CN113538583A - Method for accurately positioning position of workpiece on machine tool and vision system - Google Patents

Method for accurately positioning position of workpiece on machine tool and vision system Download PDF

Info

Publication number
CN113538583A
CN113538583A CN202110858443.4A CN202110858443A CN113538583A CN 113538583 A CN113538583 A CN 113538583A CN 202110858443 A CN202110858443 A CN 202110858443A CN 113538583 A CN113538583 A CN 113538583A
Authority
CN
China
Prior art keywords
image
workpiece
coordinate system
machine tool
pixel
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
CN202110858443.4A
Other languages
Chinese (zh)
Inventor
李智
曾继跃
张仕进
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.)
Roushenggang Intelligent Technology Suzhou Co ltd
Original Assignee
Roushenggang Intelligent Technology Suzhou 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 Roushenggang Intelligent Technology Suzhou Co ltd filed Critical Roushenggang Intelligent Technology Suzhou Co ltd
Priority to CN202110858443.4A priority Critical patent/CN113538583A/en
Publication of CN113538583A publication Critical patent/CN113538583A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
    • G06T5/70—
    • G06T5/90—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
    • G06T7/85—Stereo camera calibration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30164—Workpiece; Machine component
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30244—Camera pose

Abstract

The invention provides a method for accurately positioning a workpiece on a machine tool, which comprises the following steps: s1: providing an image acquisition device which has a relative position relation with the machine tool; s2: acquiring a workpiece to be detected at multiple points through an image acquisition device, and acquiring multi-point image information of the workpiece to be detected on a machine tool operating table; s3: image splicing is carried out on the image information in the step S2, and then outline information of the workpiece is extracted to obtain pixel coordinate information of the workpiece image; s4: obtaining the correlation between the pixel coordinate system of the workpiece image and the machine tool coordinate system by determining the correlation information between the camera coordinate system and the machine tool coordinate system and determining the correlation information between the pixel coordinate system of the workpiece image and the camera coordinate system where the image acquisition device is located; s5: and determining accurate positioning information of the workpiece at the position of the machine tool coordinate system. According to the invention, the time for manually moving the large workpiece for positioning is saved without moving the workpiece, and the positioning can be rapidly and accurately realized.

Description

Method for accurately positioning position of workpiece on machine tool and vision system
Technical Field
The invention relates to the technical field of workpiece processing equipment, in particular to a method for accurately positioning a workpiece on a machine tool and a vision system.
Background
Nowadays, mechanized machining is applied to more and more fields, along with the development of the society, the precision requirement of various industries on the machined product of a machine tool is higher and higher, and in order to improve the machining precision of a workpiece, the accurate positioning of the workpiece on the machine tool is firstly obtained, and the subsequent operation is carried out.
In the prior art, the positioning of a workpiece on a machine tool includes the following three methods: 1. positioning by a direct alignment method: a positioning method for directly aligning the design reference of the workpiece processing surface on a machine tool by using methods such as a dial indicator, a scriber or visual inspection and the like during positioning by a direct alignment method so as to obtain a correct position; 2. positioning by a scribing alignment method: the marking alignment method positioning is a positioning method for aligning a workpiece according to a line segment to be marked out in advance on a blank or a semi-finished product on a machine tool by using a marking pin so as to obtain a correct position; 3. positioning by using a clamp: the positioning of the clamp is a positioning method for obtaining a correct position of a workpiece by directly using a positioning element on the clamp. Because the relative positions of the positioning element of the clamp, the machine tool and the cutter are adjusted in advance, the workpieces do not need to be adjusted one by one when being positioned.
The three positioning methods described above have the following problems:
(1) the direct alignment method depends on the level of alignment workers, and large uncertainty exists in the actual workpiece positioning operation;
(2) the positioning of the scribing alignment method is limited by scribing accuracy and alignment accuracy, so that the positioning accuracy of the workpiece is not high;
(3) the workpiece needs to be placed at a specific position for positioning by using the clamp, time is needed, and positioning efficiency is low.
Disclosure of Invention
The technical scheme for solving the problem is as follows:
a method for the precise positioning of a workpiece in a position on a machine tool for associating the workpiece to be measured with a coordinate system of the machine tool, comprising the steps of:
s1: providing an image acquisition device which has a relative position relation with the machine tool;
s2: acquiring the workpiece to be detected through a plurality of point positions by the image acquisition device to acquire image information of the workpiece to be detected on the machine tool;
s3: acquiring pixel coordinate information of the workpiece image to be detected through the workpiece image information to be detected in the step S2;
s4: obtaining the correlation between the pixel coordinate system of the workpiece image to be measured and the machine tool coordinate system through the correlation information between the camera coordinate system and the machine tool coordinate system and the correlation information between the coordinate information of the workpiece image to be measured and the camera coordinate system where the image acquisition device is located;
s5: and determining accurate positioning information of the workpiece at the position of the machine tool coordinate system.
In the technical scheme, a workpiece to be measured is placed on a machine tool, an image acquisition device acquires image information of the workpiece to be measured, then pixel coordinate information of the image information of the workpiece to be measured is obtained, then the correlation between a pixel coordinate system of the image of the workpiece to be measured and a machine tool coordinate system is obtained according to correlation information of a camera coordinate and the machine tool coordinate, and correlation information of the pixel coordinate system of the image of the workpiece to be measured and a camera coordinate system where the image acquisition device is located, and finally positioning information of the positions of the workpiece to be measured and the machine tool coordinate system is determined; according to the technical scheme, the positioning information of the accurate position between the workpiece to be detected and the machine tool coordinate system can be simply and quickly acquired, and the workpiece to be detected can be conveniently operated on the machine tool in the next step.
On the basis of the above scheme and as a preferable scheme of the scheme: in step S2, the image acquisition device acquires the workpiece to be measured through a single-point position, and acquires image information of the workpiece to be measured on the machine tool this time.
In the technical scheme, the image acquisition device can be used for small workpieces, and complete image information of the workpieces to be detected can be acquired by single-point image acquisition.
On the basis of the above scheme and as a preferable scheme of the scheme: the image acquisition device in step S2 acquires the workpiece to be measured through multipoint acquisition, and acquires image information of the workpiece to be measured on the machine tool this time;
the step S3 further includes an image stitching process, where the image information acquired at multiple positions in the step S2 is subjected to image stitching, and the contour information of the workpiece to be detected is extracted to obtain the pixel coordinate information of the image of the workpiece to be detected.
In the technical scheme, when a large workpiece to be detected is dealt with, the image acquisition device acquires image information of the workpiece at multiple points, then splices and extracts the acquired image information to obtain complete contour information of the workpiece to be detected, pixel coordinate information of the image information of the workpiece to be detected is obtained, then the correlation between a pixel coordinate system of the image of the workpiece to be detected and a machine tool coordinate system is obtained according to correlation information of a camera coordinate and the machine tool coordinate and correlation information of the pixel coordinate system of the image of the workpiece to be detected and the camera coordinate system where the image acquisition device is located, and finally positioning information of the positions of the workpiece to be detected and the machine tool coordinate system is determined; in addition, the workpiece to be measured is positioned only by placing the workpiece to be measured on the machine tool without moving the workpiece to enter a specific position, so that the time for manually moving a large workpiece to position is saved, and the positioning method provided by the invention can quickly and accurately realize positioning.
On the basis of the above scheme and as a preferable scheme of the scheme: before step S4, the method further includes:
the first acquisition point is provided with at least a first positioning point and a second positioning point on the workpiece to be detected within the image range of the workpiece to be detected, the first positioning point is used as a reference origin of the machine tool coordinate system,
step S4 further includes:
and obtaining the deflection angle of the camera coordinate system relative to the machine tool coordinate system according to the pixel center point coordinates of the first positioning point and the second positioning point, thereby obtaining the accurate positioning information of the workpiece including the position and the angle in the machine tool coordinate system.
In the technical scheme, the deflection angle of the camera coordinate system relative to the machine tool coordinate system is obtained through the two fixed points, so that the angle relation between the camera coordinate system and the machine tool coordinate system is further determined, the angle relation of the workpiece in the machine tool coordinate system is further determined, and the positioning accuracy of the position of the workpiece on the machine tool is further improved.
On the basis of the above scheme and as a preferable scheme of the scheme: step S4 further includes:
acquiring pixel coordinates of an image center under pixel coordinates according to image information of the workpiece to be detected at a first acquisition point;
obtaining a scale of the image according to the known distance of the machine tool moving between the first positioning point and the second positioning point and the distance between the pixel coordinates of the first positioning point and the second positioning point corresponding to the known distance in the image;
obtaining the offset between the origin of the coordinate system of the camera and the reference origin of the coordinate system of the machine tool according to the coordinate offset of the pixel coordinate of the first fixed point in the image and the pixel coordinate of the central point of the image and the scale of the image;
when the image acquisition device acquires the image information of the workpiece to be detected through a single point, according to the correlation between the pixel coordinate system of the first acquisition point image of the image acquisition device and the corresponding camera coordinate system and the correlation between the camera coordinate system and the machine tool coordinate system, the correlation between the pixel coordinate system of the first acquisition point image and the machine tool coordinate system is obtained, and then the pixel coordinate system is correlated with the machine tool coordinate system to determine the accurate positioning information of the workpiece to be detected including the position and the angle in the machine tool coordinate system;
when the image acquisition device acquires the image information of the workpiece to be measured through multiple points, the mutual relation between the pixel coordinate system of the first acquisition point position image of the image acquisition device and the corresponding camera coordinate system and the mutual relation between the camera coordinate system and the machine tool coordinate system are obtained, then the pixel coordinate system of other acquisition point images except the first acquisition point is converted into the pixel coordinate system of the first acquisition point position image through the splicing process, so that the global pixel coordinate system of the spliced image of the whole workpiece is obtained, the pixel coordinate system is further associated with the machine tool coordinate system, and the accurate positioning information of the workpiece to be measured including the position and the angle in the machine tool coordinate system is determined.
In the technical scheme, the related data information required by the association of the workpiece to be measured and the machine tool coordinate system and a method for collecting the related data information are provided.
On the basis of the above scheme and as a preferable scheme of the scheme: the conversion formula between the pixel coordinate system and the camera coordinate system is as follows:
Figure BDA0003184923950000041
wherein, S: scale length of the image;
(u0，v0): coordinates of an image coordinate origin in a pixel coordinate system of the image;
(u, v): pixel point coordinates in the workpiece image;
(Xc，Yc): coordinates in the camera coordinate system corresponding to pixel points of the workpiece image.
In the technical scheme, a specific formula for converting the pixel coordinate system, the camera coordinate system and the camera coordinate system is specifically obtained according to the image size of the first acquisition point, the pixel coordinate of the image center point in the pixel coordinate system is obtained, the scale length of the image is obtained according to the known distance of the machine tool moving between the two positioning points and the distance between the pixel center coordinates of the corresponding positioning points in the image, and the pixel coordinate system and the camera coordinate system are converted.
On the basis of the above scheme and as a preferable scheme of the scheme: the coordinate transformation formula between the camera coordinate system and the machine coordinate system is as follows:
Figure BDA0003184923950000042
wherein, (X, Y): machine tool coordinates corresponding to pixel points of the workpiece image;
(Xc，Yc): coordinates in the camera coordinate system corresponding to pixel points of the workpiece image.
θ: the deflection angle of the camera coordinate system relative to the machine tool coordinate system;
(U, V): actual offset between the camera coordinate system and the machine coordinate system.
In the technical scheme, a specific formula for converting a camera coordinate system and a machine tool coordinate system is provided.
On the basis of the above scheme and as a preferable scheme of the scheme:
step S1 further includes: setting an industrial light source and a polarizer for polishing a workpiece to be detected;
step S2 further includes: the industrial light source irradiates a workpiece to be detected at a certain angle on one side or multiple sides, and the edge characteristics of the workpiece to be detected are highlighted, so that the industrial light source is suitable for an imaging occasion of a large-size workpiece to reduce the reflection phenomenon of a metal workpiece; the polarizer arranged on the lens weakens or eliminates the interference effect of astigmatism, reflection, glare and the like.
In the technical scheme, the industrial light source and the polarizer are matched to eliminate the light reflection phenomenon of the workpiece to a certain extent, and adverse influence on post image processing caused by light reflection of the workpiece is avoided.
Referring to fig. 1, in this embodiment, a specific splicing method in the step S3 is to implement image splicing based on an image splicing method of a homography transformation matrix, where the image splicing method of the homography transformation matrix includes the following steps:
q1: extracting feature points of adjacent images by using a sift feature extraction algorithm;
q2: carrying out feature matching on feature points in adjacent images by using a KNN matching algorithm;
q3: purifying the feature matching pairs by using an RANSAC algorithm to eliminate wrong matching pairs;
q4: then calculating homography transformation matrix of the two images according to the purified feature matching pair,
q5: and projecting the second image onto the first image according to the homography transformation matrix of the two images to complete the splicing of the two images, and repeating the operation steps to finally obtain a complete workpiece splicing image.
In the technical scheme, the image splicing method of the homography transformation matrix is used for splicing the images of the workpiece to be detected, which are acquired by the image acquisition device at multiple points, so as to obtain complete workpiece image information.
On the basis of the above scheme and as a preferable scheme of the scheme: further comprising:
for the workpieces with unobvious features, adding feature points in the following way: a1: placing some feature blocks near the overlapping area of the images, thereby increasing the feature points of the images for improving the precision and speed of image splicing; a2: adding some characteristic points on the surface of the workpiece in the image overlapping area by using a marking pen, wherein the characteristic points are used for image splicing scenes which can be painted on the surface of the workpiece, and the image splicing speed and precision are improved; a3: the projector is used for projecting pictures on the surface of the workpiece, so that the feature points of the workpiece image are increased, the workload of an operator is reduced, and the image splicing speed and precision are improved.
In the technical scheme, in an image splicing scene painted on the surface of a workpiece, an operator can add characteristic points on the surface of an image overlapping area of the workpiece by using a marking pen to improve the speed and the precision of image splicing; the projector is used for projecting pictures on the surface of the workpiece, so that the characteristic points of the workpiece image are increased, the workload of an operator is reduced, and the image splicing speed and precision are improved; placing some feature blocks near the overlapping area of the images, thereby increasing the feature points of the images for improving the precision and speed of image splicing; by increasing the characteristic points of the image by using different methods in different application scenes, the speed and the precision of image splicing can be improved.
On the basis of the above scheme and as a preferable scheme of the scheme: the step S2 is preceded by a preprocessing process for improving the sharpness of the image information, the preprocessing process including at least one of the following steps:
m1: the image denoising is used for eliminating or inhibiting the influence of noise on the image and realizing the smoothing of the image;
m2: the image enhancement is used for enhancing the contrast of the image and enabling the image to be clearer;
m3: and image correction is used for carrying out distortion correction on the image.
In the technical scheme, the image of the workpiece to be detected is acquired by the image acquisition device in a multi-point position mode through preprocessing, optimization processing is carried out, the image denoising step eliminates or inhibits the influence of noise on the image to obtain a smooth image, the image enhancement step enhances the contrast of the image to obtain a clear image, the image correction step is used for carrying out distortion correction on the image, and finally smooth, clear and accurate workpiece image information is obtained.
A machine tool comprising a machine tool body, further comprising: the device comprises an image acquisition device and a processor, wherein the image acquisition device is used for controlling the machine tool to drive the machine tool to do vector motion, the processor executes an accurate positioning method of the position of a workpiece on the machine tool, and the machine tool further comprises a light supplementing device which comprises a movable support and a light source, the light source is installed on the movable support, and the movable support is arranged at a proper position of the machine tool and used for supplementing light to the workpiece to be detected by the light source.
According to the technical scheme, the method for accurately positioning the position of the workpiece on the machine tool can be used for quickly and accurately positioning the position of the workpiece on the machine tool, the light supplementing device is additionally arranged outside the machine tool, the light source irradiates on the workpiece, the edge characteristics of the workpiece to be detected are highlighted, and the image acquisition device can conveniently acquire the image information of the workpiece to be detected.
A storage medium having computer-readable instructions stored thereon which, when executed by one or more processors, cause the one or more processors to perform a method of fine positioning of a position of a workpiece on a machine tool.
A vision system, comprising:
an image receiving module: the device is used for receiving multi-point position acquisition of a workpiece to be detected through an image acquisition device and sending multi-point position image information of the workpiece to be detected on a machine tool operating table;
an image stitching module: the image information is used for image splicing, and then the outline information of the workpiece is extracted to obtain the pixel coordinate information of the workpiece image;
a correlation module: the system comprises a camera coordinate acquisition device, a coordinate acquisition device and a coordinate acquisition device, wherein the camera coordinate acquisition device is used for acquiring the correlation information of a workpiece image and a machine tool coordinate;
a positioning information determination module: precise positioning information of the workpiece in a machine coordinate system including at least one of position and angle is determined.
In the technical scheme, an image receiving module in a vision system receives an image of the workpiece to be detected acquired by an image acquisition device in a multi-point position mode, transmits the image to an image splicing module for image information splicing to obtain complete workpiece contour information and obtain a pixel coordinate system of the workpiece image, associates the pixel coordinate system with a camera coordinate system through an association module, then associates the camera coordinate system with a machine tool coordinate system in a transfer mode, and finally determines positioning information of the workpiece in the machine tool coordinate system through a positioning information determination module to finish accurate positioning of the workpiece on a machine tool.
Compared with the prior art, the invention has the following beneficial effects:
1. placing a workpiece to be measured on a machine tool, acquiring image information of the workpiece to be measured by an image acquisition device, then acquiring pixel coordinate information of the image information of the workpiece to be measured, then acquiring the correlation between a pixel coordinate system of the image of the workpiece to be measured and a machine tool coordinate system according to the correlation information of the camera coordinate and the machine tool coordinate and the correlation information of the pixel coordinate system of the image of the workpiece to be measured and a camera coordinate system in which the image acquisition device is located, and finally determining the positioning information of the positions of the workpiece to be measured and the machine tool coordinate system; according to the technical scheme, the positioning information of the accurate position between the workpiece to be detected and the machine tool coordinate system can be simply and quickly acquired, and the workpiece to be detected can be conveniently operated on the machine tool in the next step.
2. When a large workpiece to be detected is dealt with, the image acquisition device acquires image information of the workpiece at multiple points, then splicing and contour extracting are carried out on the acquired image information to obtain complete contour information of the workpiece to be detected, pixel coordinate information of the image information of the workpiece to be detected is obtained, then the correlation between a pixel coordinate system of the image of the workpiece to be detected and a machine tool coordinate system is obtained according to correlation information of a camera coordinate system and a camera coordinate system where the image acquisition device is located, and finally positioning information of the positions of the workpiece to be detected and the machine tool coordinate system is determined; in addition, the workpiece to be measured is positioned only by placing the workpiece to be measured on the machine tool without moving the workpiece to enter a specific position, so that the time for manually moving a large workpiece to position is saved, and the positioning method provided by the invention can quickly and accurately realize positioning.
3. In an image splicing scene painted on the surface of a workpiece, an operator can add characteristic points on the surface of an image overlapping area of the workpiece by using a marking pen to improve the speed and the precision of image splicing; the projector is used for projecting pictures on the surface of the workpiece, so that the characteristic points of the workpiece image are increased, the workload of an operator is reduced, and the image splicing speed and precision are improved; placing some feature blocks near the overlapping area of the images, thereby increasing the feature points of the images for improving the precision and speed of image splicing; by increasing the characteristic points of the image by using different methods in different application scenes, the speed and the precision of image splicing can be improved.
4. The method comprises the steps of preprocessing, collecting images of a workpiece to be detected at multiple points of an image collecting device, optimizing, eliminating or inhibiting the influence of noise on the images in an image denoising step to obtain smooth images, enhancing the contrast of the images in an image enhancing step to obtain clear images, and performing distortion correction on the images in an image correcting step to obtain smooth, clear and accurate image information of the workpiece.
5. An image receiving module in the visual system receives the image of the workpiece to be detected acquired by the image acquisition device in a multi-point position mode, the image is transmitted to an image splicing module to be subjected to image information splicing to obtain complete workpiece contour information, a pixel coordinate system of the workpiece image is obtained, the pixel coordinate system and a camera coordinate system are connected through a connection module, then the camera coordinate system is connected with a machine tool coordinate system in a conversion mode, and finally the positioning information determining module determines the workpiece in the machine tool coordinate system to finish accurate point location of the workpiece on the machine tool.
6. The light supplementing device is additionally arranged outside the machine tool, and the light source irradiates on the workpiece to be detected, so that the edge characteristics of the workpiece to be detected are highlighted, and the image acquisition device can conveniently acquire the image information of the workpiece to be detected.
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 flow chart of a method of accurately positioning a workpiece on a machine tool according to the present invention;
FIG. 2 is a flowchart of an image stitching method of the homography transformation matrix of the present invention.
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.
For a better illustration of the invention, the invention is described in detail below with reference to the accompanying figures 1-2.
The first embodiment is as follows:
a method for the precise positioning of a workpiece in a position on a machine tool for associating the workpiece to be measured with a coordinate system of the machine tool, comprising the steps of:
s1: providing an image acquisition device which has a relative position relation with the machine tool; the image acquisition device in the embodiment is an industrial camera, and before the industrial camera acquires an image of a workpiece to be detected, at least a first positioning point and a second positioning point are arranged on the workpiece in a first image range, and the first positioning point is used as an origin of machine tool coordinates; the industrial camera is then adjusted to a height within the photographing field of view at least sufficient to encompass the first location point and the second location point.
The specific parameters of the camera in the embodiment are that the visual field range of the image is 500mm multiplied by 500mm, the distance between the camera and the object to be measured is 500mm, and the measurement precision of the image is 0.05 mm; camera Basler _ acA2440-75 uc: the frame rate reaches 75fps, the resolution is 500 ten thousand pixels (2448px multiplied by 2048px), the chip size is 8.4mm multiplied by 7.1mm, the chip type CMOS is adopted, the interface usb is 3.0, and the color camera is adopted; lens ML-M0822 UR: 8mm lens, object distance 580mm, field of view 660 × 500 mm. If the 1/5 sub-pixel edge detection algorithm is adopted, the horizontal measurement precision of the workpiece image can reach 0.054mm/px, and the vertical measurement precision can reach 0.048 mm/px.
Step S1 in this embodiment further includes: an industrial light source and a polarizer are arranged for polishing a workpiece to be measured.
S2: acquiring the workpiece to be detected through a single-point position by the image acquisition device to acquire image information of the workpiece to be detected on the machine tool; step S2 further includes: the industrial light source irradiates the workpiece to be detected at a certain angle on one side or multiple sides, and the edge characteristics of the workpiece to be detected are highlighted, so that the method is suitable for the imaging occasion of the workpiece to be detected to reduce the reflection phenomenon of the metal workpiece; and the polarizer is arranged on the lens, so that the interference effects of astigmatism, reflection, glare and the like are weakened or eliminated, the reflection phenomenon of the workpiece can be eliminated to a certain extent by the matched use of the industrial light source and the polarizer, and the unfavorable image caused by the reflection of the workpiece to the later-stage image processing is avoided. In other embodiments, the workpiece to be detected can be polished from above, and the method utilizes a large-scale backlight source to illuminate the surface of the metal workpiece completely, so that the problem of uneven image brightness caused by light reflection is avoided. Specifically, the industrial light source in this embodiment is an LED strip light source, the size of the light source is 600mm × 50mm, and the LED strip light source is mainly used for irradiating a workpiece to be measured at a certain angle on one side or multiple sides, and protruding the edge characteristics of the workpiece to be measured, and is suitable for imaging occasions of large-sized workpieces. The workpiece to be measured is polished by a method of polishing the workpiece from the side by a plurality of light sources, so that the reflection phenomenon of the metal workpiece is reduced.
S3: acquiring pixel coordinate information of the workpiece image to be detected through the workpiece image information to be detected in the step S2;
in this embodiment, in order to deal with the situation that the acquired image information is not clear due to the problem that the image information acquisition device is easily subjected to an external environment or the machine tool itself when the images are spliced, in order to adopt a preprocessing process for improving the definition of the image information before step S4, the preprocessing process includes the following steps:
m1: the image denoising is used for eliminating or inhibiting the influence of noise on the image and realizing the smoothing of the image;
m2: the image enhancement is used for enhancing the contrast of the image and enabling the image to be clearer;
m3: and image correction is used for carrying out distortion correction on the image.
In this embodiment, preprocessing is performed to acquire an image of a workpiece to be measured at a single point location (a first acquisition point location) of an image acquisition device, optimization is performed, an image denoising step eliminates or suppresses influence of noise on the image to obtain a smooth image, an image enhancement step enhances contrast of the image to obtain a clear image, an image correction step is performed to perform distortion correction on the image, and finally smooth, clear and accurate workpiece image information is obtained.
In this embodiment, the image denoising is an image denoising method based on morphological processing, and since noise brings great obstruction and influence to subsequent image processing, the noise of the image needs to be effectively suppressed or eliminated, so as to achieve a smoothing effect of the image. The morphological processing is to eliminate the noise of the image on the basis of keeping the image contour, and mainly comprises four basic operations: corrosion, expansion, opening operation and closing operation, wherein the corrosion and the expansion are basic morphological operators and are all processed aiming at white parts in the image; the principle of corrosion is to define a convolution kernel, convolve the kernel with the image, calculate the minimum value of the pixel points in the kernel coverage area and assign the minimum value to the pixel designated by the reference point, so that the highlight area in the image is gradually reduced, and the expansion is opposite to the highlight area. It should be noted that the invention adopts the method of firstly opening operation on the workpiece image and then closing operation to remove the noise point on the image without affecting the image edge information. It is worth mentioning that the open operation is the corrosion first and then the expansion, and the closed operation is the expansion first and then the corrosion. In other embodiments, the image denoising adopts a filtering algorithm-based image denoising method, such as mean filtering, gaussian filtering, median filtering, and the like, and the filtering algorithm most suitable for the image processing scene is selected by comparing the denoising effects of different filtering; and other processing methods capable of eliminating image noise are within the scope of the present invention.
In the embodiment, the image enhancement is an image enhancement method based on histogram equalization, and the method mainly aims at the problems that the feature points of the workpiece image are sparse and the brightness is not uniform due to the fact that a light source shines from the side.
S4: obtaining the correlation between the pixel coordinate system of the workpiece image to be measured and the machine tool coordinate system through the correlation information between the camera coordinate system and the machine tool coordinate system and the correlation information between the coordinate information of the workpiece image to be measured and the camera coordinate system where the image acquisition device is located;
in this embodiment, step S4 further includes:
acquiring pixel coordinates of an image center under pixel coordinates according to image information of the workpiece to be detected at a first acquisition point;
obtaining a scale of the image according to the known distance of the machine tool moving between the first positioning point and the second positioning point and the distance between the pixel coordinates of the first positioning point and the second positioning point corresponding to the known distance in the image;
obtaining the offset between the origin of the coordinate system of the camera and the reference origin of the coordinate system of the machine tool according to the coordinate offset of the pixel coordinate of the first fixed point in the image and the pixel coordinate of the central point of the image and the scale of the image;
according to the correlation between the pixel coordinate system of the first acquisition point position image of the image acquisition device and the camera coordinate system corresponding to the first acquisition point position image and the correlation between the camera coordinate system and the machine tool coordinate system, the correlation between the pixel coordinate system of the first acquisition point position image and the machine tool coordinate system is obtained, and then the pixel coordinate system is correlated with the machine tool coordinate system to determine the accurate positioning information of the workpiece to be measured in the machine tool coordinate system, wherein the accurate positioning information comprises positions and angles;
in this embodiment, in step S4, specifically, the conversion formula between the pixel coordinate system and the camera coordinate system is as follows:
Figure BDA0003184923950000101
wherein, S: scale length of the image; (u)0，v0): coordinates of an image coordinate origin in a pixel coordinate system of the image; (u, v): pixel point coordinates in the workpiece image; (X)c，Yc): coordinates in the camera coordinate system corresponding to pixel points of the workpiece image.
The coordinate transformation formula between the camera coordinate system and the machine coordinate system is as follows:
Figure BDA0003184923950000111
wherein, (X, Y): machine tool coordinates corresponding to pixel points of the workpiece image; (X)c，Yc): coordinates in the camera coordinate system corresponding to pixel points of the workpiece image; θ: the deflection angle of the camera coordinate system relative to the machine tool coordinate system; (U, V): actual offset between the camera coordinate system and the machine coordinate system.
Actual use on a machine tool with a cutting head: and (3) drilling a round hole on the workpiece by using the cutting head, setting the machine tool coordinate at the moment as an original point, controlling the cutting head to move a distance w in the positive direction of the Y axis, drilling a second round hole, and moving the cutting head back to the position for drilling for the first time. Then the cutting head is controlled to move to the height that the visual field range of the camera can contain two round holes in the Z-axis direction (the camera collects image information of the workpiece to be measured at the first collection point), and the camera is utilized to collect the image information of the workpiece to be measured at the current positionThe positions are continuously photographed for three times, and the pixel coordinates of the center of the first round hole in the corresponding image are detected to be P1(u1，v1)、P2(u2，v2)、P3(u3，v3) The pixel coordinate at the center of the second circular hole is Q1(u4，v4)、Q2(u5，v5)、Q3(u6，v6) Then, the average value is calculated, and when the machine coordinate is (0, 0), the pixel coordinate of the center of the first circular hole in the image is P0(up，vp)＝((u1+u2+u3)/3，(v1+v2+v3) /3) pixel coordinate at the center of the second circular hole is Q0(uQ，vQ)＝((u4+u5+u6)/3，(v4+v5+v6) And/3), obtaining the length of the scale of the image according to the ratio of the actual distance between the center points of the two circular holes to the pixel distance between the corresponding pixel coordinates in the image as follows:
Figure BDA0003184923950000112
and the actual offset between the camera coordinate system and the machine tool coordinate system is (U, V) D according to the pixel offset between the pixel coordinate of the first round hole in the image and the image center point and the scale length of the image(P，Q)((uP-u/2)，(vP-v/2)). And then, according to the pixel point coordinates of the two circular holes, the deflection angle w of the camera coordinate system relative to the machine tool coordinate system can be obtained as arctan ((u)Q-uP)/(vQ-vP) The relationship between the camera coordinate system and the machine tool coordinate system can be obtained, and the conversion relation between the camera coordinate system and the machine tool coordinate system is as follows:
Figure BDA0003184923950000113
w in the present embodiment is set according to actual conditions.
S5: and determining accurate positioning information of the workpiece at the position of the machine tool coordinate system. And (4) substituting the known parameters into the matrix formula according to the matrix formula in the step S4 to obtain the accurate positioning information of the workpiece to be measured including the position and the angle in the machine tool coordinate system.
Example two:
a method for the precise positioning of a workpiece in a position on a machine tool for associating the workpiece to be measured with a coordinate system of the machine tool, comprising the steps of:
s1: providing an image acquisition device which has a relative position relation with the machine tool; the image acquisition device in the embodiment is an industrial camera, and before the industrial camera acquires an image of a workpiece to be detected, at least a first positioning point and a second positioning point are arranged on the workpiece in a first image range, and the first positioning point is used as an origin of machine tool coordinates; the industrial camera is then adjusted to a height within the photographing field of view at least sufficient to encompass the first location point and the second location point.
The specific parameters of the camera in the embodiment are that the visual field range of the image is 500mm multiplied by 500mm, the distance between the camera and the object to be measured is 500mm, and the measurement precision of the image is 0.05 mm; camera Basler _ acA2440-75 uc: the frame rate reaches 75fps, the resolution is 500 ten thousand pixels (2448px multiplied by 2048px), the chip size is 8.4mm multiplied by 7.1mm, the chip type CMOS is adopted, the interface usb is 3.0, and the color camera is adopted; lens ML-M0822 UR: 8mm lens, object distance 580mm, field of view 660 × 500 mm. If the 1/5 sub-pixel edge detection algorithm is adopted, the horizontal measurement precision of the workpiece image can reach 0.054mm/px, and the vertical measurement precision can reach 0.048 mm/px.
Step S1 in this embodiment further includes: an industrial light source and a polarizer are arranged for polishing a workpiece to be measured.
S2: acquiring a workpiece to be detected at multiple points through an image acquisition device, and acquiring multi-point image information of the workpiece to be detected on a machine tool operating table; the workpiece position does not need to be moved manually, and the workpiece image information can be collected only by moving the industrial camera on the machine tool.
Step S2 further includes: the industrial light source irradiates the workpiece to be detected at a certain angle on one side or multiple sides, and the edge characteristics of the workpiece to be detected are highlighted, so that the method is suitable for the imaging occasion of the workpiece to be detected to reduce the reflection phenomenon of the metal workpiece; and the polarizer is arranged on the lens, so that the interference effects of astigmatism, reflection, glare and the like are weakened or eliminated, the reflection phenomenon of a large workpiece can be eliminated to a certain extent by the matched use of the industrial light source and the polarizer, and the unfavorable image caused by the reflection of the large workpiece to the later image processing is avoided. In other embodiments, the workpiece to be detected can be polished from above, and the method utilizes a large-scale backlight source to illuminate the surface of the metal workpiece completely, so that the problem of uneven image brightness caused by light reflection is avoided. Specifically, the industrial light source in this embodiment is an LED strip light source, the size of the light source is 600mm × 50mm, and the LED strip light source is mainly used for irradiating a workpiece to be measured at a certain angle on one side or multiple sides, and protruding the edge characteristics of the workpiece to be measured, and is suitable for imaging occasions of large-sized workpieces. The workpiece to be measured is polished by a method of polishing the workpiece from the side by a plurality of light sources, so that the reflection phenomenon of the metal workpiece is reduced.
In other embodiments, for workpieces with unobvious features, the following method is adopted to add feature points: a1: placing some feature blocks near the overlapping area of the images, thereby increasing the feature points of the images for improving the precision and speed of image splicing; a2: adding some characteristic points on the surface of the workpiece in the image overlapping area by using a marking pen, wherein the characteristic points are used for image splicing scenes which can be painted on the surface of the workpiece, and the image splicing speed and precision are improved; a3: the projector is used for projecting pictures on the surface of the workpiece, so that the feature points of the workpiece image are increased, the workload of an operator is reduced, and the image splicing speed and precision are improved. In an image splicing scene painted on the surface of a workpiece, an operator can add characteristic points on the surface of an image overlapping area of the workpiece by using a marking pen to improve the speed and the precision of image splicing; the projector is used for projecting pictures on the surface of the workpiece, so that the characteristic points of the workpiece image are increased, the workload of an operator is reduced, and the image splicing speed and precision are improved; placing some feature blocks near the overlapping area of the images, thereby increasing the feature points of the images for improving the precision and speed of image splicing; by increasing the characteristic points of the image by using different methods in different application scenes, the speed and the precision of image splicing can be improved. It should be noted that the application scenario of the a1 method for adding feature points is for smooth metal workpieces with unobvious features, and some feature blocks can be placed near the overlapping region of the images, so that the feature points of the images are increased, and the accuracy and speed of the image stitching algorithm can be improved to a certain extent; the method is suitable for image splicing scenes in which marks cannot be painted on the surface of the workpiece or objects cannot contact the surface of the workpiece, and the feature blocks can be reused, so that the cost is saved.
S3: image splicing is carried out on the image information in the step S2, and then outline information of the workpiece is extracted to obtain pixel coordinate information of the workpiece image; in this embodiment, the image stitching method is implemented based on a homography transformation matrix, and includes the following steps:
q1: extracting feature points of adjacent images by using a sift feature extraction algorithm;
q2: carrying out feature matching on feature points in adjacent images by using a KNN matching algorithm;
q3: purifying the feature matching pairs by using an RANSAC algorithm to eliminate wrong matching pairs;
q4: then calculating homography transformation matrix of the two images according to the purified feature matching pair,
q5: and projecting the second image onto the first image according to the homography transformation matrix of the two images to complete the splicing of the two images, and repeating the operation steps to finally obtain a complete workpiece splicing image. The image splicing method of the homography transformation matrix is used for splicing images of workpieces to be detected acquired by an image acquisition device at multiple points to obtain complete workpiece image information.
In this embodiment, in order to deal with the situation that the acquired image information is not clear due to the problem that the image information acquisition device is easily subjected to an external environment or the machine tool itself when the images are spliced, a preprocessing process is provided before step S4 to improve the definition of the image information, and the preprocessing process includes the following steps:
m1: the image denoising is used for eliminating or inhibiting the influence of noise on the image and realizing the smoothing of the image;
m2: the image enhancement is used for enhancing the contrast of the image and enabling the image to be clearer;
m3: and image correction is used for carrying out distortion correction on the image.
The method comprises the steps of preprocessing, collecting images of a workpiece to be detected at multiple points of an image collecting device, optimizing, eliminating or inhibiting the influence of noise on the images in an image denoising step to obtain smooth images, enhancing the contrast of the images in an image enhancing step to obtain clear images, and performing distortion correction on the images in an image correcting step to obtain smooth, clear and accurate image information of the workpiece.
In this embodiment, the image denoising is an image denoising method based on morphological processing, and since noise brings great obstruction and influence to subsequent image processing, the noise of the image needs to be effectively suppressed or eliminated, so as to achieve a smoothing effect of the image. The morphological processing is to eliminate the noise of the image on the basis of keeping the image contour, and mainly comprises four basic operations: corrosion, expansion, opening operation and closing operation, wherein the corrosion and the expansion are basic morphological operators and are all processed aiming at white parts in the image; the principle of corrosion is to define a convolution kernel, convolve the kernel with the image, calculate the minimum value of the pixel points in the kernel coverage area and assign the minimum value to the pixel designated by the reference point, so that the highlight area in the image is gradually reduced, and the expansion is opposite to the highlight area. It should be noted that the invention adopts the method of firstly opening operation on the workpiece image and then closing operation to remove the noise point on the image without affecting the image edge information. The open operation is to perform erosion before expansion, and the closed operation is to perform expansion before erosion. In other embodiments, the image denoising adopts a filtering algorithm-based image denoising method, such as mean filtering, gaussian filtering, median filtering, and the like, and the filtering algorithm most suitable for the image processing scene is selected by comparing the denoising effects of different filtering; and other processing methods capable of eliminating image noise are within the scope of the present invention.
The image enhancement is an image enhancement method based on histogram equalization, and the method mainly aims at the problems that the characteristic points of a workpiece image are sparse and the brightness is not uniform due to the fact that a light source shines from the side.
The image correction is an image correction method based on camera calibration, and the actual operation is that the same calibration plate is photographed for multiple times by using a camera from different angles and different heights, about ten calibration plate images are collected, then the camera is calibrated by using pixel coordinates of angular points in each image and physical coordinates of each angular point under a world coordinate system according to a Zhang-friend calibration method, further an internal and external reference matrix of the camera and a distortion coefficient of a lens are obtained, and finally distortion correction is carried out on a workpiece image according to the internal reference matrix and the distortion coefficient.
The invention also includes a method for detecting the splicing error, firstly, the ratio of the actual length of a unit grid in the image and the number of the occupied pixel points is collected by a standard chessboard as the scale of the image, then the pixel value of the side to be measured is obtained by the spliced image of the workpiece, and then the actual length is calculated according to the scale; the workpiece images with calibration plates placed in the overlapping areas are spliced, sub-pixel corner coordinates at the splicing positions of the calibration plates are extracted by using a corner detection algorithm, the number of pixels occupied by the cells at the splicing positions is calculated, the theoretical length of the cells at the splicing positions is calculated according to the scale of the images, the theoretical length of the cells at the splicing positions is compared with the actual length of the cells, and the splicing error of the images is solved.
S4: acquiring the correlation between the pixel coordinate system of the workpiece image and the machine tool coordinate system according to the correlation information between the camera coordinate and the machine tool coordinate and the correlation information between the pixel coordinate system of the workpiece image and the camera coordinate system where the image acquisition device is located;
step S4 further includes:
acquiring pixel coordinates of an image center under pixel coordinates according to image information of the workpiece to be detected at a first acquisition point;
obtaining a scale of the image according to the known distance of the machine tool moving between the first positioning point and the second positioning point and the distance between the pixel coordinates of the first positioning point and the second positioning point corresponding to the known distance in the image;
obtaining the offset between the origin of the coordinate system of the camera and the reference origin of the coordinate system of the machine tool according to the coordinate offset of the pixel coordinate of the first fixed point in the image and the pixel coordinate of the central point of the image and the scale of the image;
the method comprises the steps of obtaining the mutual relation between a pixel coordinate system of a first acquisition point position image and a machine tool coordinate system according to the mutual relation between the pixel coordinate system of the first acquisition point position image of an image acquisition device and a corresponding camera coordinate system of the image acquisition device and the mutual relation between the camera coordinate system and the machine tool coordinate system, converting the pixel coordinate systems of other acquisition point position images except the first acquisition point position image into the pixel coordinate system of the first acquisition point position image through a splicing process, obtaining a global pixel coordinate system of a spliced image of the whole workpiece, further associating the pixel coordinate system with the machine tool coordinate system, and determining accurate positioning information of the workpiece to be measured including position and angle in the machine tool coordinate system.
In this embodiment, in step S4, specifically, the conversion formula between the pixel coordinate system and the camera coordinate system is as follows:
Figure BDA0003184923950000151
wherein, S: scale length of the image; (u)0，v0): coordinates of an image coordinate origin in a pixel coordinate system of the image; (u, v): pixel point coordinates in the workpiece image; (X)c，Yc): coordinates in the camera coordinate system corresponding to pixel points of the workpiece image.
The coordinate transformation formula between the camera coordinate system and the machine coordinate system is as follows:
Figure BDA0003184923950000152
wherein, (X, Y): machine tool coordinates corresponding to pixel points of the workpiece image; (X)c，Yc): coordinates in the camera coordinate system corresponding to pixel points of the workpiece image; θ: the deflection angle of the camera coordinate system relative to the machine tool coordinate system; (U, V): actual offset between the camera coordinate system and the machine coordinate system.
Actual use on a machine tool with a cutting head: and (3) drilling a round hole on the workpiece by using the cutting head, setting the machine tool coordinate at the moment as an original point, controlling the cutting head to move a distance w in the positive direction of the Y axis, drilling a second round hole, and moving the cutting head back to the position for drilling for the first time. Then the cutting head is controlled to move in the Z-axis direction to a position where the visual field range of the camera can contain the height of two round holes (preferably the height of the camera for shooting the first image of the workpiece), the camera is used for continuously shooting three times at the current position, and the pixel coordinates of the center of the first round hole in the corresponding image are detected to be P respectively1(u1，v1)、P2(u2，v2)、P3(u3，v3) The pixel coordinate at the center of the second circular hole is Q1(u4，v4)、Q2(u5，v5)、Q3(u6，v6) Then, the average value is calculated, and when the machine coordinate is (0, 0), the pixel coordinate of the center of the first circular hole in the image is P0(up，vp)＝((u1+u2+u3)/3，(v1+v2+v3) /3) pixel coordinate at the center of the second circular hole is Q0(uQ，vQ)＝((u4+u5+u6)/3，(v4+v5+v6) And/3), obtaining the length of the scale of the image according to the ratio of the actual distance between the center points of the two circular holes to the pixel distance between the corresponding pixel coordinates in the image as follows:
Figure BDA0003184923950000161
and the actual offset between the camera coordinate system and the machine tool coordinate system is (U, V) D according to the pixel offset between the pixel coordinate of the first round hole in the image and the image center point and the scale length of the image(P，Q)((uP-u/2)，(vP-v 2. And then, according to the pixel point coordinates of the two circular holes, the deflection angle w of the camera coordinate system relative to the machine tool coordinate system can be obtained as arctan ((u)Q-uP)/(vQ-vP) The relationship between the camera coordinate system and the machine tool coordinate system can be obtained, and the conversion relation between the camera coordinate system and the machine tool coordinate system is as follows:
Figure BDA0003184923950000162
w in the present embodiment is set according to actual conditions.
S5: precise positioning information of the workpiece including position and angle in a machine coordinate system is determined. The precise positioning information of the workpiece in the machine coordinate system including the position and the angle can be obtained by substituting the known parameters into the matrix formula according to the matrix formula in step S4.
The practical use of the embodiment on a machine tool with a cutting head: and drilling a round hole on the workpiece by using the cutting head as a first positioning point, setting the machine tool coordinate at the moment as an original point, controlling the cutting head to move a distance w in the positive direction of the Y axis, drilling a second round hole as a second positioning point, and moving the cutting head back to the position for drilling for the first time. Then the cutting head is controlled to move in the Z-axis direction to the visual field range of the camera, the height of two round holes can be included (preferably, the camera acquires image information of a workpiece to be detected at a first acquisition point position), the camera is used for continuously taking a picture for three times at the current position, and the pixel coordinates of the center of the first round hole in a corresponding image are detected to be P respectively1(u1，v1)、P2(u2，v2)、P3(u3，v3) The pixel coordinate at the center of the second circular hole is Q1(u4，v4)、Q2(u5，v5)、Q3(u6，v6) Then, the average value is calculated, and when the machine coordinate is (0, 0), the pixel coordinate of the center of the first circular hole in the image is P0(up，vp)＝((u1+u2+u3)/3，(v1+v2+v3) /3) pixel coordinate at the center of the second circular hole is Q0(uQ，vQ)＝((u4+u5+u6)/3，(v4+v5+v6) And/3), obtaining the length of the scale of the image according to the ratio of the actual distance between the center points of the two circular holes to the pixel distance between the corresponding pixel coordinates in the image as follows:
Figure BDA0003184923950000171
and the pixel coordinate of the central point of the image in the pixel coordinate system is (u)0，v0) And (U/2, V/2), obtaining the actual offset between the camera coordinate system and the machine tool coordinate system as (U, V) according to the pixel offset between the pixel coordinate of the first round hole in the image and the image center point and the scale length of the image, wherein the actual offset is (U, V) × (S × (U ×)P-u0)，S×(vP-v0)). And then, according to the pixel point coordinates of the two circular holes, the deflection angle theta of the camera coordinate system relative to the machine tool coordinate system can be obtained as arctan ((u)Q-uP)/(vQ-vP) The correlation between the camera coordinate system and the machine tool coordinate system can be obtained, and the coordinate transformation formula between the camera coordinate system and the machine tool coordinate system is as follows:
Figure BDA0003184923950000172
(X, Y): machine tool coordinates corresponding to pixel points of the workpiece image; (X)c，Yc): coordinates in the camera coordinate system corresponding to pixel points of the workpiece image; θ: the deflection angle of the camera coordinate system relative to the machine tool coordinate system; (U, V): reality between camera coordinate system and machine coordinate systemAn offset.
In combination with the imaging principle of the camera, the coordinate (u) of the image coordinate origin in the pixel coordinate system can be determined according to the image scale S0，v0) Finding the camera coordinates (X)c，Yc) The coordinate transformation formula of the correlation with the first image pixel coordinate (u, v) is as follows:
Figure BDA0003184923950000173
according to the correlation between the pixel coordinate system of the first image and the corresponding camera coordinate system and the correlation between the camera coordinate system and the machine tool coordinate system, the correlation between the pixel coordinate system of the first image and the machine tool coordinate system can be obtained, so that the pixel coordinate system of the whole workpiece splicing image is associated with the machine tool coordinate system, and a coordinate transformation formula between the pixel coordinate system of the whole workpiece splicing image and the machine tool coordinate system is as follows:
Figure BDA0003184923950000174
further, the following formula is obtained:
Figure BDA0003184923950000181
the formula of this example was examined by setting w to 200 mm;
(1) punching a round hole on the steel plate by using a cutting head, and setting the machine tool coordinate at the moment as an original point (0, 0);
(2) controlling the cutting head to do vector motion towards the positive direction of the Y axis, and drilling a second round hole at the position of the machine tool with the coordinate of (0, 200);
(3) the cutting head is moved back again to the position at the time of the first punching, and then the cutting head is controlled to move in the Z-axis direction to a height at which the field of view of the camera can contain two circular holes. And continuously photographing for 3 times at the current position by using a camera, and detecting sub-pixel coordinates of the centers of two round holes in the three images.
Comparing the extracted pixel coordinates of each image, it can be found that the extracted pixel coordinates for the same point are not exactly the same, so the pixel coordinates are averaged here.
(4) By detecting pixel coordinates and averaging, the sub-pixel coordinates of the center of the first round hole in the image are (592.514, 770.605), the sub-pixel coordinates of the center of the second round hole are (585.474, 355.287), and the sub-pixel corner point coordinates of the upper left corner of the steel plate are (19.545, 51.587). The pixel distance between the two points is 415.37766px, the actual distance between the two points is 200mm, the scale S of the image is 0.4815mm/px, and the deflection angle θ of the machine coordinate system with respect to the camera coordinate system is 0.97 °, which is obtained from the sub-pixel coordinates of the centers of the first and second circular holes. Knowing the size of the image as (605, 806), the center point coordinates (u) of the image0，v0) The offset from the center point of the first circular hole to the center point of the image is (290.014, 367.605) (302.5, 403), and the offset of the machine coordinate system from the camera coordinate system is (U, V) (139.642, 177.002) according to the scale of the image. Changing S to 0.4815mm/px, (u)0，v0) The following conversion equation of machine coordinates and image pixel coordinates is substituted for (302.5, 403), (U, V) ═ 0.97 ° θ (139.642, 177.002):
Figure BDA0003184923950000182
obtaining:
Figure BDA0003184923950000183
(5) and (3) verification: substituting the pixel coordinates (592.514, 770.605) of the center of the first round hole into a coordinate transformation formula to obtain machine tool coordinates (-0.017, -0.052); substituting the pixel coordinates (585.474, 355.287) of the center of the second round hole into a coordinate transformation formula to obtain machine tool coordinates (-0.021, 200.016); and substituting the pixel coordinates (19.545, 51.587) of the corner point at the upper left corner of the steel plate into a coordinate transformation formula to obtain the coordinates (-269.984, 350.830) of the machine tool. The cutting head is controlled to move to the position with machine tool coordinates (-269.984, 350.830), and the cutting head is found to be just above the upper left corner of the steel plate, so that the coordinate transformation formula of the image pixel coordinates and the corresponding machine tool coordinates is established.
In addition, a third hole can be drilled on the workpiece in the image range, the machine tool coordinate at the time can be recorded, the three round holes are continuously photographed by using the image acquisition device, the pixel coordinate of the center of the round hole is detected and an average value is obtained, wherein the pixel coordinates of the first round hole and the second round hole are used for calculating a coordinate transformation formula of the image pixel coordinate and the machine tool coordinate, the pixel coordinate of the third hole is substituted into the formula to obtain the machine tool coordinate corresponding to the third hole, and the machine tool coordinate is compared with the recorded machine tool coordinate to further verify the accuracy of the coordinate transformation formula. And punching a fourth hole on the workpiece outside the image range, recording the machine tool coordinate at the moment, acquiring workpiece image information on the workpiece multi-point image, splicing the images, detecting the pixel coordinate of the centers of four circular holes on the spliced image, substituting the pixel coordinate of the fourth circular hole into the coordinate transformation formula to obtain the machine tool coordinate corresponding to the coordinate transformation formula, and comparing the machine tool coordinate with the recorded machine tool coordinate to verify whether the coordinate transformation formula is suitable for the spliced image of the whole workpiece.
It should be noted that the first positioning point and the second positioning point are characteristic points marked on the workpiece to be measured, and the first positioning point and the second positioning point are circular hole-shaped structures in this embodiment, and may also be angular points or intersection points in other embodiments. Such a positioning feature usually occupies a plurality of pixels, and the edge of the positioning feature is smooth and fuzzy, but a pixel area occupied by one positioning feature is a coordinate that cannot be used as a positioning point, and usually a coordinate corresponding to a central position of the positioning feature area or a position where the gray scale change of the positioning feature area is most intense needs to be calculated. The gray distribution characteristic of the pixel region occupied by one positioning feature is characterized in that the gray change at the center is strongest, and the farther the distance from the center is, the weaker the gray change is. In the embodiment, a sub-pixel positioning algorithm is adopted to realize accurate positioning of the positioning features, and the algorithm has the precondition that the positioning target is not a single pixel point and is necessarily composed of pixel points with certain gray distribution and distribution shapes.
The sub-pixel positioning algorithm comprises the following implementation steps:
(1) coarse positioning: finding a pixel in a pixel area occupied by the positioning characteristics by using a Shi-Tomasi corner detection algorithm as a target range of fixed point coordinates, and taking the center of the pixel as a pixel-level precision coordinate of the positioning point so as to realize coarse positioning of the positioning point;
(2) determining a search area: in order to improve the precision and reduce the computation amount, taking the pixel determined by the original coarse positioning as the center, increasing M pixel columns on the left and the right respectively, and increasing N pixel rows on the upper and the lower respectively to form a rectangular search area with the width of 2M +1 pixels and the height of 2N +1 pixels;
(3) fine positioning: and selecting a proper sub-pixel subdivision algorithm for fine positioning according to the characteristics of the gray level change and the distribution of the pixels in the search area to obtain the sub-pixel precision coordinates of the positioning points. The sub-pixel subdivision algorithm comprises several algorithms, a moment estimation method and an interpolation method; geometric methods include centroid methods and gray scale centroid methods; the moment estimation method comprises a space moment method, a gray moment method and an orthogonal moment method; interpolation methods include linear interpolation, curved interpolation, and polynomial interpolation.
The sub-pixel positioning algorithm can be used for detecting the sub-pixel precision coordinates of two positioning features in the image information, so that the positioning features can be accurately positioned; the optimal method is to shoot a plurality of images at the same point, and the coordinates of the obtained locating point are the average value of the sub-pixel coordinates of the locating point obtained by the plurality of images. Consider then the case where the locating feature in this embodiment is a round hole feature. If the center of the circular hole feature is to be found as the coordinate of the positioning point to realize accurate positioning, a target area (usually a rectangle) needs to be found by using a template matching algorithm so as to realize coarse positioning, then the contour of the circular hole is obtained by using a contour extraction algorithm, then sub-pixel points of the edge are further extracted by using a sub-pixel edge detection technology, and finally the coordinate of the sub-pixel precision of the center of the circular hole feature is calculated by using a robust least square fitting circle method.
Need to explain: before the image scale is obtained, in order to ensure equal-precision imaging of a workpiece to be measured, distortion correction needs to be carried out on a collected image, and an imaging plane of a camera needs to be parallel to a measured plane. In the embodiment, a non-distortion focal plane projection mathematical model parallel to the measurement plane is established in a mode of calibrating camera parameters, so that equal-precision mapping of pixel points and elimination of image distortion are realized.
In addition, distortion correction can be performed on the image according to the calibrated camera internal reference matrix and the distortion coefficient, euler angle sequence transformation is performed on the external reference matrix, the deflection angle of the camera coordinate system relative to the machine tool coordinate system in the direction of the X, Y, Z axis is obtained, the deflection angles of the camera coordinate system in the directions of the X axis and the Y axis are smaller than the threshold value through the two-degree-of-freedom fine adjustment device, the optical center of the camera is perpendicular to the measured plane, and therefore the alignment of the camera is achieved.
Example three:
the embodiment provides a machine tool, which comprises a machine tool body, an image acquisition device and a processor, wherein the image acquisition device is used for controlling the machine tool to drive the machine tool to perform vector motion, and the processor executes the method for accurately positioning the position of the workpiece on the machine tool in the first embodiment or the second embodiment. The method for accurately positioning the position of the workpiece on the machine tool can enable the position of the workpiece on the machine tool to be quickly and accurately positioned. The machine tool further comprises a light supplementing device, wherein the light supplementing device comprises a movable support and a light source, the light source is installed on the movable support, and the movable support is arranged at a proper position of the machine tool and used for supplementing light to a workpiece to be detected by the light source. The light supplementing device is additionally arranged outside the machine tool, the light source irradiates on the workpiece, the edge characteristics of the workpiece to be detected are highlighted, and the image acquisition device can conveniently acquire the image information of the workpiece to be detected.
Example four:
the present embodiment provides a storage medium storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to perform the method for accurately positioning a workpiece on a machine tool according to the first embodiment or the second embodiment. The storage medium in this embodiment may be connected to a control system of an existing machine tool, so that the existing machine tool can achieve accurate positioning of a position of a workpiece on the machine tool.
Example five:
this embodiment proposes a vision system comprising: an image receiving module: the device is used for receiving multi-point position acquisition of a workpiece to be detected through an image acquisition device and sending multi-point position image information of the workpiece to be detected on a machine tool operating table; an image stitching module: the image splicing device is used for splicing the image information, extracting the outline information of the workpiece and obtaining the pixel coordinate information of the workpiece image; a correlation module: the system comprises a camera coordinate acquisition device, a coordinate acquisition device and a coordinate acquisition device, wherein the camera coordinate acquisition device is used for acquiring the correlation information of a workpiece image and a machine tool coordinate; a positioning information determination module: precise positioning information of the workpiece in a machine coordinate system including at least one of position and angle is determined. An image receiving module in the visual system receives an image of a workpiece to be detected acquired by a multi-point position of an image acquisition device, transmits the image to an image splicing module for image information splicing to obtain complete workpiece contour information, obtains a pixel coordinate system of the workpiece image, then passes through a correlation module to correlate the pixel coordinate system with a camera coordinate system, then passes through a positioning information determination module to determine the workpiece in a machine tool coordinate system, and finally completes accurate point location of the workpiece on the machine tool. It should be noted that the vision system in this embodiment has a processor for providing operation processing to each module of the vision system. It should be noted that a vision system in this embodiment may be integrated into a program embedded in a control system of an existing machine tool, so that the existing machine tool can achieve accurate positioning of a position of a workpiece on the machine tool.
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, modifications, or combinations may be made by those skilled in the art within the scope of the 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 (14)

1. A method for the precise positioning of a workpiece in a position on a machine tool for associating the workpiece to be measured with a coordinate system of the machine tool, characterized in that it comprises the following steps:
s1: providing an image acquisition device which has a relative position relation with the machine tool;
s2: acquiring the workpiece to be detected through a plurality of point positions by the image acquisition device to acquire image information of the workpiece to be detected on the machine tool;
s3: acquiring pixel coordinate information of the workpiece image to be detected through the workpiece image information to be detected in the step S2;
s4: obtaining the correlation between the pixel coordinate system of the workpiece image to be measured and the machine tool coordinate system through the correlation information between the camera coordinate system and the machine tool coordinate system and the correlation information between the coordinate information of the workpiece image to be measured and the camera coordinate system where the image acquisition device is located;
s5: and determining accurate positioning information of the workpiece at the position of the machine tool coordinate system.
2. The method according to claim 1, wherein the image capturing device captures the workpiece to be measured through a single-point position in step S2 to obtain image information of the workpiece to be measured on the machine tool.
3. The method according to claim 1, wherein the image acquisition device in step S2 acquires the image information of the workpiece to be measured on the machine tool at multiple points by acquiring the workpiece to be measured at multiple points;
the step S3 further includes an image stitching process, where the image information acquired at multiple positions in the step S2 is subjected to image stitching, and the contour information of the workpiece to be detected is extracted to obtain the pixel coordinate information of the image of the workpiece to be detected.
4. A method of accurately positioning a workpiece on a machine tool according to claim 2 or 3,
before step S4, the method further includes:
the first acquisition point is provided with at least a first positioning point and a second positioning point on the workpiece to be detected within the image range of the workpiece to be detected, the first positioning point is used as a reference origin of the machine tool coordinate system,
step S4 further includes:
and obtaining the deflection angle of the camera coordinate system relative to the machine tool coordinate system according to the pixel center point coordinates of the first positioning point and the second positioning point, thereby obtaining the accurate positioning information of the workpiece including the position and the angle in the machine tool coordinate system.
5. A method of accurately positioning a workpiece on a machine tool according to claim 4,
step S4 further includes:
acquiring pixel coordinates of an image center under pixel coordinates according to image information of the workpiece to be detected at a first acquisition point;
obtaining a scale of the image according to the known distance between the first positioning point and the second positioning point of the machine tool and the distance between the pixel coordinates of the first positioning point and the second positioning point corresponding to the known distance in the image;
obtaining the offset between the origin of the coordinate system of the camera and the reference origin of the coordinate system of the machine tool according to the coordinate offset of the pixel coordinate of the first fixed point in the image and the pixel coordinate of the central point of the image and the scale of the image;
when the image acquisition device acquires the image information of the workpiece to be detected through a single point, according to the correlation between the pixel coordinate system of the first acquisition point image of the image acquisition device and the corresponding camera coordinate system and the correlation between the camera coordinate system and the machine tool coordinate system, the correlation between the pixel coordinate system of the first acquisition point image and the machine tool coordinate system is obtained, and then the pixel coordinate system is correlated with the machine tool coordinate system to determine the accurate positioning information of the workpiece to be detected including the position and the angle in the machine tool coordinate system;
when the image acquisition device acquires the image information of the workpiece to be measured through multiple points, the mutual relation between the pixel coordinate system of the first acquisition point position image of the image acquisition device and the corresponding camera coordinate system and the mutual relation between the camera coordinate system and the machine tool coordinate system are obtained, then the pixel coordinate system of other acquisition point position images except the first acquisition point position is converted into the pixel coordinate system of the first acquisition point position image through the splicing process, so that the global pixel coordinate system of the spliced image of the whole workpiece is obtained, the pixel coordinate system is further associated with the machine tool coordinate system, and the accurate positioning information of the workpiece to be measured including the position and the angle in the machine tool coordinate system is determined.
6. A method of accurately positioning a workpiece on a machine tool according to claim 5, wherein the conversion formula of the pixel coordinate system and the camera coordinate system is as follows:
Figure FDA0003184923940000021
wherein, S: scale length of the image;
(u0，v0): coordinates of an image coordinate origin in a pixel coordinate system of the image;
(u, v): pixel point coordinates in the workpiece image;
(Xc，Yc): coordinates in the camera coordinate system corresponding to pixel points of the workpiece image.
7. A method for the accurate positioning of a workpiece on a machine tool according to claim 5, characterized in that the coordinate transformation between the camera coordinate system and the machine coordinate system is as follows:
Figure FDA0003184923940000031
wherein, θ: the deflection angle of the camera coordinate system relative to the machine tool coordinate system;
(U, V): offset between the camera coordinate system and the machine tool coordinate system;
(X, Y): machine tool coordinates corresponding to pixel points of the workpiece image;
(Xc，Yc): coordinates in the camera coordinate system corresponding to pixel points of the workpiece image.
8. Method for the precise positioning of a workpiece in position on a machine tool according to claim 1, 2 or 3,
step S1 further includes: setting an industrial light source and a polarizer for polishing a workpiece to be detected;
step S2 further includes: the industrial light source irradiates a workpiece to be detected at a certain angle on one side or multiple sides, and the edge characteristics of the workpiece to be detected are highlighted, so that the industrial light source is suitable for imaging occasions of large-size workpieces, and the light reflection phenomenon of metal workpieces is reduced; the polarizer mounted on the lens weakens or eliminates the interference effect of astigmatism, reflection, glare and the like.
9. The method for accurately positioning the position of a workpiece on a machine tool according to claim 3, wherein the splicing method in the step S3 is an image splicing method based on a homography transformation matrix, and the image splicing method of the homography transformation matrix comprises the following steps:
q1: extracting feature points of adjacent images by using a sift feature extraction algorithm;
q2: carrying out feature matching on feature points in adjacent images by using a KNN matching algorithm;
q3: purifying the feature matching pairs by using an RANSAC algorithm to eliminate wrong matching pairs;
q4: then calculating homography transformation matrix of the two images according to the purified feature matching pair,
q5: and projecting the second image onto the first image according to the homography transformation matrix of the two images to complete the splicing of the two images, and repeating the operation steps to finally obtain a complete workpiece splicing image.
10. A method of accurately positioning a workpiece on a machine tool as defined in claim 3, further comprising:
for the workpieces with unobvious features, adding feature points in the following way: a1: placing some feature blocks near the overlapping area of the images, thereby increasing the feature points of the images for improving the precision and speed of image splicing; a2: adding some characteristic points on the surface of the workpiece in the image overlapping area by using a marking pen directly, wherein the characteristic points are used for image splicing scenes which can be painted on the surface of the workpiece, and the image splicing speed and precision are improved; a3: the projector is used for projecting the pattern on the surface of the workpiece, so that the characteristic points of the workpiece image are increased, the workload of an operator is reduced, and the image splicing speed and precision are improved.
11. A method for accurately positioning a workpiece on a machine tool according to claim 1, wherein the step of S4 is preceded by a preprocessing process for improving the quality of the image information, the preprocessing process comprising the steps of:
m1: the image denoising is used for eliminating or inhibiting the influence of noise on the image and realizing the smoothing of the image;
m2: the image enhancement is used for enhancing the contrast of the image and enabling the image to be clearer;
m3: and image correction is used for carrying out distortion correction on the image.
12. A machine tool, comprising a machine tool body, characterized by further comprising: the device comprises an image acquisition device and a processor, wherein the image acquisition device is used for controlling the machine tool to drive the machine tool to do vector motion, the processor executes the method for accurately positioning the position of the workpiece on the machine tool according to any one of claims 1 to 11, the device further comprises a light supplementing device, the light supplementing device comprises a movable support and a light source, the light source is installed on the movable support, and the movable support is arranged at a proper position of the machine tool and is used for supplementing light for the workpiece to be measured by the light source.
13. A storage medium having computer-readable instructions stored thereon, which, when executed by one or more processors, cause the one or more processors to perform a method of fine positioning of a workpiece in a position on a machine tool as claimed in any one of claims 1 to 11.
14. A vision system, comprising:
an image receiving module: the multi-point image acquisition device is used for receiving multi-point acquisition of the workpiece to be detected through the image acquisition device and sending multi-point image information of the workpiece to be detected on the machine tool operating table;
an image stitching module: the image information is used for image splicing, and then the contour information of the workpiece is extracted to obtain the pixel coordinate information of the workpiece image;
a correlation module: the system comprises a camera coordinate system, an image acquisition device, a camera coordinate system and a data processing device, wherein the camera coordinate system is used for acquiring a coordinate system of a workpiece image;
a positioning information determination module: and determining accurate positioning information of the workpiece in a machine tool coordinate system including the position and the angle.
CN202110858443.4A 2021-07-28 2021-07-28 Method for accurately positioning position of workpiece on machine tool and vision system Pending CN113538583A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110858443.4A CN113538583A (en) 2021-07-28 2021-07-28 Method for accurately positioning position of workpiece on machine tool and vision system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110858443.4A CN113538583A (en) 2021-07-28 2021-07-28 Method for accurately positioning position of workpiece on machine tool and vision system

Publications (1)

Publication Number Publication Date
CN113538583A true CN113538583A (en) 2021-10-22

Family

ID=78089497

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110858443.4A Pending CN113538583A (en) 2021-07-28 2021-07-28 Method for accurately positioning position of workpiece on machine tool and vision system

Country Status (1)

Country Link
CN (1) CN113538583A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113828948A (en) * 2021-11-23 2021-12-24 济南邦德激光股份有限公司 Plate edge searching method, calibration system and edge searching system of laser cutting machine
CN115131553A (en) * 2022-08-30 2022-09-30 季华实验室 Shielding hole positioning method and device, electronic equipment and storage medium
CN116100145A (en) * 2023-04-10 2023-05-12 中科德迈(沈阳)激光技术有限公司 Water-guided laser positioning method and device, storage medium and water-guided laser equipment
TWI812002B (en) * 2022-02-10 2023-08-11 明新學校財團法人明新科技大學 Cutting tool image detecting method
CN116597014A (en) * 2023-07-19 2023-08-15 太仓庄正数控设备有限公司 Workpiece accurate positioning method and device of straightener

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113828948A (en) * 2021-11-23 2021-12-24 济南邦德激光股份有限公司 Plate edge searching method, calibration system and edge searching system of laser cutting machine
TWI812002B (en) * 2022-02-10 2023-08-11 明新學校財團法人明新科技大學 Cutting tool image detecting method
CN115131553A (en) * 2022-08-30 2022-09-30 季华实验室 Shielding hole positioning method and device, electronic equipment and storage medium
CN115131553B (en) * 2022-08-30 2022-11-08 季华实验室 Shielding hole positioning method and device, electronic equipment and storage medium
CN116100145A (en) * 2023-04-10 2023-05-12 中科德迈(沈阳)激光技术有限公司 Water-guided laser positioning method and device, storage medium and water-guided laser equipment
CN116597014A (en) * 2023-07-19 2023-08-15 太仓庄正数控设备有限公司 Workpiece accurate positioning method and device of straightener
CN116597014B (en) * 2023-07-19 2023-10-13 太仓庄正数控设备有限公司 Workpiece accurate positioning method and device of straightener

Similar Documents

Publication Publication Date Title
CN113538583A (en) Method for accurately positioning position of workpiece on machine tool and vision system
US9124873B2 (en) System and method for finding correspondence between cameras in a three-dimensional vision system
CN108562250B (en) Keyboard keycap flatness rapid measurement method and device based on structured light imaging
CN109029299B (en) Dual-camera measuring device and method for butt joint corner of cabin pin hole
CN110660107A (en) Plane calibration plate, calibration data acquisition method and system
CN108470356B (en) Target object rapid ranging method based on binocular vision
CN106780623A (en) A kind of robotic vision system quick calibrating method
CN108007388A (en) A kind of turntable angle high precision online measuring method based on machine vision
CN113269762B (en) Screen defect detection method, system and computer storage medium
CN110033407B (en) Shield tunnel surface image calibration method, splicing method and splicing system
US10535157B2 (en) Positioning and measuring system based on image scale
CN111508032B (en) Method for sorting feature points in camera calibration process
JP2021168143A (en) System and method for efficiently scoring probe in image by vision system
CN111062940A (en) Screw positioning and identifying method based on machine vision
CN106952262B (en) Ship plate machining precision analysis method based on stereoscopic vision
CN111707187A (en) Measuring method and system for large part
CN110640303B (en) High-precision vision positioning system and positioning calibration method thereof
CN111915485A (en) Rapid splicing method and system for feature point sparse workpiece images
CN114979469A (en) Camera mechanical error calibration method and system based on machine vision comparison
Wohlfeil et al. Automatic camera system calibration with a chessboard enabling full image coverage
CN111932517B (en) Contour mapping method and device for residual plate, electronic equipment and storage medium
CN114964032B (en) Blind hole depth measurement method and device based on machine vision
CN113538399A (en) Method for obtaining accurate contour of workpiece, machine tool and storage medium
WO2017107564A1 (en) Board image acquisition method and system
CN115661256A (en) Method for calculating deflection angle between camera and carrying platform, calibration plate and detection device

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