CN110849285A - Welding spot depth measuring method, system and medium based on monocular camera - Google Patents

Welding spot depth measuring method, system and medium based on monocular camera Download PDF

Info

Publication number
CN110849285A
CN110849285A CN201911142628.4A CN201911142628A CN110849285A CN 110849285 A CN110849285 A CN 110849285A CN 201911142628 A CN201911142628 A CN 201911142628A CN 110849285 A CN110849285 A CN 110849285A
Authority
CN
China
Prior art keywords
welding
information
monocular camera
spot
depth
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.)
Pending
Application number
CN201911142628.4A
Other languages
Chinese (zh)
Inventor
江琴
王东
唐鼎
郑永佳
刘玮洁
李大永
彭颖红
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.)
Shanghai Xin Yanlong Motor Vehicle Equipment Manufacturing Co Ltd
Shanghai Jiaotong University
Original Assignee
Shanghai Xin Yanlong Motor Vehicle Equipment Manufacturing Co Ltd
Shanghai Jiaotong University
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 Shanghai Xin Yanlong Motor Vehicle Equipment Manufacturing Co Ltd, Shanghai Jiaotong University filed Critical Shanghai Xin Yanlong Motor Vehicle Equipment Manufacturing Co Ltd
Priority to CN201911142628.4A priority Critical patent/CN110849285A/en
Publication of CN110849285A publication Critical patent/CN110849285A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01BMEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00Measuring arrangements characterised by the use of optical techniques
    • G01B11/22Measuring arrangements characterised by the use of optical techniques for measuring depth

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention provides a method, a system and a medium for measuring the depth of a welding spot based on a monocular camera, comprising the following steps: establishing a global coordinate system: establishing a global coordinate system at a ground set position; calibrating internal and external parameters of the monocular camera: placing a checkerboard at the determined position, and calibrating internal and external parameters of the monocular camera according to the linear transformation relation between the coordinate of each control point and the pixel coordinate of the imaging point of the control point in the image plane of the monocular camera; a sequence image acquisition step: the manipulator drives the monocular camera to move in a set track, and the monocular camera collects sequence images in the moving process; acquiring welding spot parameter information: obtaining the central positions of all welding points and the circular arcs of the welding points in the image; a welding spot depth obtaining step: two images containing the same welding point are extracted, and the depth information of the welding point is obtained. The welding spot depth information can guide the welding process of the spot welding process. The invention can save the physical hardware overhead and has more accurate processing method.

Description

Welding spot depth measuring method, system and medium based on monocular camera
Technical Field
The invention relates to the field of industrial visual detection, in particular to a method, a system and a medium for measuring the depth of a welding spot based on a monocular camera, and particularly relates to a machine visual detection method suitable for a welding spot of a white car body.
Background
Spot welding of body-in-white in the automotive industry is widely used due to its robust welding and low cost. The detection of spot welds is of self-evident importance in relation to the personal safety of the consumer. The demand of spot welding detection is big for the car of super large batch production, and traditional reliance human eye detects has subjectivity, people is tired easily and experience dependence is big, still has management and the overhead problem to personnel. The use of industrial cameras for solder joint detection is then by itself the direction of human efforts. In the 7 large defect type of the welding spot, too deep indentation and too shallow indentation occupy two seats. The depth of the welding spot can be seen to play an important role in judging whether the welding spot is qualified or not. To obtain depth information, there are three main methods currently used: a structured light; binocular vision; laser triangulation. The laser equipment is relatively expensive and is not suitable for large-scale use. The structured light three-dimensional scanner needs to have a structured light source emitting head and at least 2 cameras for shooting, so the size of the structured light three-dimensional scanner is difficult to be small. A binocular vision three-dimensional scanner, as its name implies, must have the position of two cameras. A plurality of complex arc surfaces, particularly concave arcs, are arranged on a white automobile body, and dead angles are generated for hardware equipment with large sizes such as structural light and binocular vision. Even if the blind spot is viewed by the delicate shooting distance and angle setting, this setting process takes a lot of man-hours. However, the adoption of a small and flexible monocular industrial camera generally can only shoot a two-dimensional image and cannot obtain the depth of the image. It is common practice to infer three dimensions from two-dimensional images, such as Shapefrom shading. However, this method is not accurate enough to be used for qualitative analysis, but not for quantitative measurement. And it is sensitive to light and physical surface characteristics, and is prone to large errors.
Patent document CN106447766B discloses a method of acquiring depth information using a monocular camera, but it relates two frames of images by irradiating a laser light on a target point. There is still room for improvement in the accuracy of the processing method.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a welding spot depth measuring method, a welding spot depth measuring system and a welding spot depth measuring medium based on a monocular camera.
The invention provides a welding spot depth measuring method based on a monocular camera, which comprises the following steps: establishing a global coordinate system: establishing a global coordinate system at a ground set position, and acquiring global coordinate system establishment result information; calibrating internal and external parameters of the monocular camera: establishing result information according to a global coordinate system, placing a checkerboard at a determined position, calibrating internal and external parameters of the monocular camera according to a linear transformation relation between the coordinate of each control point and the pixel coordinate of an imaging point of the control point in the image plane of the monocular camera, and acquiring calibration result information of the internal and external parameters of the monocular camera; a sequence image acquisition step: according to the set information of the movement track of the manipulator, the manipulator drives the monocular camera to move in the set track, and the monocular camera acquires sequence images in the movement process to acquire the acquisition information of the sequence images; acquiring welding spot parameter information: acquiring information according to the sequence image to obtain the center positions of all welding spots and the arcs of the welding spots in the image and obtain the center position information and the arc information of the welding spots; a welding spot depth obtaining step: extracting two images containing the same welding point according to the sequence image acquisition information, the welding point center position information and the welding point arc information, and acquiring welding point depth information according to visual difference; the welding spot depth information can guide the welding process of the spot welding process.
Preferably, the method comprises the following steps: path planning step: adjusting the focal length of the monocular camera, planning the path of the manipulator, enabling the lens of the monocular camera to be aligned to a welding point, and setting and keeping the distance from the monocular camera to the welding point; the path planning step is performed before the monocular camera inside and outside parameter calibration step.
Preferably, the welding spot parameter information acquiring step includes: hough transformation step: according to the sequence image acquisition information, Hough transformation is adopted for each frame of image, the center positions of all welding spots and the circular arcs of the welding spots in the image are obtained, and the information of the center positions of the welding spots and the circular arcs of the welding spots is obtained.
Preferably, the solder joint depth acquiring step includes: parameter difference calculation: according to the information of the center position of the welding spot and the information of the arc of the welding spot, the depth information of the circle center of the welding spot and the depth information of the plane where the arc of the welding spot is located are obtained; calculating the difference between the depth of the circle center of the welding spot and the depth of the plane of the arc of the welding spot according to the depth information of the circle center of the welding spot and the depth information of the plane of the arc of the welding spot, and acquiring the depth information of the welding spot; the plane of the welding spot circular arc is a plane formed by three determined points on the welding spot circular arc.
Preferably, the three determined points on the welding spot arc are respectively the intersection point of the connecting line between the welding spot and the centers of the left and right welding spots on the welding spot arc, and the intersection point of the straight line perpendicular to the connecting line with the left welding spot and the upper half arc.
The invention provides a welding spot depth measuring system based on a monocular camera, which comprises: a global coordinate system establishment module: establishing a global coordinate system at a ground set position, and acquiring global coordinate system establishment result information; the monocular camera internal and external parameter calibration module comprises: establishing result information according to a global coordinate system, placing a checkerboard at a determined position, calibrating internal and external parameters of the monocular camera according to a linear transformation relation between the coordinate of each control point and the pixel coordinate of an imaging point of the control point in the image plane of the monocular camera, and acquiring calibration result information of the internal and external parameters of the monocular camera; a sequence image acquisition module: according to the set information of the movement track of the manipulator, the manipulator drives the monocular camera to move in the set track, and the monocular camera acquires sequence images in the movement process to acquire the acquisition information of the sequence images; the welding spot parameter information acquisition module: acquiring information according to the sequence image to obtain the center positions of all welding spots and the arcs of the welding spots in the image and obtain the center position information and the arc information of the welding spots; solder joint degree of depth acquisition module: extracting two images containing the same welding point according to the sequence image acquisition information, the welding point center position information and the welding point arc information, and acquiring welding point depth information according to visual difference; the welding spot depth information can guide the welding process of the spot welding process.
Preferably, the method comprises the following steps: a path planning module: adjusting the focal length of the monocular camera, planning the path of the manipulator, enabling the lens of the monocular camera to be aligned to a welding point, and setting and keeping the distance from the monocular camera to the welding point; the path planning module is executed before the monocular camera inside and outside parameter calibration module.
Preferably, the welding spot parameter information obtaining module includes: a Hough transformation module: according to the sequence image acquisition information, Hough transformation is adopted for each frame of image, the center positions of all welding spots and the circular arcs of the welding spots in the image are obtained, and the information of the center positions of the welding spots and the circular arcs of the welding spots is obtained.
Preferably, the solder joint depth acquisition module includes: a parameter difference module: according to the information of the center position of the welding spot and the information of the arc of the welding spot, the depth information of the circle center of the welding spot and the depth information of the plane where the arc of the welding spot is located are obtained; calculating the difference between the depth of the circle center of the welding spot and the depth of the plane of the arc of the welding spot according to the depth information of the circle center of the welding spot and the depth information of the plane of the arc of the welding spot, and acquiring the depth information of the welding spot; the plane of the welding spot circular arc is a plane formed by three determined points on the welding spot circular arc.
According to the present invention, there is provided a computer readable storage medium having a computer program stored thereon, which, when being executed by a processor, carries out the steps of the monocular camera based weld spot depth measuring method.
Compared with the prior art, the invention has the following beneficial effects:
1. according to the invention, only one monocular camera (industrial camera) is used for acquiring images, and the robot grabs the monocular camera to sweep all welding points on the vehicle body once, so that the depth information of each welding point can be known;
2. the invention adopts Hough transformation for association, saves a cost on physical hardware, and is more accurate in a pixel-level processing method.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a schematic flow chart of the method of the present invention.
FIG. 2 is a system framework diagram of the present invention.
Fig. 3 is a schematic diagram illustrating a method for finding a corresponding point according to an embodiment of the present invention.
In the figure:
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that it would be obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit of the invention. All falling within the scope of the present invention.
As shown in fig. 1, 2 and 3, the method for measuring the depth of a weld spot based on a monocular camera according to the present invention includes: establishing a global coordinate system: establishing a global coordinate system at a ground set position, and acquiring global coordinate system establishment result information; calibrating internal and external parameters of the monocular camera: establishing result information according to a global coordinate system, placing a checkerboard at a determined position, calibrating internal and external parameters of the monocular camera according to a linear transformation relation between the coordinate of each control point and the pixel coordinate of an imaging point of the control point in the image plane of the monocular camera, and acquiring calibration result information of the internal and external parameters of the monocular camera; a sequence image acquisition step: according to the set information of the movement track of the manipulator, the manipulator drives the monocular camera to move in the set track, and the monocular camera acquires sequence images in the movement process to acquire the acquisition information of the sequence images; acquiring welding spot parameter information: acquiring information according to the sequence image to obtain the center positions of all welding spots and the arcs of the welding spots in the image and obtain the center position information and the arc information of the welding spots; a welding spot depth obtaining step: extracting two images containing the same welding point according to the sequence image acquisition information, the welding point center position information and the welding point arc information, and acquiring welding point depth information according to visual difference; the welding spot depth information can guide the welding process of the spot welding process.
Preferably, the method comprises the following steps: path planning step: adjusting the focal length of the monocular camera, planning the path of the manipulator, enabling the lens of the monocular camera to be aligned to a welding point, and setting and keeping the distance from the monocular camera to the welding point; the path planning step is performed before the monocular camera inside and outside parameter calibration step.
Preferably, the welding spot parameter information acquiring step includes: hough transformation step: according to the sequence image acquisition information, Hough transformation is adopted for each frame of image, the center positions of all welding spots and the circular arcs of the welding spots in the image are obtained, and the information of the center positions of the welding spots and the circular arcs of the welding spots is obtained.
Preferably, the solder joint depth acquiring step includes: parameter difference calculation: according to the information of the center position of the welding spot and the information of the arc of the welding spot, the depth information of the circle center of the welding spot and the depth information of the plane where the arc of the welding spot is located are obtained; calculating the difference between the depth of the circle center of the welding spot and the depth of the plane of the arc of the welding spot according to the depth information of the circle center of the welding spot and the depth information of the plane of the arc of the welding spot, and acquiring the depth information of the welding spot; the plane of the welding spot circular arc is a plane formed by three determined points on the welding spot circular arc.
Preferably, the three determined points on the welding spot arc are respectively the intersection point of the connecting line between the welding spot and the centers of the left and right welding spots on the welding spot arc, and the intersection point of the straight line perpendicular to the connecting line with the left welding spot and the upper half arc.
Specifically, in one embodiment, a method for measuring the depth of a weld spot based on a monocular camera comprises: a monocular camera is mounted at the end of the robot to obtain the determined position and orientation at the determined time. When the manipulator drives the camera to move, the camera takes pictures at a certain frame rate, so that the sequence number of the obtained sequence photos can obtain the determined direction and position of the camera during taking pictures. Before the test is started, the focal length of the camera is adjusted, and when the track of the manipulator is set, the distance from the plane of the camera to the welding point is determined according to the adjusted focal length, and the optical axis of the camera is perpendicular to the welding point to be shot as much as possible.
And then establishing a world coordinate system with the ground as a reference system. A checkerboard of a4 paper was printed and glued to a rigid board. The board is placed in a fixed position and orientation, such as perpendicular to the Z axis of the world coordinate system, with a distance of 100mm from the origin, with the meridian of the grid parallel to the X axis and the weft parallel to the Y axis. The checkerboard is stationary and the robot drives the camera to photograph the checkerboard at different positions (each position having known coordinates). And obtaining the internal and external parameters of the monocular camera by using a Zhangyingyou calibration method. And starting the test, and finding out the photos of two positions simultaneously containing the same interested welding point in the sequence images shot by the camera.
And obtaining the disparity maps of the two images according to the positions of the welding points. And obtaining the depth of the center of the welding point according to the disparity map. And obtaining the depth of the plane where the circular arc of the welding point is located according to the parallax map by selecting three fixed points and respectively obtaining the three fixed points in the two images. These three points are: as shown in fig. 3, the second welding point 2 is the welding point to be measured, the first welding point 1 is the left welding point, and the third welding point 3 is the right welding point. The line connecting the centers of the first spot weld 1 and the second spot weld 2 will have an intersection point a with the arc of the second spot weld 2. The line connecting the third solder point 3 with the centre of the second solder point 2 will have an intersection point B with the arc of the second solder point 2. These two points can be found in both of the selected original images, which are a1 and a2, B1 and B2. A straight line perpendicular to the center line of the first weld points 1 and 2 can be found through the center of the second weld point 2. The straight line and the upper semicircle of the circular arc of the second welding point 2 only have one intersection point C. These two points can be found in both of the selected original images, as C1 and C2. The depths of the A, B and C points can be obtained according to the parallax of the two images. And thus their coordinates in the world coordinate system. Three points define a plane. The depth of the center of the second weld point 2 can also be derived from the coordinates of the center in the world coordinate system. In the world coordinate system, the positions of a point to a plane are determined, and the distances between the points and the plane can be calculated. This is the depth of the solder joint.
The person skilled in the art can understand the method for measuring the depth of a weld spot based on a monocular camera provided by the present invention as an embodiment of the system for measuring the depth of a weld spot based on a monocular camera provided by the present invention. That is, the monocular camera based weld spot depth measuring system may be implemented by executing the flow of steps of the monocular camera based weld spot depth measuring method.
The invention provides a welding spot depth measuring system based on a monocular camera, which comprises: a global coordinate system establishment module: establishing a global coordinate system at a ground set position, and acquiring global coordinate system establishment result information; the monocular camera internal and external parameter calibration module comprises: establishing result information according to a global coordinate system, placing a checkerboard at a determined position, calibrating internal and external parameters of the monocular camera according to a linear transformation relation between the coordinate of each control point and the pixel coordinate of an imaging point of the control point in the image plane of the monocular camera, and acquiring calibration result information of the internal and external parameters of the monocular camera; a sequence image acquisition module: according to the set information of the movement track of the manipulator, the manipulator drives the monocular camera to move in the set track, and the monocular camera acquires sequence images in the movement process to acquire the acquisition information of the sequence images; the welding spot parameter information acquisition module: acquiring information according to the sequence image to obtain the center positions of all welding spots and the arcs of the welding spots in the image and obtain the center position information and the arc information of the welding spots; solder joint degree of depth acquisition module: extracting two images containing the same welding point according to the sequence image acquisition information, the welding point center position information and the welding point arc information, and acquiring welding point depth information according to visual difference; the welding spot depth information can guide the welding process of the spot welding process.
Preferably, the method comprises the following steps: a path planning module: adjusting the focal length of the monocular camera, planning the path of the manipulator, enabling the lens of the monocular camera to be aligned to a welding point, and setting and keeping the distance from the monocular camera to the welding point; the path planning module is executed before the monocular camera inside and outside parameter calibration module.
Preferably, the welding spot parameter information obtaining module includes: a Hough transformation module: according to the sequence image acquisition information, Hough transformation is adopted for each frame of image, the center positions of all welding spots and the circular arcs of the welding spots in the image are obtained, and the information of the center positions of the welding spots and the circular arcs of the welding spots is obtained.
Preferably, the solder joint depth acquisition module includes: a parameter difference module: according to the information of the center position of the welding spot and the information of the arc of the welding spot, the depth information of the circle center of the welding spot and the depth information of the plane where the arc of the welding spot is located are obtained; calculating the difference between the depth of the circle center of the welding spot and the depth of the plane of the arc of the welding spot according to the depth information of the circle center of the welding spot and the depth information of the plane of the arc of the welding spot, and acquiring the depth information of the welding spot; the plane of the welding spot circular arc is a plane formed by three determined points on the welding spot circular arc.
According to the present invention, there is provided a computer readable storage medium having a computer program stored thereon, which, when being executed by a processor, carries out the steps of the monocular camera based weld spot depth measuring method.
The invention calibrates the internal and external parameters of the monocular camera by establishing a world coordinate system on the ground and using a checkerboard with a determined position; according to the invention, the motion of the manipulator is associated with the shooting beat of the camera, so that the position information of the camera at the moment can be known according to the serial number of the monocular camera; in the invention, all welding spots are found out by Hough transformation on each image, and the circle center position and the circular arc diameter of each welding spot are stored; the method comprises the steps of selecting two frames of images containing the same complete welding point, and calibrating by combining position information and parameters of the two frames of images to obtain a disparity map of the welding point; in the invention, the plane where the arc of the welding spot is located is determined by the plane where three fixed points are located; in the invention, the depth of the center of the welding spot and the distance between the planes of the arcs of the welding spot are the depth of the welding spot.
According to the invention, only one monocular camera (industrial camera) is used for acquiring images, and the robot grabs the monocular camera to sweep all welding points on the vehicle body once, so that the depth information of each welding point can be known; the invention adopts Hough transformation for association, saves a cost on physical hardware, and is more accurate in a pixel-level processing method.
Those skilled in the art will appreciate that, in addition to implementing the system and its various devices, modules, units provided by the present invention as pure computer readable program code, the system and its various devices, modules, units provided by the present invention can be fully implemented by logically programming method steps in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Therefore, the system and various devices, modules and units thereof provided by the invention can be regarded as a hardware component, and the devices, modules and units included in the system for realizing various functions can also be regarded as structures in the hardware component; means, modules, units for performing the various functions may also be regarded as structures within both software modules and hardware components for performing the method.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.

Claims (10)

1. A welding spot depth measuring method based on a monocular camera is characterized by comprising the following steps:
establishing a global coordinate system: establishing a global coordinate system at a ground set position, and acquiring global coordinate system establishment result information;
calibrating internal and external parameters of the monocular camera: establishing result information according to a global coordinate system, placing a checkerboard at a determined position, calibrating internal and external parameters of the monocular camera according to a linear transformation relation between the coordinate of each control point and the pixel coordinate of an imaging point of the control point in the image plane of the monocular camera, and acquiring calibration result information of the internal and external parameters of the monocular camera;
a sequence image acquisition step: according to the set information of the movement track of the manipulator, the manipulator drives the monocular camera to move in the set track, and the monocular camera acquires sequence images in the movement process to acquire the acquisition information of the sequence images;
acquiring welding spot parameter information: acquiring information according to the sequence image to obtain the center positions of all welding spots and the arcs of the welding spots in the image and obtain the center position information and the arc information of the welding spots;
a welding spot depth obtaining step: extracting two images containing the same welding spot according to the sequence image acquisition information, the welding spot center position information and the welding spot arc information to obtain welding spot depth information;
the welding spot depth information can guide the welding process of the spot welding process.
2. The method for measuring the depth of a welding spot based on a monocular camera according to claim 1, comprising:
path planning step: adjusting the focal length of the monocular camera, planning the path of the manipulator, enabling the lens of the monocular camera to be aligned to a welding point, and setting and keeping the distance from the monocular camera to the welding point;
the path planning step is performed before the monocular camera inside and outside parameter calibration step.
3. The monocular camera-based weld spot depth measuring method according to claim 1, wherein the weld spot parameter information acquiring step includes:
hough transformation step: according to the sequence image acquisition information, Hough transformation is adopted for each frame of image, the center positions of all welding spots and the circular arcs of the welding spots in the image are obtained, and the information of the center positions of the welding spots and the circular arcs of the welding spots is obtained.
4. The monocular camera-based weld spot depth measuring method according to claim 1, wherein the weld spot depth acquiring step includes:
parameter difference calculation: according to the information of the center position of the welding spot and the information of the arc of the welding spot, the depth information of the circle center of the welding spot and the depth information of the plane where the arc of the welding spot is located are obtained; calculating the difference between the depth of the circle center of the welding spot and the depth of the plane of the arc of the welding spot according to the depth information of the circle center of the welding spot and the depth information of the plane of the arc of the welding spot, and acquiring the depth information of the welding spot;
the plane of the welding spot circular arc is a plane formed by three determined points on the welding spot circular arc.
5. The method for measuring the depth of the welding spot based on the monocular camera as recited in claim 4, wherein the three determined points on the arc of the welding spot are respectively an intersection point of a connecting line between the welding spot and the centers of the left and right welding spots on the arc of the welding spot, and an intersection point of a straight line perpendicular to the connecting line with the left welding spot and the upper half arc.
6. A welding spot depth measuring system based on a monocular camera is characterized by comprising:
a global coordinate system establishment module: establishing a global coordinate system at a ground set position, and acquiring global coordinate system establishment result information;
the monocular camera internal and external parameter calibration module comprises: establishing result information according to a global coordinate system, placing a checkerboard at a determined position, calibrating internal and external parameters of the monocular camera according to a linear transformation relation between the coordinate of each control point and the pixel coordinate of an imaging point of the control point in the image plane of the monocular camera, and acquiring calibration result information of the internal and external parameters of the monocular camera;
a sequence image acquisition module: according to the set information of the movement track of the manipulator, the manipulator drives the monocular camera to move in the set track, and the monocular camera acquires sequence images in the movement process to acquire the acquisition information of the sequence images;
the welding spot parameter information acquisition module: acquiring information according to the sequence image to obtain the center positions of all welding spots and the arcs of the welding spots in the image and obtain the center position information and the arc information of the welding spots;
solder joint degree of depth acquisition module: extracting two images containing the same welding spot according to the sequence image acquisition information, the welding spot center position information and the welding spot arc information to obtain welding spot depth information;
the welding spot depth information can guide the welding process of the spot welding process.
7. The monocular camera-based weld spot depth measuring system of claim 6, comprising:
a path planning module: adjusting the focal length of the monocular camera, planning the path of the manipulator, enabling the lens of the monocular camera to be aligned to a welding point, and setting and keeping the distance from the monocular camera to the welding point;
the path planning module is executed before the monocular camera inside and outside parameter calibration module.
8. The monocular camera-based weld spot depth measuring system of claim 6, wherein the weld spot parameter information acquiring module comprises:
a Hough transformation module: according to the sequence image acquisition information, Hough transformation is adopted for each frame of image, the center positions of all welding spots and the circular arcs of the welding spots in the image are obtained, and the information of the center positions of the welding spots and the circular arcs of the welding spots is obtained.
9. The monocular camera-based weld spot depth measuring system of claim 6, wherein the weld spot depth acquiring module comprises:
a parameter difference module: according to the information of the center position of the welding spot and the information of the arc of the welding spot, the depth information of the circle center of the welding spot and the depth information of the plane where the arc of the welding spot is located are obtained; calculating the difference between the depth of the circle center of the welding spot and the depth of the plane of the arc of the welding spot according to the depth information of the circle center of the welding spot and the depth information of the plane of the arc of the welding spot, and acquiring the depth information of the welding spot;
the plane of the welding spot circular arc is a plane formed by three determined points on the welding spot circular arc.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the monocular camera based weld point depth measuring method of any one of claims 1 to 4.
CN201911142628.4A 2019-11-20 2019-11-20 Welding spot depth measuring method, system and medium based on monocular camera Pending CN110849285A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911142628.4A CN110849285A (en) 2019-11-20 2019-11-20 Welding spot depth measuring method, system and medium based on monocular camera

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911142628.4A CN110849285A (en) 2019-11-20 2019-11-20 Welding spot depth measuring method, system and medium based on monocular camera

Publications (1)

Publication Number Publication Date
CN110849285A true CN110849285A (en) 2020-02-28

Family

ID=69603097

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911142628.4A Pending CN110849285A (en) 2019-11-20 2019-11-20 Welding spot depth measuring method, system and medium based on monocular camera

Country Status (1)

Country Link
CN (1) CN110849285A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111692990A (en) * 2020-05-12 2020-09-22 中国电子产品可靠性与环境试验研究所((工业和信息化部电子第五研究所)(中国赛宝实验室)) Method and device for detecting welding spot of tab
WO2021223124A1 (en) * 2020-05-06 2021-11-11 深圳市大疆创新科技有限公司 Position information obtaining method and device, and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102005043776A1 (en) * 2005-09-14 2007-03-22 Bayerische Motoren Werke Ag Ultrasonic test head positioning procedure uses camera fixed on industrial robot to image approximate weld position to create data to place test head in ideal position
CN102168954A (en) * 2011-01-14 2011-08-31 浙江大学 Monocular-camera-based method for measuring depth, depth field and sizes of objects
CN104766333A (en) * 2015-04-20 2015-07-08 吉林大学 Vehicle door point welding robot path correction method based on stereoscopic vision
CN104942496A (en) * 2015-06-29 2015-09-30 湖南大学 Car body-in-white welding spot positioning method and device based on robot visual servo
CN105606620A (en) * 2016-01-29 2016-05-25 广州立为信息技术服务有限公司 PCBA welding spot detection method and system based on vision
CN108021857A (en) * 2017-08-21 2018-05-11 哈尔滨工程大学 Building object detecting method based on unmanned plane image sequence depth recovery
CN108896658A (en) * 2018-05-14 2018-11-27 湖南湖大艾盛汽车技术开发有限公司 A kind of ultrasonic wave automated detection method based on PLC

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102005043776A1 (en) * 2005-09-14 2007-03-22 Bayerische Motoren Werke Ag Ultrasonic test head positioning procedure uses camera fixed on industrial robot to image approximate weld position to create data to place test head in ideal position
CN102168954A (en) * 2011-01-14 2011-08-31 浙江大学 Monocular-camera-based method for measuring depth, depth field and sizes of objects
CN104766333A (en) * 2015-04-20 2015-07-08 吉林大学 Vehicle door point welding robot path correction method based on stereoscopic vision
CN104942496A (en) * 2015-06-29 2015-09-30 湖南大学 Car body-in-white welding spot positioning method and device based on robot visual servo
CN105606620A (en) * 2016-01-29 2016-05-25 广州立为信息技术服务有限公司 PCBA welding spot detection method and system based on vision
CN108021857A (en) * 2017-08-21 2018-05-11 哈尔滨工程大学 Building object detecting method based on unmanned plane image sequence depth recovery
CN108896658A (en) * 2018-05-14 2018-11-27 湖南湖大艾盛汽车技术开发有限公司 A kind of ultrasonic wave automated detection method based on PLC

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
张彬彬: "车身焊点质量检测机器人视觉定位系统", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 *
杨懿: "车身焊点质量检测机器人视觉定位算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
王新成: "《多媒体实用技术(图像分册)》", 30 June 1995, 电子科技大学出版社 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021223124A1 (en) * 2020-05-06 2021-11-11 深圳市大疆创新科技有限公司 Position information obtaining method and device, and storage medium
CN111692990A (en) * 2020-05-12 2020-09-22 中国电子产品可靠性与环境试验研究所((工业和信息化部电子第五研究所)(中国赛宝实验室)) Method and device for detecting welding spot of tab

Similar Documents

Publication Publication Date Title
TWI555379B (en) An image calibrating, composing and depth rebuilding method of a panoramic fish-eye camera and a system thereof
CN105716527B (en) Laser seam tracking transducer calibration method
US20170127045A1 (en) Image calibrating, stitching and depth rebuilding method of a panoramic fish-eye camera and a system thereof
CN110728715A (en) Camera angle self-adaptive adjusting method of intelligent inspection robot
US20140009583A1 (en) Three-dimensional measurement apparatus and robot system
CN111210468A (en) Image depth information acquisition method and device
CN103337069B (en) High-quality three-dimensional color image acquisition methods and device based on multiple camera
CN106625673A (en) Narrow space assembly system and assembly method
JP6880822B2 (en) Equipment, mobile equipment and methods
US11446822B2 (en) Simulation device that simulates operation of robot
CN111009030A (en) Multi-view high-resolution texture image and binocular three-dimensional point cloud mapping method
CN103852060A (en) Visible light image distance measuring method based on monocular vision
JP4132068B2 (en) Image processing apparatus, three-dimensional measuring apparatus, and program for image processing apparatus
CN110097516B (en) Method, system and medium for correcting distortion of image on inner hole wall surface
CN110275179A (en) A kind of building merged based on laser radar and vision ground drawing method
CN112348890B (en) Space positioning method, device and computer readable storage medium
CN110849285A (en) Welding spot depth measuring method, system and medium based on monocular camera
CN107850425B (en) Method for measuring an article
CN111738971B (en) Circuit board stereoscopic scanning detection method based on line laser binocular stereoscopic vision
Said et al. Depth estimation for a mobile platform using monocular vision
CN110543612B (en) Card collection positioning method based on monocular vision measurement
CN111044039A (en) Monocular target area self-adaptive high-precision distance measuring device and method based on IMU
KR101438514B1 (en) Robot localization detecting system using a multi-view image and method thereof
CN110490934A (en) Mixing machine vertical blade attitude detecting method based on monocular camera and robot
CN110969652B (en) Shooting method and system based on mechanical arm monocular camera serving as binocular stereoscopic vision

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20200228

RJ01 Rejection of invention patent application after publication