A1 WO2020147639 A1 WO 2020147639A1 CN 2020071096 W CN2020071096 W CN 2020071096W WO 2020147639 A1 WO2020147639 A1 WO 2020147639A1
Authority
WO
WIPO (PCT)
Prior art keywords
threshold
area
coordinate system
groove
imaging element
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2020/071096
Other languages
English (en)
French (fr)
Inventor
都东
薛博策
彭国栋
王力
王国庆
高彦军
田志杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tsinghua University
Capital Aerospace Machinery Co Ltd
Original Assignee
Tsinghua University
Capital Aerospace Machinery Co Ltd
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 Tsinghua University, Capital Aerospace Machinery Co Ltd filed Critical Tsinghua University
Publication of WO2020147639A1 publication Critical patent/WO2020147639A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • 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
    • B23K26/20—Bonding
    • B23K26/21—Bonding by welding
    • 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
    • B23K26/70—Auxiliary operations or equipment

Definitions

  • the embodiments of the present application relate to the field of welding automation, and more specifically, to a method for real-time tracking and detection of weld bead trajectory and posture, electronic equipment, and media.
  • the structured light method is commonly used in weld inspection. This method projects structured light onto the groove, and obtains the position information of the groove through the deformation of the structured light.
  • This method can only detect the three-dimensional coordinates of the groove, and it is difficult to detect the posture of the workpiece surface, so the welding gun cannot be guided to adjust the posture during the welding process.
  • Cipherical Patent Literature discloses a device and method for detecting narrow bevels of a strongly specularly reflective workpiece based on a spherical light source.
  • the sensor alternately lights and projects a laser array and a spherical light source on the surface of the workpiece and synchronizes with an imaging element.
  • Shoot images when different light sources are lit obtain the pose of the workpiece surface near the projection point of the laser array through the images when the laser array is lit, and obtain the two-dimensional information of the groove through the image with uniform brightness when the spherical light source is lit. The two are combined to determine the three-dimensional pose of the groove.
  • this method has two shortcomings: First, there is a time difference between the image lit by the laser array and the image lit by the spherical light source collected by the imaging element. The detection caused by the time difference during high-speed welding or when the surface pose of the workpiece to be welded changes drastically The error is obvious; second, this method requires that the image grayscale when the spherical light source is lit is close to saturation, so as to quickly and accurately extract the center position of the groove. In the application of groove real-time tracking, the detection device is often fixedly connected to the welding torch. In some occasions where long-distance welding is required, such as laser welding in some occasions, the welding torch is difficult to approach the workpiece. In order to make the image gray scale close to saturation, a more powerful spherical light source is required. The larger the power of the light source, the larger the volume will usually be. The larger the size, the larger the volume of the detection device.
  • the embodiments of the present application provide a real-time tracking detection method, electronic equipment and medium for the trajectory and posture of the weld bead, so as to solve the existing technology that is difficult to adapt to high-speed welding, long-distance detection and other occasions when real-time detection of small gap grooves exists in the prior art.
  • the problem is difficult to adapt to high-speed welding, long-distance detection and other occasions when real-time detection of small gap grooves exists in the prior art. The problem.
  • the embodiments of the present application provide a method for real-time tracking and detection of weld bead trajectory and posture, including:
  • the three-dimensional position of the groove center and the normal vector of the surface of the workpiece to be welded are calculated.
  • an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor.
  • the processor executes the program as described in the first aspect. Provides the steps of the real-time tracking detection method of the weld bead trajectory and attitude.
  • the embodiments of the present application provide a non-transitory computer-readable storage medium on which a computer program is stored.
  • the computer program is executed by a processor, real-time tracking of the weld bead trajectory and posture provided in the first aspect is realized Steps of the detection method.
  • the real-time tracking detection method, electronic equipment and medium of weld bead trajectory and posture provided by the embodiments of this application can be applied to high-speed welding and long-distance detection of fine groove grooves, and broaden the application scenarios of the method of fine groove groove detection. And the image processing method is fast, which can meet the requirements of welding real-time tracking.
  • FIG. 1 is a schematic diagram of the structural principle of a detection device adopting the detection method proposed in an embodiment of the present application;
  • Figure 2 is a schematic diagram of a multi-line laser light source projected on the surface of the workpiece to be welded;
  • FIG. 3 is a schematic flow diagram of a method for real-time tracking and detection of weld bead trajectory and posture provided by an embodiment of the application;
  • Figure 4 is a schematic diagram of an original image collected by an imaging element
  • Figure 5 is a gray frequency histogram of the original image collected by the imaging element.
  • FIG. 6 is a schematic diagram of the physical structure of an electronic device provided by an embodiment of the application.
  • Fig. 1 is a schematic diagram of the structure and principle of a detection device for real-time tracking and detecting of weld bead trajectory and posture provided by an embodiment of the present application, including: a control unit 1, a sensor housing 3, and an imaging element 4 fixed in the sensor housing 3, and a filter Element 6, multi-line laser light source 5, and uniform diffusion light source 7.
  • the control unit 1 and the imaging element 4 are connected by a control line; the multi-line laser light source 5 can emit at least two laser lines to project on the surface of the workpiece 8 to be welded, as shown in FIG.
  • the uniformly diffused light source 7 can emit diffused light with uniform brightness to project on the surface of the workpiece to be welded 8; the reflected light from the surface of the workpiece to be welded 8 passes through the filter element 6 and enters the imaging element 4 for imaging.
  • the welding torch needs to be aligned with the welding bead, and at the same time, the welding torch needs to maintain a certain attitude relationship with the surface of the workpiece to be welded (for example, the torch axis should be perpendicular to the surface of the workpiece) to ensure welding quality. Therefore, the welding trajectory and attitude are tracked in real time
  • the goal of detection is to track and detect the three-dimensional position of the groove center and the normal vector of the workpiece surface in real time.
  • the three-dimensional position of the groove center and the normal vector information of the workpiece surface can provide a reference for the adjustment of the welding gun pose and welding process parameters during the welding process.
  • Fig. 3 is a schematic flow chart of a method for real-time tracking and detecting weld bead trajectory and posture provided by an embodiment of the present application, including:
  • Step 100 Use a uniform diffused light source and a multi-line laser light source to simultaneously illuminate the area near the crevice groove on the surface of the workpiece to be welded, and obtain an original image with a suitable gray scale by adjusting the exposure time of the imaging element;
  • the fine gap groove on the surface of the workpiece to be welded refers to the groove with a very small gap, generally not exceeding 0.1mm.
  • the embodiment of the application uses a uniform diffused light source and a multi-line laser light source to simultaneously irradiate the area near the fine groove on the surface of the workpiece to be welded, so that the three-dimensional position of the groove and the normal vector of the workpiece surface can be calculated according to the same frame of image, which avoids the existing
  • the method uses the detection error caused by the time difference when the two frames of images are calculated, and the grayscale of the image does not have to be close to saturation, which reduces the requirement for uniform diffused light source illumination brightness.
  • Adjust the exposure time of the imaging element to obtain an original image with a suitable gray scale where the gray scale refers to that the gray scale of the image obtained by the imaging element meets the preset gray scale range.
  • the multi-line laser light source 5 and the uniformly diffused light source 7 are simultaneously lit to illuminate the area near the groove 81 on the surface of the workpiece 8 to be welded, and the control unit 1 controls the imaging element 4 to take the original image I of the area, as shown in FIG. 4
  • a represents the groove
  • b represents the two laser lines
  • the small squares and ellipses in the figure show the traces of the workpiece surface.
  • the control unit 1 calculates the average gray level rave of the original image I, if rave ⁇ [r min ,r max ], then enters the next step, otherwise the control unit 1 adjusts the exposure time of the imaging element 4 to obtain the original image I again, until r ave ⁇ [r min ,r max ], where [r min ,r max ] is a preset gray scale range, here is to make the surface of the workpiece 8 to be welded in the original image I have a moderate gray scale for subsequent follow-up
  • the groove area and the laser projection area are extracted. For example, when the average gray level of the original image I is 128, it can be considered that the gray level of the original image is moderate.
  • a three-dimensional rectangular coordinate system ⁇ C ⁇ of the imaging element is established, where the origin of ⁇ C ⁇ is the optical center of the imaging element 4, ⁇ C ⁇
  • the z-axis direction is the same as the optical axis direction of the imaging element 4;
  • a two-dimensional pixel coordinate system ⁇ P ⁇ is established on the image collected by the imaging element 4;
  • the multi-line laser light source 5 is calibrated to obtain the 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 Calculate and analyze the gray frequency histogram of the original image, and determine a first threshold for extracting the groove area and a second threshold for extracting the laser projection area;
  • the determination of the first threshold for extracting the groove area and the second threshold for extracting the laser projection area by analyzing the gray frequency histogram of the original image specifically includes:
  • r is the gray value in the gray frequency histogram
  • p(i) is the frequency of the gray value i
  • a is a preset value, 0 ⁇ a ⁇ 1.
  • the gray level of the laser line in the original image I is much higher than other areas, there will be a peak in the high gray area in the gray frequency histogram. As shown in Figure 5, the gray value corresponding to the trough in front of the peak can be taken as Threshold to extract the laser projection area.
  • the gray frequency histogram p(r) is smoothed first to remove random fluctuations in it, and after the smoothed gray frequency histogram p s (r) is obtained, the maximum gray scale in p s (r) is found A minimum point of, and the gray level corresponding to the minimum point is used as the second threshold t high for extracting the laser projection area.
  • the groove 81 may be relatively narrow, there may be no valleys in the low grayscale area of the gray frequency histogram, so a similar method cannot be used to determine the threshold t low for extracting the groove area.
  • Gaussian filtering method or average filtering method may be used to smooth the gray frequency histogram.
  • Step 300 Binarize the original image by using the first threshold and the second threshold respectively, and perform a morphological operation on the original image after the binarization process and the preservation of connected domains to obtain a groove area And laser projection area;
  • the original image is binarized by using the first threshold and the second threshold respectively, two binarized images can be obtained, and the binarized image obtained by the binarization operation using the first threshold is performed
  • the morphology and the connected domain are retained to obtain the groove area; the morphology and the connected domain are retained on the binarized image obtained by the binarization operation using the second threshold to obtain the laser projection area.
  • Step 300 includes the following steps:
  • first threshold t low to perform binarization processing on the original image I, and keep the points in the original image I whose grayscale is less than or equal to the first threshold t low to obtain the first binarized image I low ;
  • a first binarized image I low in the groove region may be slight gaps and holes, so the first binarized image I low morphological closing operation once, so that the gaps and holes which are closed.
  • the gray level in the original image I is low, and it is retained in the middle after the binarization process, and these low-reflection areas are generally small or The shape is not as slender as the groove 81, so the connected domain is extracted again, and the connected domain with large enough area and slender shape is retained.
  • the connected domains whose area and roundness ratio meet the first preset condition are reserved, and the first preset condition is specifically:
  • A represents the area of the connected component
  • a min1 represents the preset first area threshold of the connected component
  • R c represents the roundness rate of the connected component
  • R cmax1 represents the preset first roundness threshold of the connected component
  • the roundness rate R c of the connected domain is defined as:
  • P represents the perimeter of the connected domain.
  • the connected domain remaining in the first binarized image I low is used as the groove area, and the coordinates of the groove center in the pixel two-dimensional coordinate system ⁇ P ⁇ are obtained based on the groove area.
  • the specific steps of obtaining the coordinates of the groove center in the pixel two-dimensional coordinate system may be: taking the middle column in the first binarized image I low , and finding the two intersection points between this column and the remaining connected domains, The midpoint of the two intersections is regarded as the center of the groove, and the coordinates of the intersection are obtained, that is, the coordinates of the center of the groove in the pixel two-dimensional coordinate system ⁇ P ⁇ are obtained. If the connected domain is discontinuous, after the connected domain is fitted with a straight line, the middle column of the first binarized image I low is taken, and the intersection of this column and the fitted connected domain is regarded as the center of the groove, and then Get the coordinates of the groove center in the pixel two-dimensional coordinate system ⁇ P ⁇ .
  • the gray level is higher in the original image I, and is retained in I high after the binarization process, and these high-reflection areas are generally small in area or not shaped like a laser
  • the projection area is the same slender, so the connected domain is extracted again, and the connected domain with large enough area and long enough shape is reserved.
  • the connected domains whose area and roundness ratio meet the second preset condition are reserved, and the second preset condition is specifically:
  • A represents the area of the connected component
  • a min2 represents the preset second area threshold of the connected component
  • R c represents the roundness rate of the connected component
  • R cmax2 represents the preset second roundness threshold of the connected component .
  • R c is defined as described above.
  • the connected domain remaining in the second binary image I high is taken as the laser projection area, where the laser projection area refers to the surface area of the workpiece where the multi-line laser projection is located.
  • Step 400 Based on the groove area and the laser projection area, calculate and obtain the three-dimensional position of the groove center and the normal vector of the surface of the workpiece to be welded.
  • the surface area of the workpiece 8 where multiple laser projection lines are located is regarded as a plane W, and based on the coordinates of a series of points on the laser projection line in the three-dimensional rectangular coordinate system ⁇ C ⁇ of the imaging element, the The equation of the workpiece plane W where the multi-line laser projection is located in the three-dimensional rectangular coordinate system ⁇ C ⁇ of the imaging element.
  • the fitting method can adopt the least square method.
  • 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 ⁇ 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 ⁇ , the The conversion relationship of corresponding points between the imaging element three-dimensional rectangular coordinate system ⁇ C ⁇ and the pixel two-dimensional coordinate system ⁇ P ⁇ is calculated to obtain the coordinates of the groove center in the three-dimensional rectangular coordinate system ⁇ C ⁇ .
  • the three-dimensional position of the groove center and the normal vector of the workpiece surface it can provide a reference for the adjustment of the welding gun's pose and welding process parameters during the welding process.
  • the real-time tracking detection method for the trajectory and posture of the weld bead provided by the embodiments of the application detects the three-dimensional coordinates of the groove and the posture of the workpiece surface, which can be applied to high-speed welding of fine groove grooves, long-distance detection and other occasions, and widens the fine gap
  • the application scenarios of the groove detection method and the fast image processing method can meet the requirements of welding real-time tracking.
  • FIG. 6 is a schematic diagram of the physical structure of an electronic device provided by an embodiment of the application.
  • the electronic device may include: a processor 610, a communication interface 620, a memory (memory) 630, and communication The bus 640, wherein the processor 610, the communication interface 620, and the memory 630 communicate with each other through the communication bus 640.
  • the processor 610 can call a computer program stored on the memory 630 and running on the processor 610 to execute the real-time tracking and detection method of the weld bead trajectory and posture provided by the foregoing method embodiments, for example, including: using a uniformly diffused light source Simultaneously irradiate the area near the gap groove on the surface of the workpiece to be welded with the multi-line laser light source, and obtain the original image with appropriate gray scale by adjusting the exposure time of the imaging element; calculate and analyze the gray frequency histogram of the original image to determine the The first threshold for extracting the groove area and the second threshold for extracting the laser projection area; the first threshold and the second threshold are used to binarize the original image, and the binarized The original image is subjected to morphological operations and connected domains to obtain the groove area and the laser projection area; based on the groove area and the laser projection area, the three-dimensional position of the groove center and the surface of the workpiece to be welded are calculated and obtained Normal vector.
  • the aforementioned logic instructions in the memory 630 can be implemented in the form of software functional units and when sold or used as independent products, they can be stored in a computer readable storage medium.
  • the technical solutions of the embodiments of the present application essentially or contribute to the existing technology or parts of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium.
  • a number of instructions are included to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program code .
  • the embodiments of the present application also provide a non-transitory computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the method for real-time tracking and detection of weld bead trajectory and posture provided by the foregoing method embodiments is implemented.
  • it includes: using a uniform diffuse light source and a multi-line laser light source to simultaneously illuminate the area near the crevice groove on the surface of the workpiece to be welded, and adjusting the exposure time of the imaging element to obtain an original image with a suitable gray level; calculating and analyzing the original image Gray frequency histogram, determining the first threshold for extracting the groove area and the second threshold for extracting the laser projection area; using the first threshold and the second threshold to binarize the original image, Morphological operations and the preservation of connected domains are performed on the original image after the binarization process to obtain the groove area and the laser projection area; based on the groove area and the laser projection area, the three-dimensional position of the groove center is calculated And the normal vector of the surface of the workpiece to be welded.
  • the device embodiments described above are merely illustrative.
  • the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement without creative work.
  • each implementation manner can be implemented by software plus a necessary general hardware platform, and of course, it can also be implemented by hardware.
  • the above technical solutions can be embodied in the form of software products in essence or part of the contribution to the existing technology, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic Discs, optical discs, etc., include several instructions to enable a computer device (which may be a personal computer, server, or network device, etc.) to perform the methods described in the various embodiments or some parts of the embodiments.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Optics & Photonics (AREA)
  • Plasma & Fusion (AREA)
  • Mechanical Engineering (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Laser Beam Processing (AREA)

Abstract

一种焊道轨迹及姿态实时跟踪检测方法，使用均匀漫射光源(7)和多线激光光源(5)同步照射待焊工件(8)表面细隙坡口(8)附近区域，并通过调节成像元件(4)的曝光时间获得灰度合适的原始图像；通过计算分析所述原始图像的灰度频率直方图确定两个阈值；用两个阈值分别对原始图像进行二值化，并提取出坡口区域和激光投影区域；基于所述坡口区域和激光投影区域，计算获得坡口中心的三维位置和所述待焊工件表面的法向量。该方法采用双光源同步照射工件表面并获取灰度不饱和的图像，能够适应高速焊接、远距离检测等特殊场合，且图像处理方法速度快，能够满足焊接实时跟踪的要求。还涉及一种电子设备和一种非暂态计算机可读存储介质。

Description

焊道轨迹及姿态实时跟踪检测方法、电子设备及介质
交叉引用
本申请引用于2019年01月15日提交的专利名称为“焊道轨迹及姿态实时跟踪检测方法、电子设备及介质”的第2019100373796号中国专利申请，其通过引用被全部并入本申请。
技术领域
本申请实施例涉及焊接自动化领域，更具体地，涉及一种焊道轨迹及姿态实时跟踪检测方法、电子设备及介质。
背景技术
在焊接领域，焊缝的自动检测对于焊前自动示教和焊中自动跟踪均具有重要意义，而视觉检测因能够提供丰富的关于焊缝的信息，成为了焊缝自动检测的重要方式。
目前焊缝检测常用结构光方法，该方法将结构光投射到坡口上，通过结构光的变形获取坡口的位置信息，然而当坡口间隙极小时，结构光在图像中的变形难以分辨，且该方法只能检测坡口的三维坐标，难以检测工件表面的姿态，因此焊接过程中无法引导焊枪调整姿态。
中国专利文献(公开号CN103954216A)公开了一种基于球面光源的强镜面反射工件细窄坡口检测装置及方法，该传感器将激光阵列和球面光源交替点亮投射在工件表面上，并用成像元件同步拍摄不同光源点亮时的图像，通过激光阵列点亮时的图像获取激光阵列投影点附近工件表面的位姿，再通过球面光源点亮时的亮度均匀的图像获取坡口的二维信息，将二者结合以确定坡口的三维位姿。然而，该方法存在两点不足：一是成像元件采集的激光阵列点亮的图像和球面光源点亮的图像存在时间差，在高速焊接或待焊工件表面位姿变化剧烈时，由时间差引起的检测误差明显；二是该方法要求球面光源点亮时的图像灰度接近饱和，以便快速准确提取坡口的中心位置，而在坡口实时跟踪的应用中，检测装置往往与焊炬固连，在一些需要远距离焊接的场合中，如某些场合下的激光焊接，焊炬难以接 近工件，为了使图像灰度接近饱和，需要更大功率的球面光源，而光源的功率越大体积一般也会越大，导致检测装置整体的体积增大。
发明内容
本申请实施例提供一种焊道轨迹及姿态实时跟踪检测方法、电子设备及介质，以解决现有技术存在的对细隙坡口进行实时检测时存在的难以适应高速焊接、远距离检测等场合的问题。
第一方面，本申请实施例提供一种焊道轨迹及姿态实时跟踪检测方法，包括：
使用均匀漫射光源和多线激光光源同步照射待焊工件表面细隙坡口附近区域，并通过调节成像元件的曝光时间获得灰度合适的原始图像；
计算并分析所述原始图像的灰度频率直方图，确定用于提取坡口区域的第一阈值和用于提取激光投影区域的第二阈值；
分别利用所述第一阈值和第二阈值对所述原始图像进行二值化，并对经过二值化处理的所述原始图像进行形态学操作和连通域的保留，获得坡口区域和激光投影区域；
基于所述坡口区域和激光投影区域，计算获得坡口中心的三维位置和所述待焊工件表面的法向量。
第二方面，本申请实施例提供一种电子设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述程序时实现如第一方面所提供的焊道轨迹及姿态实时跟踪检测方法的步骤。
第三方面，本申请实施例提供一种非暂态计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现如第一方面所提供的焊道轨迹及姿态实时跟踪检测方法的步骤。
本申请实施例提供的焊道轨迹及姿态实时跟踪检测方法、电子设备及介质，能够适用于细隙坡口的高速焊接、远距离检测等场合，拓宽了细隙坡口检测方法的应用场景，且图像处理方法速度快，能够满足焊接实时跟踪的要求。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为采用本申请实施例提出的检测方法的检测装置的结构原理示意图；
图2为多线激光光源投射在待焊工件表面上的示意图；
图3为本申请实施例提供的焊道轨迹及姿态实时跟踪检测方法的流程示意图；
图4为成像元件采集的原始图像的示意图；
图5为成像元件采集的原始图像的灰度频率直方图。
图6为本申请实施例提供的电子设备的实体结构示意图；
附图标记说明：1-控制单元；2-焊枪；3-传感器外壳；4-成像元件；5-多线激光光源；6-滤光元件；7-均匀漫射光源；8-待焊工件；81-坡口。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
图1是采用本申请实施例提供的焊道轨迹及姿态实时跟踪检测方检测装置的结构原理示意图，包括：控制单元1、传感器外壳3，以及固定于传感器外壳3内的成像元件4、滤光元件6、多线激光光源5以及均匀漫射光源7。其中，控制单元1与成像元件4通过控制线相连；多线激光光源5能发出至少两条激光线投射在待焊工件8的表面，如图2所示，为多线激光光源5投射在待焊工件表面上的示意图；均匀漫射光源7能发出亮度均匀的漫射光投射在待焊工件8的表面；待焊工件8表面的反射光经过滤光元件6后进入成像元件4成像。
焊接过程中，焊枪需要对准焊道，同时焊枪需要与待焊工件表面保持一定的姿态关系(比如焊枪轴线要与工件表面垂直)，以保证焊接质量， 因此，对焊接轨迹及姿态进行实时跟踪检测的目标是实时跟踪检测坡口中心三维位置和工件表面的法向量，坡口中心三维位置和工件表面的法向量信息可为焊接过程中的焊枪位姿调整和焊接工艺参数调节提供参考依据。
图3是本申请实施例提供的焊道轨迹及姿态实时跟踪检测方法的流程示意图，包括：
步骤100、使用均匀漫射光源和多线激光光源同步照射待焊工件表面细隙坡口附近区域，并通过调节成像元件的曝光时间获得灰度合适的原始图像；
待焊工件表面的细隙坡口是指间隙极小的坡口，一般不超过0.1mm。
本申请实施例使用均匀漫射光源和多线激光光源同步照射待焊工件表面细隙坡口附近区域，从而可以根据同一帧图像计算坡口的三维位置和工件表面的法向量，避免了现有方法利用两帧图像进行计算时由时间差引起的检测误差，且图像的灰度不必接近饱和，降低了对均匀漫射光源照明亮度的要求。
调节成像元件的曝光时间，获得灰度合适的原始图像，其中，灰度合适是指成像元件获得的图像的灰度满足预先设置的灰度范围。
具体地，多线激光光源5和均匀漫射光源7同时点亮，照射待焊工件8表面坡口81附近的区域，控制单元1控制成像元件4拍摄该区域的原始图像I，如图4所示，图中的a表示坡口，b表示两条激光线，图中的小方块和椭圆显示了工件表面痕迹。之后控制单元1计算原始图像I的平均灰度r ave，若r ave∈[r min,r max]则进入下一步，否则控制单元1调整成像元件4的曝光时间再次获取原始图像I，直至r ave∈[r min,r max]，其中，[r min,r max]为一预先设定的灰度范围，此处是为了使原始图像I中待焊工件8表面的灰度适中，便于后续步骤中提取坡口区域和激光投影区域。例如，原始图像I的平均灰度为128时，可以认为该原始图像的灰度适中。
为了实现对焊道轨迹及姿态进行实时跟踪检测，在步骤100之前，建立成像元件三维直角坐标系{C}，其中，所述{C}的原点为成像元件4的光心，{C}的z轴方向与成像元件4光轴方向相同；在成像元件4采集的图像上建立像素二维坐标系{P}；
对成像元件4进行标定，获得所述成像元件三维直角坐标系{C}与所 述像素二维坐标系{P}之间对应点的转换关系；
对多线激光光源5进行标定，获得所述多线激光光源每个光平面在所述成像元件三维直角坐标系{C}中的方程。
步骤200、计算并分析所述原始图像的灰度频率直方图，确定用于提取坡口区域的第一阈值和用于提取激光投影区域的第二阈值；
获得平均灰度符合要求的原始图像I后，计算其灰度频率直方图p(r)。
通过分析所述原始图像的灰度频率直方图确定用于提取坡口区域的第一阈值和用于提取激光投影区域的第二阈值，具体包括：
根据下式计算提取坡口区域所用的第一阈值t low：
t low＝max r,
s,t.
Figure PCTCN2020071096-appb-000001
其中，r为灰度频率直方图中的灰度值，p(i)为灰度值i出现的频率，a为一预先设定的值，0＜a＜1。
由于原始图像I中激光线的灰度远高于其他区域，因此灰度频率直方图中高灰度区会存在一个高峰，如图5所示，可通过将高峰前方的低谷对应的灰度值作为阈值来提取激光投影区域。
具体地，先对灰度频率直方图p(r)进行平滑处理以去掉其中的随机波动，得到平滑后的灰度频率直方图p s(r)之后，找到p s(r)中灰度最大的一个极小值点，将该极小值点对应的灰度作为提取激光投影区域的第二阈值t high。
需要说明的是，由于坡口81可能较为细窄，因此灰度频率直方图的低灰度区可能不存在低谷，因此无法用类似的方法确定提取坡口区域所用的阈值t low。
可以采用高斯滤波法或平均值滤波法对所述灰度频率直方图进行平滑处理。
步骤300、分别利用所述第一阈值和第二阈值对所述原始图像进行二值化，并对经过二值化处理的所述原始图像进行形态学操作和连通域的保留，获得坡口区域和激光投影区域；
具体地，分别利用所述第一阈值和第二阈值对所述原始图像进行二值化，可以获得两个二值化图像，对利用第一阈值进行二值化操作获得的二 值化图像进行形态学和连通域的保留，获得坡口区域；对利用第二阈值进行二值化操作获得的二值化图像进行形态学和连通域的保留，获得激光投影区域。
步骤300包括以下步骤：
利用所述第一阈值t low对所述原始图像I进行二值化处理，保留原始图像I中灰度小于等于所述第一阈值t low的点，得到第一二值化图像I low；
由于噪声等原因，第一二值化图像I low中坡口区域可能存在微小的间隙和孔洞，因此对第一二值化图像I low进行一次形态学闭操作，使其中的间隙和孔洞闭合。
由于待焊工件8表面可能存在部分低反射区，如图4所示，在原始图像I中灰度较低，经二值化处理后被保留在中，而这些低反射区一般面积较小或形状不像坡口81一样细长，因此再进行连通域提取，保留面积够大且形状细长的连通域。
即保留面积和圆度率满足第一预设条件的连通域，第一预设条件具体为：
Figure PCTCN2020071096-appb-000002
其中，A代表连通域的面积，A min1代表预先设定的连通域的第一面积阈值，R c代表连通域的圆度率，R cmax1代表预先设定的连通域的第一圆度率阈值；
其中，连通域的圆度率R c定义为：
Figure PCTCN2020071096-appb-000003
其中，P代表连通域的周长。
将所述第一二值化图像I low中保留下的连通域作为坡口区域，基于所述坡口区域获取坡口中心在所述像素二维坐标系{P}中的坐标。
获取坡口中心在所述像素二维坐标系中的坐标的具体步骤可以为：在第一二值化图像I low中取中间的一列，找到这一列与保留下的连通域的两个交点，将两个交点的中点视为坡口中心，获取该交点的坐标，即获得了坡口中心在像素二维坐标系{P}中的坐标。若连通域是不连续的，则对连通域进行直线拟合后，取第一二值化图像I low中间的一列，将这一列与拟合后的连通域的交点视为坡口中心，进而获取到坡口中心在像素二维坐标 系{P}中的坐标。
利用所述第二阈值t high对所述原始图像I进行二值化处理，保留原始图像I中灰度大于等于所述第二阈值t high的点，得到第二二值化图像I high；
由于激光散斑等原因，原始图像I中激光投影区域存在大量微小的低灰度区，二值化后成为微小的间隙和孔洞，因此对I high进行一次形态学闭操作，消除激光投影区域中的微小间隙和孔洞。
由于待焊工件8表面可能存在部分高反射区，在原始图像I中灰度较高，经二值化处理后被保留在I high中，而这些高反射区一般面积较小或形状不像激光投影区域一样细长，因此再进行连通域提取，保留面积够大且形状够细长的连通域，
即保留面积和圆度率满足第二预设条件的连通域，第二预设条件具体为：
Figure PCTCN2020071096-appb-000004
其中，A代表连通域的面积，A min2代表预先设定的连通域的第二面积阈值，R c代表连通域的圆度率，R cmax2代表预先设定的连通域的第二圆度率阈值。R c定义如前所述。
将所述第二二值化图像I high中保留下的连通域作为激光投影区域，其中，激光投影区域是指多线激光投影所在的工件表面区域。
基于所述激光投影区域获取激光投影线上的一系列点在所述像素二维坐标系{P}中的坐标。
步骤400、基于所述坡口区域和激光投影区域，计算获得坡口中心的三维位置和所述待焊工件表面的法向量。
具体地，根据步骤300获得的所述激光投影线上一系列点在所述像素二维坐标系{P}中的坐标，结合之前标定获得的所述成像元件三维直角坐标系{C}与像素二维坐标系{P}之间对应点的转换关系以及所述多线激光光源每个光平面在所述成像元件三维直角坐标系{C}中的方程，计算所述激光投影线上一系列点在所述成像元件三维直角坐标系{C}中的坐标；
将多条激光投影线所在的待焊工件8的表面区域视为一平面W，基于所述激光投影线上一系列点在所述成像元件三维直角坐标系{C}中的坐标，拟合出多线激光投影所在的工件平面W在所述成像元件三维直角坐标系 {C}中的方程。
拟合方法可采用最小二乘法。
并根据所述方程计算获得所述工件平面W的法向量。
根据所述坡口中心在所述像素二维坐标系{P}中的坐标、所述多线激光投影所在的工件平面W在所述成像元件三维直角坐标系{C}中的方程、所述成像元件三维直角坐标系{C}与像素二维坐标系{P}之间对应点的转换关系，计算获得坡口中心在所述三维直角坐标系{C}中的坐标。
根据坡口中心三维位置和工件表面的法向量，可为焊接过程中的焊枪位姿调整和焊接工艺参数调节提供参考依据。
本申请实施例提供的焊道轨迹及姿态实时跟踪检测方法，检测坡口的三维坐标和工件表面的位姿，能够适用于细隙坡口的高速焊接、远距离检测等场合，拓宽了细隙坡口检测方法的应用场景，且图像处理方法速度快，能够满足焊接实时跟踪的要求。
图6为本申请实施例提供的电子设备的实体结构示意图，如图6所示，该电子设备可以包括：处理器(processor)610、通信接口(Communications Interface)620、存储器(memory)630和通信总线640，其中，处理器610，通信接口620，存储器630通过通信总线640完成相互间的通信。处理器610可以调用存储在存储器630上并可在处理器610上运行的计算机程序，以执行上述各方法实施例所提供的焊道轨迹及姿态实时跟踪检测方法，例如包括：使用均匀漫射光源和多线激光光源同步照射待焊工件表面细隙坡口附近区域，并通过调节成像元件的曝光时间获得灰度合适的原始图像；计算并分析所述原始图像的灰度频率直方图，确定用于提取坡口区域的第一阈值和用于提取激光投影区域的第二阈值；分别利用所述第一阈值和第二阈值对所述原始图像进行二值化，并对经过二值化处理的所述原始图像进行形态学操作和连通域的保留，获得坡口区域和激光投影区域；基于所述坡口区域和激光投影区域，计算获得坡口中心的三维位置和所述待焊工件表面的法向量。
此外，上述的存储器630中的逻辑指令可以通过软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储 介质中。基于这样的理解，本申请实施例的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
本申请实施例还提供一种非暂态计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现上述各方法实施例提供的焊道轨迹及姿态实时跟踪检测方法，例如包括：使用均匀漫射光源和多线激光光源同步照射待焊工件表面细隙坡口附近区域，并通过调节成像元件的曝光时间获得灰度合适的原始图像；计算并分析所述原始图像的灰度频率直方图，确定用于提取坡口区域的第一阈值和用于提取激光投影区域的第二阈值；分别利用所述第一阈值和第二阈值对所述原始图像进行二值化，并对经过二值化处理的所述原始图像进行形态学操作和连通域的保留，获得坡口区域和激光投影区域；基于所述坡口区域和激光投影区域，计算获得坡口中心的三维位置和所述待焊工件表面的法向量。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件。基于这样的理解，上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如ROM/RAM、磁碟、光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行各个实施例或者实施例的某些部分所述的方法。
最后应说明的是：以上实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述实施例对本申请进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (10)

  1. 一种焊道轨迹及姿态实时跟踪检测方法，其特征在于，包括：
    使用均匀漫射光源和多线激光光源同步照射待焊工件表面细隙坡口附近区域，并通过调节成像元件的曝光时间获得灰度合适的原始图像；
    计算并分析所述原始图像的灰度频率直方图，确定用于提取坡口区域的第一阈值和用于提取激光投影区域的第二阈值；
    分别利用所述第一阈值和第二阈值对所述原始图像进行二值化，并对经过二值化处理的所述原始图像进行形态学操作和连通域的保留，获得坡口区域和激光投影区域；
    基于所述坡口区域和激光投影区域，计算获得坡口中心的三维位置和所述待焊工件表面的法向量。
  2. 根据权利要求1所述的方法，其特征在于，所述使用均匀漫射光源和多线激光光源同步照射待焊工件表面细隙坡口附近区域，并通过调节成像元件的曝光时间获得灰度合适的原始图像的步骤之前，还包括：
    建立成像元件三维直角坐标系，在成像元件采集的图像上建立像素二维坐标系；
    对成像元件进行标定，获得所述成像元件三维直角坐标系与所述像素二维坐标系之间对应点的转换关系；
    对多线激光光源进行标定，获得所述多线激光光源每个光平面在所述成像元件三维直角坐标系中的方程。
  3. 根据权利要求1所述的方法，其特征在于，所述通过调节成像元件的曝光时间获得灰度合适的原始图像的步骤，具体为：
    计算成像元件拍摄的所述待焊工件表面细隙坡口附近区域的图像的平均灰度；
    若所述平均灰度不在预设的灰度范围内，则调整所述成像元件的曝光时间，直至待焊工件表面细隙坡口附近区域的图像的平均灰度满足所述预设的灰度范围。
  4. 根据权利要求1所述的方法，其特征在于，所述计算并分析所述原始图像的灰度频率直方图，确定用于提取坡口区域的第一阈值和用于提取激光投影区域的第二阈值的步骤，具体为：
    计算所述原始图像的灰度频率直方图；
    根据如下公式计算所述第一阈值t low：
    t low＝max r,
    Figure PCTCN2020071096-appb-100001
    其中，r为灰度频率直方图中的灰度值，p(i)为灰度值i出现的频率，a为一预先设定的值，0＜a＜1；
    对所述原始图像的灰度频率直方图进行平滑处理，得到经过平滑处理后的灰度频率直方图p s(r)，获取p s(r)中灰度最大的一个极小值点，将所述极小值点的灰度作为所述第二阈值t high。
  5. 根据权利要求2所述的方法，其特征在于，所述分别利用所述第一阈值和第二阈值对所述原始图像进行二值化，并对经过二值化处理的所述原始图像进行形态学操作和连通域的保留，获得坡口区域和激光投影区域的步骤，具体为：
    利用所述第一阈值对所述原始图像进行二值化处理，保留灰度小于等于所述第一阈值的点，得到第一二值化图像；
    对所述第一二值化图像进行形态学闭操作，再进行连通域的提取，保留满足第一预设条件的连通域，将所述第一二值化图像中保留下的连通域作为坡口区域，基于所述坡口区域获取坡口中心在所述像素二维坐标系中的坐标；
    利用所述第二阈值对所述原始图像进行二值化处理，保留灰度大于等于所述第二阈值的点，得到第二二值化图像；
    对所述第二二值化图像进行形态学闭操作，再进行连通域的提取，保留满足第二预设条件的连通域，将所述第二二值化图像中保留下的连通域作为激光投影区域，基于所述激光投影区域获取激光投影线上的一系列点在所述像素二维坐标系中的坐标。
  6. 根据权利要求5所述的方法，其特征在于，所述基于所述坡口区域和激光投影区域，计算获得坡口中心的三维位置和所述待焊工件表面的法向量的步骤，具体为：
    根据所述激光投影线上一系列点在所述像素二维坐标系中的坐标、所述成像元件三维直角坐标系与像素二维坐标系之间对应点的转换关系以及所述多线激光光源每个光平面在所述成像元件三维直角坐标系中的方 程，计算所述激光投影线上一系列点在所述成像元件三维直角坐标系中的坐标；
    基于所述激光投影线上一系列点在所述成像元件三维直角坐标系中的坐标，拟合出多线激光投影所在的工件平面在所述成像元件三维直角坐标系中的方程，并根据所述方程计算获得所述工件平面的法向量；
    根据所述坡口中心在所述像素二维坐标系中的坐标、所述多线激光投影所在的工件平面在所述成像元件三维直角坐标系中的方程、所述成像元件三维直角坐标系与像素二维坐标系之间对应点的转换关系，计算获得坡口中心在所述三维直角坐标系中的坐标。
  7. 根据权利要求4所述的方法，其特征在于，所述对所述灰度频率直方图进行平滑处理的步骤，具体为：
    采用高斯滤波法或平均值滤波法对所述灰度频率直方图进行平滑处理。
  8. 根据权利要求5所述的方法，其特征在于，所述第一预设条件具体为：
    Figure PCTCN2020071096-appb-100002
    其中，A代表连通域的面积，A min1代表预先设定的连通域的第一面积阈值，R c代表连通域的圆度率，R cmax1代表预先设定的连通域的第一圆度率阈值；
    其中，R c定义为：
    Figure PCTCN2020071096-appb-100003
    其中，P代表连通域的周长；
    相应地，所述第二预设条件为：
    Figure PCTCN2020071096-appb-100004
    其中，A代表连通域的面积，A min2代表预先设定的连通域的第二面积阈值，R c代表连通域的圆度率，R cmax2代表预先设定的连通域的第二圆度率阈值。
  9. 一种电子设备，其特征在于，包括：
    至少一个处理器；以及
    与所述处理器通信连接的至少一个存储器，其中：
    所述存储器存储有可被所述处理器执行的程序指令，所述处理器调用所述程序指令能够执行如权利要求1至8任一所述的方法。
  10. 一种非暂态计算机可读存储介质，其特征在于，所述非暂态计算机可读存储介质存储计算机指令，所述计算机指令使所述计算机执行如权利要求1至8任一所述的方法。
PCT/CN2020/071096 2019-01-15 2020-01-09 焊道轨迹及姿态实时跟踪检测方法、电子设备及介质 Ceased WO2020147639A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910037379.6A CN109822216B (zh) 2019-01-15 2019-01-15 焊道轨迹及姿态实时跟踪检测方法、电子设备及介质
CN201910037379.6 2019-01-15

Publications (1)

Publication Number Publication Date
WO2020147639A1 true WO2020147639A1 (zh) 2020-07-23

Family

ID=66861078

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/071096 Ceased WO2020147639A1 (zh) 2019-01-15 2020-01-09 焊道轨迹及姿态实时跟踪检测方法、电子设备及介质

Country Status (2)

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

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114782526A (zh) * 2022-06-22 2022-07-22 季华实验室 H型钢的焊缝轨迹计算方法、装置、电子设备及存储介质
CN116930079A (zh) * 2023-07-11 2023-10-24 中国汽车工业工程有限公司 一种四线激光涂胶检测传感器光路干扰优化方法
CN120852371A (zh) * 2025-07-18 2025-10-28 东莞市林泽通讯器材有限公司 一种手机壳装配缺陷检测方法及系统
CN121083045A (zh) * 2025-11-10 2025-12-09 克勒伯电机(宁波)有限公司 一种无刷电机定子点焊设备

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109822216B (zh) * 2019-01-15 2020-03-17 清华大学 焊道轨迹及姿态实时跟踪检测方法、电子设备及介质
CN111179255B (zh) * 2019-12-30 2021-11-16 南京衍构科技有限公司 一种膜式水冷壁自动化制备过程中特征识别方法
US12179284B2 (en) * 2020-08-27 2024-12-31 Dm3D Technology, Llc Vision-based rotary part offset correction for weld toolpathing
CN114345841B (zh) * 2021-12-31 2022-10-04 苏州德威尔卡光电技术有限公司 一种激光清洗过程中的控制方法以及激光清洗控制系统
CN114749849B (zh) * 2022-06-01 2023-09-01 江苏徐工工程机械研究院有限公司 焊接控制方法、装置和系统
CN115055806B (zh) * 2022-08-11 2022-11-18 先富斯技术（武汉）有限公司 基于视觉跟踪的焊接轨迹跟踪方法及装置
CN115988866B (zh) * 2023-03-21 2023-06-20 深圳市利和兴股份有限公司 一种基于机器视觉的nfc lami加工控制方法及系统
CN117705405B (zh) * 2023-11-29 2025-05-20 东风商用车有限公司 发动机水套的二维水流流场分布测试方法、装置及系统
CN119027398A (zh) * 2024-08-19 2024-11-26 河北工业大学 一种用于钢格板焊缝识别与定位的检测方法及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS6033874A (ja) * 1983-08-03 1985-02-21 Mitsubishi Heavy Ind Ltd ア−ク溶接用ロボット
US5481085A (en) * 1994-09-09 1996-01-02 University Of Kentucky Research Foundation Apparatus and method for measuring 3-D weld pool shape
CN102780845A (zh) * 2012-06-14 2012-11-14 清华大学 一种光源交替频闪同步摄像方法及视觉检测系统
CN103954216A (zh) * 2014-05-13 2014-07-30 清华大学 基于球面光源的强镜面反射工件细窄坡口检测装置及方法
CN104950800A (zh) * 2015-06-12 2015-09-30 广东省自动化研究所 一种寻踪定位处理系统及定位方法
CN109822216A (zh) * 2019-01-15 2019-05-31 清华大学 焊道轨迹及姿态实时跟踪检测方法、电子设备及介质

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106952281B (zh) * 2017-05-15 2019-09-27 上海交通大学 一种焊缝轮廓特征识别及其焊道实时规划的方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS6033874A (ja) * 1983-08-03 1985-02-21 Mitsubishi Heavy Ind Ltd ア−ク溶接用ロボット
US5481085A (en) * 1994-09-09 1996-01-02 University Of Kentucky Research Foundation Apparatus and method for measuring 3-D weld pool shape
CN102780845A (zh) * 2012-06-14 2012-11-14 清华大学 一种光源交替频闪同步摄像方法及视觉检测系统
CN103954216A (zh) * 2014-05-13 2014-07-30 清华大学 基于球面光源的强镜面反射工件细窄坡口检测装置及方法
CN104950800A (zh) * 2015-06-12 2015-09-30 广东省自动化研究所 一种寻踪定位处理系统及定位方法
CN109822216A (zh) * 2019-01-15 2019-05-31 清华大学 焊道轨迹及姿态实时跟踪检测方法、电子设备及介质

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114782526A (zh) * 2022-06-22 2022-07-22 季华实验室 H型钢的焊缝轨迹计算方法、装置、电子设备及存储介质
CN114782526B (zh) * 2022-06-22 2022-09-02 季华实验室 H型钢的焊缝轨迹计算方法、装置、电子设备及存储介质
CN116930079A (zh) * 2023-07-11 2023-10-24 中国汽车工业工程有限公司 一种四线激光涂胶检测传感器光路干扰优化方法
CN120852371A (zh) * 2025-07-18 2025-10-28 东莞市林泽通讯器材有限公司 一种手机壳装配缺陷检测方法及系统
CN121083045A (zh) * 2025-11-10 2025-12-09 克勒伯电机(宁波)有限公司 一种无刷电机定子点焊设备

Also Published As

Publication number Publication date
CN109822216B (zh) 2020-03-17
CN109822216A (zh) 2019-05-31

Similar Documents

Publication Publication Date Title
CN109822216B (zh) 焊道轨迹及姿态实时跟踪检测方法、电子设备及介质
US8831285B2 (en) Detecting objects with a depth sensor
CN111344553B (zh) 曲面物体的缺陷检测方法及检测系统
CN114714355A (zh) 自主移动焊接机器人嵌入式视觉跟踪控制系统
CN103455813A (zh) 一种ccd图像测量系统光斑中心定位的方法
CN107192716A (zh) 一种基于轮廓特征的工件缺陷快速检测方法
CN107909571A (zh) 一种焊缝图像处理方法、系统、设备及计算机存储介质
WO2021195873A1 (zh) 识别sfr测试卡图像中感兴趣区域的方法及装置、介质
Wang Unsupervised recognition and characterization of the reflected laser lines for robotic gas metal arc welding
WO2015172485A1 (en) Apparatus and method for detecting narrow groove of specular reflection workpiece
CN110475078A (zh) 摄像机曝光时间调整方法及终端设备
CN112132884B (zh) 基于平行激光和语义分割的海参长度测量方法及系统
CN121585923A (zh) 提升焊缝图像质量的采集设备参数确定方法及设备
Khan et al. High-density single shot 3D sensing using adaptable speckle projection system with varying preprocessing
CN117309701A (zh) 面向高速公路视频监控的雾气浓度检测方法
KR101637977B1 (ko) 레이저 비전 시스템을 이용한 용접 조인트의 특징점 검출 방법
CN113909689B (zh) 一种激光光条的管道焊接坡口特征提取方法
CN103617601B (zh) 一种图像处理方法及装置
CN108106610B (zh) 一种载物台垂直度检测方法、系统及其控制装置
WO2022205827A1 (zh) 结构光图像处理方法、障碍物检测方法、模组及设备
CN110717502B (zh) 一种脉冲激光拼焊图像中熔池识别方法
CN110782439B (zh) 一种辅助检测图像标注质量的方法及装置
CN110298799B (zh) 一种pcb图像定位校正方法
CN111881748A (zh) 一种基于vbai平台建模的车道线视觉识别方法和系统
CN116523864A (zh) 一种焊接坡口的几何特征尺寸检测方法及装置

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: 20741408

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20741408

Country of ref document: EP

Kind code of ref document: A1